How Cepsa used Amazon SageMaker and Amazon Step Functions to industrialize their ML projects and operate their models at scale

海外精选
海外精选的内容汇集了全球优质的亚马逊云科技相关技术内容。同时,内容中提到的“AWS” 是 “Amazon Web Services” 的缩写,在此网站不作为商标展示。
0
0
{"value":"This blog post is co-authored by Guillermo Ribeiro, Sr. Data Scientist at Cepsa.\n\nMachine learning (ML) has rapidly evolved from being a fashionable trend emerging from academic environments and innovation departments to becoming a key means to deliver value across businesses in every industry. This transition from experiments in laboratories to solving real-world problems in production environments goes hand in hand with [MLOps](https://aws.amazon.com/sagemaker/mlops/), or the adaptation of DevOps to the ML world.\n\nMLOps helps streamline and automate the full lifecycle of an ML model, putting its focus on the source datasets, experiment reproducibility, ML algorithm code, and model quality.\n\nAt [Cepsa](https://www.cepsa.com/en), a global energy company, we use ML to tackle complex problems across our lines of businesses, from doing predictive maintenance for industrial equipment to monitoring and improving petrochemical processes at our refineries.\n\nIn this post, we discuss how we built our reference architecture for MLOps using the following key AWS services:\n\n- [Amazon SageMaker](https://aws.amazon.com/sagemaker/), a service to build, train, and deploy ML models\n- [AWS Step Functions](https://aws.amazon.com/step-functions/), a serverless low-code visual workflow service used to orchestrate and automate processes\n- [Amazon EventBridge](https://aws.amazon.com/eventbridge/), a serverless event bus\n- [AWS Lambda](https://aws.amazon.com/lambda/), a serverless compute service that allows you to run code without provisioning or managing servers\n\nWe also explain how we applied this reference architecture to bootstrap new ML projects in our company.\n\n#### **The challenge**\n\nDuring the last 4 years, multiple lines of business across Cepsa kicked off ML projects, but soon certain issues and limitations started to arise.\n\nWe didn’t have a reference architecture for ML, so each project followed a different implementation path, performing ad hoc model training and deployment. Without a common method to handle project code and parameters and without an ML model registry or versioning system, we lost the traceability amongst datasets, code, and models.\n\nWe also detected room for improvement in the way we operated models in production, because we didn’t monitor deployed models and therefore didn’t have the means to track model performance. As a consequence, we usually retrained models based on time schedules, because we lacked the right metrics to make informed retraining decisions.\n\n#### **The solution**\n\nStarting from the challenges we had to overcome, we designed a general solution that aimed to decouple data preparation, model training, inference, and model monitoring, and featured a centralized model registry. This way, we simplified managing environments across multiple AWS accounts, while introducing centralized model traceability.\n\nOur data scientists and developers use [AWS Cloud9](https://aws.amazon.com/cloud9/) (a cloud IDE for writing, running, and debugging code) for data wrangling and ML experimentation and GitHub as the Git code repository.\n\nAn automatic training workflow uses the code built by the data science team to [train models on SageMaker](https://aws.amazon.com/sagemaker/train/) and to register output models in the model registry.\n\nA different workflow manages model deployment: it obtains the reference from the model registry and creates an inference endpoint using [SageMaker model hosting features](https://aws.amazon.com/sagemaker/deploy/).\n\nWe implemented both model training and deployment workflows using Step Functions, because it provided a flexible framework that enables the creation of specific workflows for each project and orchestrates different AWS services and components in a straightforward way.\n\n#### **Data consumption model**\n\nIn Cepsa, we use a series of data lakes to cover diverse business needs, and all these data lakes share a common data consumption model that makes it easier for data engineers and data scientists to find and consume the data they need.\n\nTo easily handle costs and responsibilities, data lake environments are completely separated from data producer and consumer applications, and deployed in different AWS accounts belonging to a common AWS Organization.\n\nThe data used to train ML models and the data used as an inference input for trained models is made available from the different data lakes through a set of well-defined APIs using [Amazon API Gateway](https://aws.amazon.com/api-gateway/), a service to create, publish, maintain, monitor, and secure APIs at scale. The API backend uses [Amazon Athena](https://aws.amazon.com/athena/) (an interactive query service to analyze data using standard SQL) to access data that is already stored in [Amazon Simple Storage Service](http://aws.amazon.com/s3) ([Amazon S3](https://aws.amazon.com/cn/s3/?trk=cndc-detail)) and cataloged in the [AWS Glue](https://aws.amazon.com/glue/) Data Catalog.\n\nThe following diagram provides a general overview of Cepsa’s MLOps architecture.\n\n![image.png](1)\n\n#### **Model training**\n\nThe training process is independent for each model and handled by a [Step Functions standard workflow](https://docs.aws.amazon.com/step-functions/latest/dg/concepts-standard-vs-express.html), which gives us flexibility to model processes based on different project requirements. We have a defined a base template that we reuse on most projects, performing minor adjustments when required. For example, some project owners have decided to add manual gates to approve deployments of new production models, while other project owners have implemented their own error detection and retry mechanisms.\n\nWe also perform transformations on the input datasets used for model training. For this purpose, we use Lambda functions that are integrated in the training workflows. In some scenarios where more complex data transformations are required, we run our code in [Amazon Elastic Container Service](https://aws.amazon.com/ecs/) ([Amazon ECS](https://aws.amazon.com/cn/ecs/?trk=cndc-detail)) on [AWS Fargate](https://aws.amazon.com/fargate/), a serverless compute engine to run containers.\n\nOur data science team uses custom algorithms frequently, so we take advantage of the ability to [use custom containers in SageMaker model training](https://docs.aws.amazon.com/sagemaker/latest/dg/adapt-training-container.html), relying on [Amazon Elastic Container Registry](https://aws.amazon.com/ecr/) (Amazon ECR), a fully managed container registry that makes it easy to store, manage, share, and deploy container images.\n\nMost of our ML projects are based on the Scikit-learn library, so we have extended the standard [SageMaker Scikit-learn container](https://github.com/aws/sagemaker-scikit-learn-container) to include the environment variables required for the project, such as the Git repository information and deployment options.\n\nWith this approach, our data scientists just need to focus on developing the training algorithm and to specify the libraries required by the project. When they push code changes to the Git repository, our CI/CD system ([Jenkins](https://www.jenkins.io/) hosted on AWS) builds the container with the training code and libraries. This container is pushed to Amazon ECR and finally passed as a parameter to the SageMaker training invocation.\n\nWhen the training process is complete, the resulting model is stored in [Amazon S3](https://aws.amazon.com/cn/s3/?trk=cndc-detail), a reference is added in the model registry, and all the collected information and metrics are saved in the experiments catalog. This assures full reproducibility because the algorithm code and libraries are linked to the trained model along with the data associated to the experiment.\n\nThe following diagram illustrates the model training and retraining process.\n\n![image.png](2)\n\n#### **Model deployment**\n\nThe architecture is flexible and allows both automatic and manual deployments of the trained models. The model deployer workflow is automatically invoked by means of an event that SageMaker training publishes in EventBridge after training has finished, but it can also be manually invoked if needed, passing the right model version from the model registry. For more information about automatic invocation, see [Automating Amazon SageMaker with Amazon EventBridge](https://docs.aws.amazon.com/sagemaker/latest/dg/automating-sagemaker-with-eventbridge.html).\n\nThe model deployer workflow retrieves the model information from the model registry and uses [AWS CloudFormation](https://aws.amazon.com/cloudformation/), a managed infrastructure as code service, to either deploy the model to a real-time inference endpoint or perform batch inference with a stored input dataset, depending on the project requirements.\n\nWhenever a model is successfully deployed in any environment, the model registry is updated with a new tag indicating on which environments the model is currently running. Any time an endpoint is removed, its tag is also deleted from the model registry.\n\nThe following diagram shows the workflow for model deployment and inference.\n\n![image.png](3)\n\n#### **Experiments and model registry**\n\nStoring every experiment and model version in a single location and having a centralized code repository enables us to decouple model training and deployment and to use different AWS accounts for every project and environment.\n\nAll experiment entries store the commit ID of the training and inference code, so we have complete traceability of the whole experimentation process and are able to easily compare different experiments. This prevents us from performing duplicate work on the scientific exploration phase for algorithms and models, and enables us to deploy our models anywhere, independently from the account and environment where the model was trained. This also holds true for models trained in our [AWS Cloud9](https://aws.amazon.com/cn/cloud9/?trk=cndc-detail) experimentation environment.\n\nAll in all, we have fully automated model training and deployment pipelines and have the flexibility to perform fast manual model deployments when something isn’t working properly or when a team needs a model deployed to a different environment for experimentation purposes.\n\n#### **A detailed use case: YET Dragon project**\n\nThe YET Dragon project aims to improve the production performance of Cepsa’s petrochemical plant in Shanghai. To achieve this goal, we studied the production process thoroughly, looking for the less efficient steps. Our target was to increase the yield efficiency of the processes by keeping component concentration exactly below a threshold.\n\nTo simulate this process, we built four generalized additive models or GAM, linear models whose response depends on smooth functions of predictor variables, to predict the results of two oxidation processes, one concentration process, and the aforementioned yield. We also built an optimizer to process the results of the four GAM models and find the best optimizations that could be applied in the plant.\n\nAlthough our models are trained with historical data, the plant can sometimes operate under circumstances that weren’t registered in the training dataset; we expect that our simulation models won’t work well under those scenarios so we also built two anomaly detection models using Isolation Forests algorithms, which determine how far are data points to the rest of the data to detect the anomalies. These models help us detect such situations to disable the automated optimization processes whenever this happens.\n\nIndustrial chemical processes are highly variable and the ML models need to be well aligned with the plant operation, so frequent retraining is required as well as traceability of the models deployed in each situation. YET Dragon was our first ML optimization project to feature a model registry, full reproducibility of the experiments, and a fully managed automated training process.\n\nNow, the complete pipeline that brings a model into production (data transformation, model training, experiment tracking, model registry, and model deployment) is independent for each ML model. This enables us to improve models iteratively (for example adding new variables or testing new algorithms) and to connect the training and deployment stages to different triggers.\n\n#### **The results and future improvements**\n\nWe are currently able to automatically train, deploy, and track the six ML models used in the YET Dragon project, and we have already deployed over 30 versions for each of the production models. This MLOps architecture has been extended to hundreds of ML models in other projects across the company.\n\nWe plan to keep launching new YET projects based on this architecture, which has decreased project mean duration by 25%, thanks to the reduction of bootstrapping time and the automation of ML pipelines. We have also estimated savings of around €300,000 per year thanks to the increase in yield and concentration that is a direct result of the YET Dragon project.\n\nThe short-term evolution of this MLOps architecture is towards model monitoring and automated testing. We plan to automatically test model efficiency against previously deployed models before a new model is deployed. We’re also working in the implementation of model monitoring and inference data drift monitoring with [Amazon SageMaker Model Monitor](https://aws.amazon.com/sagemaker/model-monitor/), in order to automate model retraining.\n\n#### **Conclusion**\n\nCompanies are facing the challenge of bringing their ML projects to production in an automated and efficient manner. Automating the full ML model lifecycle helps reduce project times and ensures better model quality and faster and more frequent deployments to production.\n\nBy developing a standardized MLOps architecture that has been adopted by different business across the company, we at Cepsa were able to speed up ML project bootstrapping and to improve ML model quality, providing a reliable and automated framework upon which our data science teams can innovate faster.\n\nFor more information about MLOps on SageMaker, visit [Amazon SageMaker for MLOps](https://aws.amazon.com/sagemaker/mlops/) and check out other customer use cases in the [AWS Machine Learning Blog](https://aws.amazon.com/search/?searchQuery=mlops#facet_blog_name=AWS%20Machine%20Learning%20Blog&facet_type=blogs&limit=25&page=1&sortResults=modification_date%20desc).\n\n#### **About the authors**\n\n![image.png](4)\n\n**Guillermo Ribeiro Jiménez** is a Sr Data Scientist at Cepsa with a PhD. in Nuclear Physics. He has 6 years of experience with data science projects, mainly in the telco and energy industry. He is currently leading data scientist teams in Cepsa’s Digital Transformation department, with a focus on the scaling and productization of machine learning projects.\n\n![image.png](5)\n\n**Guillermo Menéndez Corral** is a Solutions Architect at AWS Energy and Utilities. He has over 15 years of experience designing and building SW applications, and currently provides architectural guidance to AWS customers in the energy industry, with a focus on analytics and machine learning.","render":"<p>This blog post is co-authored by Guillermo Ribeiro, Sr. Data Scientist at Cepsa.</p>\n<p>Machine learning (ML) has rapidly evolved from being a fashionable trend emerging from academic environments and innovation departments to becoming a key means to deliver value across businesses in every industry. This transition from experiments in laboratories to solving real-world problems in production environments goes hand in hand with <a href=\\"https://aws.amazon.com/sagemaker/mlops/\\" target=\\"_blank\\">MLOps</a>, or the adaptation of DevOps to the ML world.</p>\\n<p>MLOps helps streamline and automate the full lifecycle of an ML model, putting its focus on the source datasets, experiment reproducibility, ML algorithm code, and model quality.</p>\n<p>At <a href=\\"https://www.cepsa.com/en\\" target=\\"_blank\\">Cepsa</a>, a global energy company, we use ML to tackle complex problems across our lines of businesses, from doing predictive maintenance for industrial equipment to monitoring and improving petrochemical processes at our refineries.</p>\\n<p>In this post, we discuss how we built our reference architecture for MLOps using the following key AWS services:</p>\n<ul>\\n<li><a href=\\"https://aws.amazon.com/sagemaker/\\" target=\\"_blank\\">Amazon SageMaker</a>, a service to build, train, and deploy ML models</li>\\n<li><a href=\\"https://aws.amazon.com/step-functions/\\" target=\\"_blank\\">AWS Step Functions</a>, a serverless low-code visual workflow service used to orchestrate and automate processes</li>\\n<li><a href=\\"https://aws.amazon.com/eventbridge/\\" target=\\"_blank\\">Amazon EventBridge</a>, a serverless event bus</li>\\n<li><a href=\\"https://aws.amazon.com/lambda/\\" target=\\"_blank\\">AWS Lambda</a>, a serverless compute service that allows you to run code without provisioning or managing servers</li>\\n</ul>\n<p>We also explain how we applied this reference architecture to bootstrap new ML projects in our company.</p>\n<h4><a id=\\"The_challenge_17\\"></a><strong>The challenge</strong></h4>\\n<p>During the last 4 years, multiple lines of business across Cepsa kicked off ML projects, but soon certain issues and limitations started to arise.</p>\n<p>We didn’t have a reference architecture for ML, so each project followed a different implementation path, performing ad hoc model training and deployment. Without a common method to handle project code and parameters and without an ML model registry or versioning system, we lost the traceability amongst datasets, code, and models.</p>\n<p>We also detected room for improvement in the way we operated models in production, because we didn’t monitor deployed models and therefore didn’t have the means to track model performance. As a consequence, we usually retrained models based on time schedules, because we lacked the right metrics to make informed retraining decisions.</p>\n<h4><a id=\\"The_solution_25\\"></a><strong>The solution</strong></h4>\\n<p>Starting from the challenges we had to overcome, we designed a general solution that aimed to decouple data preparation, model training, inference, and model monitoring, and featured a centralized model registry. This way, we simplified managing environments across multiple AWS accounts, while introducing centralized model traceability.</p>\n<p>Our data scientists and developers use <a href=\\"https://aws.amazon.com/cloud9/\\" target=\\"_blank\\">AWS Cloud9</a> (a cloud IDE for writing, running, and debugging code) for data wrangling and ML experimentation and GitHub as the Git code repository.</p>\\n<p>An automatic training workflow uses the code built by the data science team to <a href=\\"https://aws.amazon.com/sagemaker/train/\\" target=\\"_blank\\">train models on SageMaker</a> and to register output models in the model registry.</p>\\n<p>A different workflow manages model deployment: it obtains the reference from the model registry and creates an inference endpoint using <a href=\\"https://aws.amazon.com/sagemaker/deploy/\\" target=\\"_blank\\">SageMaker model hosting features</a>.</p>\\n<p>We implemented both model training and deployment workflows using Step Functions, because it provided a flexible framework that enables the creation of specific workflows for each project and orchestrates different AWS services and components in a straightforward way.</p>\n<h4><a id=\\"Data_consumption_model_37\\"></a><strong>Data consumption model</strong></h4>\\n<p>In Cepsa, we use a series of data lakes to cover diverse business needs, and all these data lakes share a common data consumption model that makes it easier for data engineers and data scientists to find and consume the data they need.</p>\n<p>To easily handle costs and responsibilities, data lake environments are completely separated from data producer and consumer applications, and deployed in different AWS accounts belonging to a common AWS Organization.</p>\n<p>The data used to train ML models and the data used as an inference input for trained models is made available from the different data lakes through a set of well-defined APIs using <a href=\\"https://aws.amazon.com/api-gateway/\\" target=\\"_blank\\">Amazon API Gateway</a>, a service to create, publish, maintain, monitor, and secure APIs at scale. The API backend uses <a href=\\"https://aws.amazon.com/athena/\\" target=\\"_blank\\">Amazon Athena</a> (an interactive query service to analyze data using standard SQL) to access data that is already stored in <a href=\\"http://aws.amazon.com/s3\\" target=\\"_blank\\">Amazon Simple Storage Service</a> ([Amazon S3](https://aws.amazon.com/cn/s3/?trk=cndc-detail)) and cataloged in the <a href=\\"https://aws.amazon.com/glue/\\" target=\\"_blank\\">AWS Glue</a> Data Catalog.</p>\\n<p>The following diagram provides a general overview of Cepsa’s MLOps architecture.</p>\n<p><img src=\\"data:image/png;base64,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\\" alt=\\"image.png\\" rel=\\"1\\" /></p>\n<h4><a id=\\"Model_training_49\\"></a><strong>Model training</strong></h4>\\n<p>The training process is independent for each model and handled by a <a href=\\"https://docs.aws.amazon.com/step-functions/latest/dg/concepts-standard-vs-express.html\\" target=\\"_blank\\">Step Functions standard workflow</a>, which gives us flexibility to model processes based on different project requirements. We have a defined a base template that we reuse on most projects, performing minor adjustments when required. For example, some project owners have decided to add manual gates to approve deployments of new production models, while other project owners have implemented their own error detection and retry mechanisms.</p>\\n<p>We also perform transformations on the input datasets used for model training. For this purpose, we use Lambda functions that are integrated in the training workflows. In some scenarios where more complex data transformations are required, we run our code in <a href=\\"https://aws.amazon.com/ecs/\\" target=\\"_blank\\">Amazon Elastic Container Service</a> ([Amazon ECS](https://aws.amazon.com/cn/ecs/?trk=cndc-detail)) on <a href=\\"https://aws.amazon.com/fargate/\\" target=\\"_blank\\">AWS Fargate</a>, a serverless compute engine to run containers.</p>\\n<p>Our data science team uses custom algorithms frequently, so we take advantage of the ability to <a href=\\"https://docs.aws.amazon.com/sagemaker/latest/dg/adapt-training-container.html\\" target=\\"_blank\\">use custom containers in SageMaker model training</a>, relying on <a href=\\"https://aws.amazon.com/ecr/\\" target=\\"_blank\\">Amazon Elastic Container Registry</a> (Amazon ECR), a fully managed container registry that makes it easy to store, manage, share, and deploy container images.</p>\\n<p>Most of our ML projects are based on the Scikit-learn library, so we have extended the standard <a href=\\"https://github.com/aws/sagemaker-scikit-learn-container\\" target=\\"_blank\\">SageMaker Scikit-learn container</a> to include the environment variables required for the project, such as the Git repository information and deployment options.</p>\\n<p>With this approach, our data scientists just need to focus on developing the training algorithm and to specify the libraries required by the project. When they push code changes to the Git repository, our CI/CD system (<a href=\\"https://www.jenkins.io/\\" target=\\"_blank\\">Jenkins</a> hosted on AWS) builds the container with the training code and libraries. This container is pushed to Amazon ECR and finally passed as a parameter to the SageMaker training invocation.</p>\\n<p>When the training process is complete, the resulting model is stored in Amazon S3, a reference is added in the model registry, and all the collected information and metrics are saved in the experiments catalog. This assures full reproducibility because the algorithm code and libraries are linked to the trained model along with the data associated to the experiment.</p>\n<p>The following diagram illustrates the model training and retraining process.</p>\n<p><img src=\\"data:image/png;base64,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\\" alt=\\"image.png\\" rel=\\"2\\" /></p>\n<h4><a id=\\"Model_deployment_67\\"></a><strong>Model deployment</strong></h4>\\n<p>The architecture is flexible and allows both automatic and manual deployments of the trained models. The model deployer workflow is automatically invoked by means of an event that SageMaker training publishes in EventBridge after training has finished, but it can also be manually invoked if needed, passing the right model version from the model registry. For more information about automatic invocation, see <a href=\\"https://docs.aws.amazon.com/sagemaker/latest/dg/automating-sagemaker-with-eventbridge.html\\" target=\\"_blank\\">Automating Amazon SageMaker with Amazon EventBridge</a>.</p>\\n<p>The model deployer workflow retrieves the model information from the model registry and uses <a href=\\"https://aws.amazon.com/cloudformation/\\" target=\\"_blank\\">AWS CloudFormation</a>, a managed infrastructure as code service, to either deploy the model to a real-time inference endpoint or perform batch inference with a stored input dataset, depending on the project requirements.</p>\\n<p>Whenever a model is successfully deployed in any environment, the model registry is updated with a new tag indicating on which environments the model is currently running. Any time an endpoint is removed, its tag is also deleted from the model registry.</p>\n<p>The following diagram shows the workflow for model deployment and inference.</p>\n<p><img src=\\"data:image/png;base64,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\\" alt=\\"image.png\\" rel=\\"3\\" /></p>\n<h4><a id=\\"Experiments_and_model_registry_79\\"></a><strong>Experiments and model registry</strong></h4>\\n<p>Storing every experiment and model version in a single location and having a centralized code repository enables us to decouple model training and deployment and to use different AWS accounts for every project and environment.</p>\n<p>All experiment entries store the commit ID of the training and inference code, so we have complete traceability of the whole experimentation process and are able to easily compare different experiments. This prevents us from performing duplicate work on the scientific exploration phase for algorithms and models, and enables us to deploy our models anywhere, independently from the account and environment where the model was trained. This also holds true for models trained in our AWS Cloud9 experimentation environment.</p>\n<p>All in all, we have fully automated model training and deployment pipelines and have the flexibility to perform fast manual model deployments when something isn’t working properly or when a team needs a model deployed to a different environment for experimentation purposes.</p>\n<h4><a id=\\"A_detailed_use_case_YET_Dragon_project_87\\"></a><strong>A detailed use case: YET Dragon project</strong></h4>\\n<p>The YET Dragon project aims to improve the production performance of Cepsa’s petrochemical plant in Shanghai. To achieve this goal, we studied the production process thoroughly, looking for the less efficient steps. Our target was to increase the yield efficiency of the processes by keeping component concentration exactly below a threshold.</p>\n<p>To simulate this process, we built four generalized additive models or GAM, linear models whose response depends on smooth functions of predictor variables, to predict the results of two oxidation processes, one concentration process, and the aforementioned yield. We also built an optimizer to process the results of the four GAM models and find the best optimizations that could be applied in the plant.</p>\n<p>Although our models are trained with historical data, the plant can sometimes operate under circumstances that weren’t registered in the training dataset; we expect that our simulation models won’t work well under those scenarios so we also built two anomaly detection models using Isolation Forests algorithms, which determine how far are data points to the rest of the data to detect the anomalies. These models help us detect such situations to disable the automated optimization processes whenever this happens.</p>\n<p>Industrial chemical processes are highly variable and the ML models need to be well aligned with the plant operation, so frequent retraining is required as well as traceability of the models deployed in each situation. YET Dragon was our first ML optimization project to feature a model registry, full reproducibility of the experiments, and a fully managed automated training process.</p>\n<p>Now, the complete pipeline that brings a model into production (data transformation, model training, experiment tracking, model registry, and model deployment) is independent for each ML model. This enables us to improve models iteratively (for example adding new variables or testing new algorithms) and to connect the training and deployment stages to different triggers.</p>\n<h4><a id=\\"The_results_and_future_improvements_99\\"></a><strong>The results and future improvements</strong></h4>\\n<p>We are currently able to automatically train, deploy, and track the six ML models used in the YET Dragon project, and we have already deployed over 30 versions for each of the production models. This MLOps architecture has been extended to hundreds of ML models in other projects across the company.</p>\n<p>We plan to keep launching new YET projects based on this architecture, which has decreased project mean duration by 25%, thanks to the reduction of bootstrapping time and the automation of ML pipelines. We have also estimated savings of around €300,000 per year thanks to the increase in yield and concentration that is a direct result of the YET Dragon project.</p>\n<p>The short-term evolution of this MLOps architecture is towards model monitoring and automated testing. We plan to automatically test model efficiency against previously deployed models before a new model is deployed. We’re also working in the implementation of model monitoring and inference data drift monitoring with <a href=\\"https://aws.amazon.com/sagemaker/model-monitor/\\" target=\\"_blank\\">Amazon SageMaker Model Monitor</a>, in order to automate model retraining.</p>\\n<h4><a id=\\"Conclusion_107\\"></a><strong>Conclusion</strong></h4>\\n<p>Companies are facing the challenge of bringing their ML projects to production in an automated and efficient manner. Automating the full ML model lifecycle helps reduce project times and ensures better model quality and faster and more frequent deployments to production.</p>\n<p>By developing a standardized MLOps architecture that has been adopted by different business across the company, we at Cepsa were able to speed up ML project bootstrapping and to improve ML model quality, providing a reliable and automated framework upon which our data science teams can innovate faster.</p>\n<p>For more information about MLOps on SageMaker, visit <a href=\\"https://aws.amazon.com/sagemaker/mlops/\\" target=\\"_blank\\">Amazon SageMaker for MLOps</a> and check out other customer use cases in the <a href=\\"https://aws.amazon.com/search/?searchQuery=mlops#facet_blog_name=AWS%20Machine%20Learning%20Blog&amp;facet_type=blogs&amp;limit=25&amp;page=1&amp;sortResults=modification_date%20desc\\" target=\\"_blank\\">AWS Machine Learning Blog</a>.</p>\\n<h4><a id=\\"About_the_authors_115\\"></a><strong>About the authors</strong></h4>\\n<p><img src=\\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAGQAAABmCAIAAACySKMIAAAgAElEQVR4nLS8aZBl2XEelpnnnLu8tbaupbune6Z7egazYIABBjtAggQIggDCoAiapmBRtBhhU6IlSt4E20FTIk1bNm2FKZq2SdGiaIm0LYqLCQJcsIPADAYzg9nX7pneu6urura33OUsmekft3sAUJbD4wiceD+qXsS7dW7ezC+//L7zCuf+DIIDzVUsYW5NZowhIgCC7+gSBURhJmsAIAkbQlEJob1+ZWtvdx5Echdy087aePT2N2wsHQIEBUEAEARERXjwscf/6PNfy5yJzSz5ClLwTc3MAJT8rN8z83lbT5vBwADgfFIbm4LHaaytuutXdodro//65z/x+ttPmf5CC6w+QmSWlESA0Fo7m0xPP/HwbDbr9XopJWtpTOgM5QgZorl5H4zf6WARAgBZ0/oYYsvMPvnZbBaTaKo0D/1eX4KoFkkx3tgYKCgCflvMEwMpgaCqgqgqqgIwAIgIACAiADCzMJBREWVmC9YYo6opJSJSFWMNYwJEIgIRBjWqKSVmLoqCmUXEOlokst1GQKHbyV/Y0HdiKYAIAMDe/s50OhVJqoqIqUFnuDDqSFmdicZFte2NJ3djY3hjeyJCIIQEBGCQFSwBswIAKogyABCRiDCzqoqAMaaLHYB43zRNhQSiigqqil1wCYkQEZk5pVTXdVmWzjlLZEFBFQBAFZC6h/EdTisAUDWEzJFTa40iGUR0zkFPSTVJ3J/Nxce+tUQtUQ2w8K9cAFQ1IzSoRAYJVYVQGQURARQADCCgJmEAUMIkYjXrEgoAvPdN0xCRKqsSIhJRYEZEJLLWSkptE6zJBv2RqloAAYQuOvjNTSB+h3MLUQE4xRaZSURYQ+S9am+7bQ/2Jpcv7+4czI6sL37gu+5XxMaYf81FEBFAlFSTdku66lNVA5gQRQRFDBpEZBHvfYpCDAgAqiJCBAyACtZaAZYoQmCJEDGEEEIYjUYxRkS0AKygCK8iOn3H49QtFkDNi2Jxefny5Stnz13a3trb2dl141GGRTUjX7vpgSd0klhiAFVA/FbMQgTnHCGqanfbqopIXcDoxvMAVQUAItsBF4ExRArCzIysIICowiKmu39WQTRERICSOCsLJWRQULUABlRFFVERUZVvwvx3eBkLAAI69+zFqRlQKYeOLq8tQ2bd6nK9fTBf6FNBNZa80At/8eMKgGCtFQXlhMwiHfKAqLKIRQVAVVZVY4wCsAirWCJrLackIqpsAEFURAAEADto63BNRESEiKy1WZZNp1MLSggA2IGm3IwXfqepgwLULZ89f+6xJx6PCZJm29cPQO21K8HaBBZ3Z5Wurj/57JX11YWFwyP49nzvQBYRU0oqSSVxSqzSpRWzWoKuLDskUoGuo7Ew3qheMMYYYwBYhNAg3LwmEbEIsDKzMQYRq6pSVSvxAtEYzVDFKBJivImOry1YCg1IiQBASXRGuggKYBIAgRKwgAFAYaBL13avbR9sTdK5cxe2ru95H5umYU3Mqa5mDMYgWIPA6eLVgzIvVlZWNl6Zfex9b11dXzEGQRMgIhlRSlGNacVgU6ckKWMPHJL3EWzPIaiNYU4YQHJOwRoQLiTJqFd4TQdmZhWYWaw1SROqM1ZiAHJERkSJkEAVIjPlzpRZbquwZW3rUK0ZAhCCAaBXOcT/94VgAUEUUJFwERAAEoCN4BEzsDSZpwuXr569sPnK+c2DWeC4HyMDOmGVGEJoRZJRiVFSTC1Il+DT2m9PZq9cvnb+4qXX333yPW9/461rCwYZEFWJDGgyiYXAZCbj2FpjsiIPbVC9wRi6hIoxJg4AQAb1JoGy7gZAd7nGzESUZbZjbCzSNE0MnGdkjEkp2iIfEhVkDAB0RFSly8bXFiwAIwJkREQ5gXUAoAAJwUXF5144/+DDj1/fn/kELCZzfVRwxrY+hJBUxABr8prC0I0SUoy+TcIIamxM0ko9OXv94vXpg489+UMf+t73v+vNDsCQtNMdX0dXOFBofUsAgpBSABBQJaSbvJREBFicccwiklJKBtCZGzepCAYwciJAshQ5ERGk5L13zjEzdODl3G2gBsQqIAAgwf9PjqUEKKBEREQCSgBOcef0S/PHn3r+/MWtWduiRafat1kMdR2CCLRtaNsAyigMyhkR+FlGZIkRmREU0SmJSJQ0r2RSwz/6zT94+sXzP/aXPrQ6NuOebZuJMT1hD+oVkgB2yPUqEYKbJJ4IrKUUYkpCqHlmDQKIwg1yC6iKeAPqnDO+YRBRRWYmY6wlK1wAAHapdCNMCUAB3GsNFxGIACGIRkIHKT788IOf+crl/YO5y0owRCkiSk6S6llkm6LExMJRYrDAzkBGiOSJCFAzm5CssRijhJTmAHVQsTmY7E8+9+Dm5Usf+8j7NJnByIX2ACEUGYYoquRMFn1DgDeqUDWkmFJCRIOgyiLJoMldxtxySkQAAKpqrRVR7gYLgKapumoty15mrSpbMAGUFQXBAFgAq4qK+lrTSwUUgSilBNbkAPunn3/8a5974nrD1uScwKgp8wwBQxUwWSOpbuatD6rqEAuLPWMssMkAVVRSwGCUnUIkUYuKWB1M8ryXGikIn3vu5SeefubU607dujCwxG3dMDMSpsDBNxmRJYwpMHO3p5RSbgzdGMBVQQx2uJQAkIhE1RqryqCACiIyn89TSsPhqCwLSW3bequgihFEEAHRggKiAXjtVItARQEIIQE21y4898KTjy/kixtmBmAdmSLLYvIikixw4EIDOinJAICBlKOWyBY4KVgiQMwsibCmhkQVTSZpuUd7s32kDChLSeoAX3ro8fe+/tjRtXGe+dlkD61jluTbQVGSgdhGVc2zrOMTYEzXNIiI0w0OZeCbAN8NAK8O3m3bImpZlswpeM/MViEHIdDQpVU3Jyq+ZoBHBGNQhYy1e9vPPP/sk4N8mRY18yTMbV0XJFpEBZjHlCGI5kldTNJpAJYjBQ/JoxbKiTlKSkpdGqiiDEiIXFNku3MJyTvnQMQJP/7YC4N3vmF1PJ7jtG28tVmeWdAEQjFGVc2yLMbInJjAqAEAIooSJHGWW2MMiAAQgDCriJC1qAxJASDLsqqqmJMkbwxaqyCorMwKlhwggQKhvHaelRqFnhJUrzz6x58SPUxuJuyHhfPe254oJFAEgKFxvZyNpJRSlJQkiQh3NJzQxEpUmCMokBgWIBG0NkfJIFgHQaprTVDtE0fHbYzpS1994m1vv6vnDLa+T/15YOqLUs7MklKoGu+9JqHSCQH4iGQ4YZR62Bvn5SBGFUkIoGQUMbJySBYkzKez6a4q5s5YawmQAAEREcy3j4SvuSOKhBwtYPv1L32xmYFIPZvMCYCELagBtKAIAqLEjClJTMBCqiiiKUmMmhhFERQViMggqiqCIICmFEILyqWzg36eEdTzWWhrQjWGptPZC8+fESVrbdPOFZKydgyryyMAuMEXUoJuxjYGEdu2DdFba7uZhoi697sRej6ft21bFAUoiYAxrhMbjDEOERW4K6hu+HxNy5AzApOd565cOJ/RMDQH3AZLAikhMymTilEh4e6lEkAjKINyN6+oRJUIoqBCqsoJUkRlUkFOoAzJA4dRZsaFo9T6tuLok3pAvLq5s7szz7JMwZeF1XRjriYiY8kY01GCrtxEpLvTtq1DCOgcIooIJ311HuyULGstkbHWGnJERDeGLOiesajyaw1Tt1QQIJ59/hFkVAb1vmez2M5J2KhYUAtgVI1K96tDMCok0WhyCA7BgpIwKoMkkAQqKbYcPGpESCQiIUgzK5DHhclJkUP0bQhtUeag9uz5q8KUObIGQDAlYeZOHUCCbsLucjalFELQV3UoohtDuCoAMDOhZdYuWL6NzKIKzEo3x0ACQBFW4G7+fs3REhumL1948YwFIzwjtSRoDFhCS+iMMagESAjdCwkAFbqbQSUCok5U6QQAMagGFSRqSiQdikVK0XHIgTNkElFh4ZS4BYCta3u7exObuZQCANR13QG8KkuKr5ZhN+vc0KesJSK4WUZd7Logeu9jjIjGOQc3K/dV9aoDKVHt5oPXHCs0cPb0k9piTg4p9LIeAVpyXTncrGvpcMEYA6IEaJAIAQEQgBCtMYidWKQd4UZU0cDiAYBUSCNE7yTlhhBERKyiRM/SxCQXL19HcsZZBW7btisoUL6hwIhKujEtIuJNXwY62tTxT+EboajruuOxeZ4XReGchW8FcrzBrboH+5pXlHa6Px/lQ05egYui6Bd5YlAERUJEAUA0QIiGAKnbK377evVqHSB08erQ+UYKMEvwKFJ0cpgIshiMCNFat709vb4zd1khwABkjLGWRCRxQP1m4jAna28YFojYZTcRvSo3d4w0RkZE0QQAiCiSCEBe1YYQEalT419zsKxJo96yJmbxw8FYUgsAo9GSc7nNMrLW2uyGAKkoCGQNEEongBKRMV0RKgigsqSYAqBaZ8h0jFpU1RBBh2sopGCM4cigibUlIt/yxQtXo7CgvtramDnGKCKIaJE68mmMQYQuxeDG5EhdqXZ10IFaV4Mh+JSSc103vOGYIAAJEwApfLMh/oXO2HlANzgxCIAIKKsgYFvHJjZZngM5dbkYVAnOUGFdYV1G6IAwCaRk9EYNZtZZQyqcYlARUM3UQJQMrUGjrAZcYYqccpu8AfRJg2BKiUOj4iW1gD75RIwilSswy3sF9XLRFCtHWFDGQRCccdYSYAqZmpycSFTwvdL2MgOcmCAkQURAQeHgG0kRALz3PoSkao2x5Oy/LlO+Fe3gZnSMMQpMYAARO89TBQgIievJbH/HImbOOucUTVs3oamFu4ijqnaIoYIdTUEVAiEQUjCAnVIpBIaQRTuhSYFVGUCMMcyiqkmk9imk+OqM8ur2GLRLImNMZh2KckzauTVoQDrojGhIPCDa3Ll/8o9/bXll5d4H3jZpGiACJQUFoFlVz5u6LDIRsIaQiFXoXw3Qt6DGt5k8HRwSKIAoS1eqRASQFMJ0+8p0fzvPLBEpJxA1SMbamzMXAwgREBGSImlKQSSpsiorxO4lGhDVGDQWHRmLSKqggqCCkFQENKbUtG0IAQD0JtjdVJM5hBBj7NDwprgOBokAOw4VWZkTSyzy8mC3/vLnv/6P/uEv7W9e7vcHCCZ1m4ixqds8KwfDsVLH2umb/uCrsHUzanDj78E3leyur4sAACHd+KAP8+lsd9rs1gfbEJvCZcDS1k1TzUWS4I3e113NIHX9jWOQxMoiiTkFTkElCUfhKJK66u5iqpIkRY4hpaQqUThwSsKd+wD4Tc8ZEUE1hBBazxxJgQxYgi5kncMqIhyzmLzLo0GBVGysHP/ql7764vOP2bz03qeUVLCNKYoWvb4AZcYSIhgiY/7fxppXW/5N+tMhogEAFhZIgLH2k4PqehunB9ubHDufLYKqcgSRENoYI8A3fWC+qVQqsGhiid07r2ZZCpGZJTEIKyeOKaXEIUpMqtrlDoN2P6OoqoAoqdw0JjjGKMzGdpRb27YNIbCKqIqitbYsy67xlVk+Ho6aJrzw3POAKHJjhx3MA2FKyRAYYywiS/w2zPoWnPoLhdn5HGgMKmhIrW8bII6p3drdjBxcb6WeHxjEyF3HAmVhiCJC4IxxXbA6LqMsBAhqmFmYlQWECbCTaVkVAW+ks5JIQlEEUEkI9ia1TMwiHFUJRARYVakzAG62IxFRVmEIKSYFZ5wAAII1rUYgGKhqXkrtp9/93e+89963xnmlkoCFlS1SUWQao7EIKRlrFdi3zf8DwH9rsFQ7I06NQQBQ0CZN9/Z2mmqa9WyWZcbauQ9Xrux6X0dmg4jGchKDCqj9MufoiAyAIhoAkqRdF++AphvHADoD/ZsSsAioAoigKCE6Mkn0Zu9XiSlxUtbOXlW4UQFdiiKpMUZSUhAAUkRAEFAVIVVJIc+Kqg5AcuHKy8eOH/6N3/wnZvHQwfYkNC2zZoUR1DzPa98wM8YQ2BtjYmi/HeC/fcp5lSgSkYJuXtv8+te//sxzj+3uX+mN3eLSwDi0eVb2xkQ9ImIFBgQiZga50ZistarKrKposGOhhoiIrN5ccLOd3ZzRkGPimLoKVUEA6iiSc85aKyLKQgrK8irOvurZdOw8z12WZTZz3VTchpgiI2Lmek3TiLRkEgDkefkP/ttfvPDSC71eD0BEk6q2TUMK3QdZYts0vq0BwAITmBbBQrJAc2PKCAwAJu0IkLNLiMSaLl17ZWfP09JsJT96/OipELeMrLLuGbx01y1vBZl94ylIDJBZ4Gidap4DmKTBqrE2E0iJA6k1aiAiACSJ6JykEFjIgiRFIgU2MbWh4RgEAcgwaFJQhWTUQnTCa4M8hTD1vtWUcpu89jKnTcOsgHBQV4nAGC1YoqHdecUKhiyxWIQYWiwpWoVotcGl5dWvfe2xtdWNxbXVOsYoSsZFBXGuVY4+yHxmMu7lRWo9h0gCEUABrNoANEJA9fNM/EG7PZlcAD4Luke40y/NXSduf+up78tLmdVXMieRJ6PBxtFDb0aslPaDRY8IWSbWRjRoe3kxGPQXMCNwQM4a57Iscy43xhi0mSmAyVCRmwFJKamIPq/nNG3bBAatExFuW0jRoThUCAlCItFMaVyWi72eU02N7+dFaj0iGmclxTSr9reuizHW5arfLJSOzatqFOnnvaqqbG73dnff/pY3/Kf/+SdGw+F8Pu0qKbOuzAvfNNPZgaoiwGQyqaoKAGzkF8DUBm9lXic6SGFW5u2k+U2Bv7IyuuVa9TdDGB0e/VdL4xXC09D0xsONvd3zpT3ad+uASUBRgfmSQDabNyTN4rjfy3KLeQqJNXJmlAg4ibIAGGMSmshpIvW0nR/MpnUTrMli5KZqYowam9GwP8xy4Zi8R0RjRFUdGFAmUVEuiBbK8trBzDCLj+Ij5KaOTQ/h2HDRNrFtUmFcZ8yllFLkQb8PzE1KPgil5Jyb19VSv/eXP/5vrd5+7ODatgjemPxQEgcAdc6E6Cf7O87YheGozDNbNwcvXfh7g1H/rkO/RdgASYp4Yf7PFweK7qeM72l2ZjP8wpL8Bwf826Y5Ol742JH1e4whjQk0AhBCf3fn6lOnz71w9jLq1tri+OTxW5ZHy4Qg3JI4ApM4hRBi5OBlNq/quj29f23r+u60rqumRTQIxhmDCuSD2Z8u9fpr46HN+qGpU4p5WaB0Z9MgRY9gCkvWkDHOe59ZKwTMcaU/vvvQukBMVfAFzWuf+IYtyMykSmQFSGI0xqCRUa9/eGMVYts2M4AeqrJoZ1/HGNu2nc2mgxxHg35Z5CzJDvN7Tow/8cSVH1gd//uHir/WwGUM35+yW0gvciuHil9P9iuXp7+9NfnyvDp58vhHMrN++vSDw2GzsTEQXbF8O5h04ez+w08/29YmzGfnrly4Ntk+cfTY0bW1ssTSMyMqa/JtVfndyfRgXvuQwLtmPwbPoFZU84xK5+qqMlkR2ub6wTT4uDjo5c4iaB0i3TicRixCBpwlIhBVD9GaPKXYc3Y5z2zdeGntMKuJp7NKFYnIGkopGkBrLYoiYPJhsFjmjieTfUA1xsTWG5OHEGzeRzBN09Szed+ZYb+01nrvichu+X92ZPWBB4r/whWfnTZfPnfwJ0cWX1/M//7e/Gfjxvdu0K/m8v5DfZwOfndQ/kdglk5f+uxL554olx8crf/IEN/MMLc4yV3WT3Ly6K3D/tL0YFujn13f2ZO0stwvyyVRlcTiY1vNZ5OpD9Fk2TjO71odgV3uj0ejhTGn0DbzejbdDc437WRvf296UDfVysJw0C9JCUxSMVEEUAyqJQSQNgZAEUkQwlKZjwjr+T456wSqpuXu2BazqubWGaK6rhFAgI3B0NSQZ9baOK9DCKquo++dKOpc1uv1MuROfgCAfr9vt8Ivnz/fvuuWL1zbW3jo6f9m6g9Gb3ppffh9L17z18++Uq5+Y633/pLelOJgMJpuHjz6/At7b37je9vm5JlzXzt+6MTi8JZ9+McbJ4bvuu8OgtHS8tGmGu/ubM/2ptKINFJhYwCjD/PJbHYwTfO5MqSYJO4W/f7c1zt7s2m109R1bqjI3GpR1Ggcl45iVVW7B7sqg8Xx0CCxAoiCAooY5YwMKRmjFrSwbqMoV/oFILvxCKytmwrJkGiS2PGJTm/JDVUGCDUjnNSzGKMzmQIBUPARIEM0MSZn80A0n02KUa9rDikle+ElcaOtLfxFK39b8TeXFrMMaCkvl1befvHyc2q/BPJxsksOTuzPvnC4PPmhD3zEAZK89fFLf/jcwY88MPxVnL+/33/5yOvWHn349JOvnLl06VJVNeP+4vrK8lSHdx7vO+dM4hA8+9YKtN7P95p5Fvd3rl7bnVQttyEZxKNrGwiykl4aL68U/X4oDEJWFsWgyEFZo4IaFSEFEjaEhTXOWAtsBBZcsVIORkUx18YM8qgKaEQSsDjniLVtW0OUZVn0LVgXgl8fL0SjzJzqtvbBuExVfQjWe1TilLyPRd7rmqnLc1W1Mzjyl47/WtFsuZXB+9/9v1WTx0p94yzY516cv+kErpcNwJ8BvFfl9MrwvcCDMtlgnt/1T2+s/BvD/KeIjxTucJ7ft3HLb5//jS8+fe5yGPQxFotrhw/fcercsy/6/afe/sBber3+3LjKGK9+muJuqLmxqOUdx9bRuoPpZGFhYWNjYzabhWuXrx8cFC0XRdYjKlBzYRVB4CBIVJDJNIlDs1j0BzlX7cyZvI3BIOZoIjhl8MhWBBksucjJo2YGRIJDTijg933ghbW7F0fx6uWLLN60+5lQQ0XdNC6f1XESQjsejhqcoUhKAWo1xtiW733u0psOb1w62P2tw+M3zGdbRVlV+y89c/pLh1d+5vjKO9t0WnQ2KO8FzhlsgJe5JQkzZydD/UAVdl6e/a1x/z29fr6xPF5dXh8fXqWQZ9Y5TSc2VmI4YFBjrSvyxNxUNQgPer3bjh1mZmfzhaXlMi9i9NE3rcnb4pb+dr6zd72aVUuLi0sLYxJJPggDRmaIRoSIBFFVLAKyjHu93MeDvd3Dg3wwGl5n32ZZJ9kQIBEZpG4OAeEUciACWwWoi4Ucnbl89YpP3pt86nV3HsQUzvYXR8thOmmqtk77jhzkRER2vtN/0X36crW6Xhyt9r56bvP0LctL73j92+4+jk9sXknlcJ2sla/o+PutfdZgFsSMi6MD9/698A8vz//G4uL7VtKHa7myv78/GpaHFlZ741Irmk3nu9M9g2ZlZUVUGRQNdaKEcW5lMLQa+2UevK+uX9WySD601ZxA6hBzy0dWlzqgsQBZZhNoPQ/CsTvRaYyJCt574QiiQ2M3Do1TM/PJF2VfWRMBIgACM5Pt/GNCNAqMRhQ179trO694gWMnPtJbfp3WbRiuLigNjtheUe6ee3myv5eaGQZAY8p+P3cuhWin1782WDxXyV2rh9/1xYc+9fBLn/r+9xy27uMHk8NzffZr81/4oft/7LaNL1fTM6381eGgHMPxSfuHOWeL2Q96/F9zOHpk9IGd8Omze+cHg5Fw3NufUmu8j1mJzuZFkTVNoz7Oq9r7aJGcy3t5EXzMnSvy3IdmXrWESplVln6uppf3ej1mnk6n0XsfO20PUJRIlIHJBNE2hpSiEIKkUa+IltEQxyQiaLGzR4P3KcVOz2FmZFGrHKKVCDHWM4g6cIt39VeNEGTKmhmjMJ3PGn/Q6xMK53mRQghtTYD2yafOXnnlyb/6wftx8mK7vbicv+PQ8q3TRt79pl861LdPnP/Vh1/85OkrT77//gf6cO3a1sXlhUzMowpvafEg4aHIayq7i9kCzWVo+mCACluOesCQDTNk4703gKoaQhKBsiiKoiyMIeeQpSiK0WgkmjTFEH1om4V8UOZFCKGu22GvP9embVtjOqfGJJGUGAgTOUBS1UTkk6/mB5lF63JmBUGLZCxmxsUQUozS6V8hGkDQLPlGvfYGZTWfXN+f7YdUKbWBib2S9go3q6vpbKZgsOX5dGYtOUN5ntu91r9++c23Ff287f3Uj3/gYrv26GOn4WQCMLN05OT6O59/+qce3Gm3/G0fefOBT488dv5TD5z669ZtThps5rfumfboUg5+PQ84tn07yA94Ask4JPAini2ytZn3qa2bGCOhNYCZsaUDBsXoBRgRQaUgGoyGqljkJWGIQTmptZl12saASsY45gAAjJbBoHWdZpGY0WBZZMEnr2iHXQsTVEG8oeEwcwQia0B85kCSbeo0a1pgMEggODC2KK2xQAyaOHoJBBJilmJe9lXSfHZgP/bBE2uTW7evPX1o8NH9+teX1vdvPfTjbb3/5IVPebv+Q2956wffGX/i5IceOfNDf/b4Qx+850eT/+RLlx+/9/BHF4rlHuZoIYYq5X8YQCh3edbHusKILs+zDDnFpm1FyNcNM+cuAyCLkFvjemZY9LIsCz7GGFWAlArjmGxiZQZEy4JkrCupiTHGTpwCJBsV6sgMKKImoVgpimKYu8l03pKxuUvAqhqTtwTOuRQDsESJjoxy4/Lkwcwiut7YQLr0wjc0GwnPghKKTq5feuShz4eDvWxpOK0nQ/SgETUBiL0j8xvrp0rXO3Pt+Y3Dd55af+C2Iw+UlN1/5Hu//Nz/cnH/vhc3v6uxj3/v7b+ym+7rud2LZ85u42d7xXPHhz+ZmddHu2VgZW9627X2hSz2NOWDwajX64kkcNxCg0lEYmhaVCqKXtM0dV0T4JTcAM1KbzQcLKCSBJ8ajwoMTAgheh8EgNrgQ4rgnIjvDANBaH2ovIQkQGiFQLCtm5ajMU4yU3EIBhQkhOTIZRmGG8YhMHMOw1mzK643rX0z27l48amD39u+dHF7Z3r12Vcur4yXN5b7V65dOLq4Vp64vTEtCZe5zaxRYPOuj9558ZXnFFfe9j1/e239e85ffSRfmvb6d2ws3VFm/uGLz3HxwWr254Phzqj30T/49Ce+8MuXLcQAACAASURBVMzn3v/Gn153b2ecZdntkf40Ax7Q2y98/Rs+zIbDrJcNrDNtW21f3ZLAto1AVjPrg09togihCQKIjLubO/VkXuRFmWe9skQDxpoiL9o2Vk0VONRt432c1ZGZGg6gTAi782bPy26QadtyklbZij+2PLIpoi206M1VGvG5lDEkFmbBIFA1wRgqcteQQgwlQmgm03q+vHyyzPv17By0MNneGvXKtdVDC4PRfD4px30RaBNYYWnjbBLM2oY/c23aW0vvel/viZd/54nn/7vjqycWxh/CcPnc9J9t7p75wD2vf8fGoIQzzqTD5geOHXt3m91+4G7xzC+//N9j/sWyuCfynZtPP6hJx/0xhzSdV3uTPQBFaw3ZpOhbj4LIXDdzybC3NFywZYpxe2urDY0CKyRDlDiF0LLEpm1aH5OIT1y1bR08sCZhQKh9OGjD1IckwiINyKHe4HB/DIDcM7Tca5O3gE0dENQ5q0AhcUpsCQjUAEryRp1ztL66ZE2RZz0wsrFg3v22++9+3cm6mu8fVE0QUHf50tWLFy+tLo+HvcJlzt5ybP3MZGXWW3th/1cmutCM7j4v82XdbQ7gtz/5x8NVv3fkSN1e32lmK7f+zutO/MIqve4rm78wPfiBfn95PDg+tEcLHIamMgSYsJ21bVPX3k/n0/F4OBj2FfKMlQ8oNQe+rgzCwtrKYGnB7sQ5mrauNjd9El/Xi6uHDg16ZZCWEEFTCm1TBx+ZAaq6BlUDkOc5WxckhBC8qE8RUUOU/ciLC6VdMFpKmtY5FTFGBEFEftWzUY0gg8wAuRi4cKaHsHf5kqSsf6jsUVgZ5o2PGtt5XV28ck3RjPr9S5tXq9rbNVfXjf2xj/2N//GTf/aZh5te8Ya/88MfumXxq5u12Tm40OudtPCmNx19+23H3/+7X/qlS/7R5WmI9/0P9xz60QeW324G9wrdla2vS9yp4+ddv9ekqvWxUJJYbW9tz5p6YVz28yy5PrLUVVX7OimMF5fyfLC3tT/f3Lu2vdUCr48PDUYLMcbLFy8sLy7aHB3ZDMACpcCBGcF0J4QYMYRYt8nHkEQEEQhLxoZbd2RptL5YV5PUhjIr25DyPG+bKsYIePNbS6DWZr1+MZ2nEGOZkcRWWa5cvdbsigxxOuMYY0Bjs8JLtBmPRvny2vrebFIUJxDRzgan7r7tD9fWuIryyDN/+I77XrnFN7t7GzY78le+72ffdOdbwHx2tGg/eOc7l4Z/fvq530uzW+8/8eOQIUCZoifboLm1geyA9wR7gePe/tbm1SuDxSVL6JtQJF/X88n+3n4122/ql3d2J5Oqqb0zmhduaWXF9AZobO6KUDdXNreLgVsYDhDAGbTWcROjRAvAAGpsm7RmUSAygopoXGiq5dXFwaHeJFYi1DZG2ViS0H3TELEzBDtrjch6TgnEli7ENoTKJ3ttujWBMFwYlAuru9NqGlI2GC4tLaNoisGSKbJ8MBrmsbCLq99z7OiD77v1uU99+dGf/rmtf+9H3nDq9qeOnOyn9t+5/+43nTv/G3vV//yDD/ydaqe/1147Ojru2vdORId0XOHTB/XXe8W7LKyfv/YrZzbPLPiTaLLN69uNSGazc9d2ief3HD5iMjefz5966aUr+wceDJAbj5dHvQxy553zgNenraTgjJ3OAvhWTVagVqFh1SaFGH2vLKsQGKznlJQEusMwDGBq0LwsLMK0qskOp00N0Y9KU9c1ADjnQrxx8rE7NtMmbdu6sAMGXVtfx2ny1zdNHkeHNrzD5dtOLlF+sLcX5i9tzeZ+1BsvLhiEsy+/MloY2yORtgcf+MrXnz6U3/fv/uja1f0Xv/jPb8+XX/yf/kP3p1/7p//n7/3kxz56+/38+oXlOwf+vdvyjWnxhZc3+eTiJwD7pl/0zPeDXl0dSAv+pfMX86MnaDD0rXnm4paPNcT8wWeevOvkqdQ27Gw5Ho0Go6hmf28yiXXpst6sOZjUZZ4JqBBu7mz3+z0xdm2YNdxWKgESZVTkLqGZNnFeNZ45xqjChAAAtsh2J3VTwdJorak9clSQyKgK1mZ5nif2iGhNZpBFZFa1KOwkiWrdxnkVSONb7z156sjhV67uP/D6t/f7g8988g+krgYrK8b1MIXCZSEEH5P5+b/7946sLLT1/lvv23jP/fcMyvxHP/YbaSffGPTL3trx28ulYxcfef4bNHqgPzhSwmw/PHP20tP/4vO/fHr/hZTuLl3WL95oyu+d1me+9KknjxzaGC31zm5Nnzp/1RPtzeSZ/YsvX740mU4Pbxzu9fuz+VySpBAmMfgQSLGaV7PKT0LYrqr9tt2rGtQwHveNxSpKRMiznAhSlP15tT+rgQxzFJUo0sZk0NaNr1tvgFYGRY48r+eSOw6KANaaEJKPLKyoTKA+pgIhV+gVZR1C3WpbVe95x70yjwnLo6fuOXf23EtPPbLYN0vLo/54YZzT8qhcWVwE68zxjTvve8ep0WD9wRd/fOOW/qWnTm5vf5aLNTdev++Ou7FIX3py+88fvnhx53OHVvm5x3/nq9/4fZynN9x1z23H//LLl56O8fHjK+81pj+7XP/Jn3x+eWMwHLtzF69u7dW9Ms/4gHBoye3sz6sAUczOfiXWeYEaakNQz2fOUpZnk3oeROoYWcx83jrrRsNRYY0m8aytZhpwc7I35RhIA2BgiSJCbNSSzXb364vX9mdiewtLwOxYTaxARcWwYozsQByoeC9CZFEJ2GZgyu2tK4fXi/e+6w1ndqfjhbVqXj39xEMxhJWltaGl5V4zKCG3TiJKK+aH/+0P33Fbryzv3ptXLzz7lQ+8/z/5xpmvvHT5i++7/6fn/tk//vpvvXIZM17a2jz92FMPehodXt14/vyzt991y3fd/jO3L/2gSNxYuJ/04S38+d/9/Ys2rp06Uhzs8Nnrrc3iimT9AjP2pw6vLxdu6OyhcV9CSxKGmK8U/ZXeYHkwyAwG3xhUTm3bJpQ4LNyhhQVVFaVp1e7sT5sUdmfzVpgRNImmzq0Gm1uffNYrkejs+XOz2Wxp5VDRG7bWlIeOT2jpwoHZ9UXLlESMNTlNm3pujRv280EhuzubP/LDH9k4fPiFM5vbmzvnXnpxurO52C9Ll1vnin45dIV1ljFCmcy//L3fz1wwZozZyovPvrS1eXliTs9AbhkfP374nXvt1T//6p9uDF957+tOLpTZA+984P43fHi38c+8/Lml1UduWzn2yc/88nDtUS+PfvJzB089DtVufWyprEN4ZXOrZ+CO5aUTqytrvf69R287tXFkYzReyMuccFwUh914wWYFqFUm5WEvX19dGpbZwdyntl5aGB+/5ch8Xu/Pqv15M2v8ft1U3keElEQVkTDGqCKMHIUTp8FgRMbu7U32Z7720Dt2b7Zw+KCFq9u786r2UT2juAHnIwtZyaFPqd8vANOH3/d9Mp0/de7KfH+/Z/nUkaWNcTHMcWVUDnp20Y2cyROYsrdgJRK4YwZ8VZ39/g/+zO7V55986LMvV3uzuyJqgTP2V3eXjqx86F0fvzT5Qm+Nhu51b77jw888ev5Lj3z64tK173r3j710fusXf2F6/tKJ5cHYp2dfubazcGhxuS/Lg8GbHrgza3OIagRLk0eIfW1XjyxVod27ugWkaAZMiUnKUW+8vDSr5nvN+e2rba/XC0l3Z/ODaV0HqX3ar+cAQGDaEJwBNBhBrLWShICEQZjLvEiFztvYXN/dfPTlft+xNBhnpUuQiMVNa9y1G2vluEybCarCmhKxNPbK5hb2e/e/+3bDKc73uJ3Faj6f7ZTs0khH4/E4H2V5bn7mZz8B6AiMxGo4KA6vLjzz/OkvP/bgLau3vvHU97zw+GdPnLDv/O5/88jhv749vzhvzLHyuwdFBX5+/YJZPX7LyTt/8ud+7tlHnnkmGxarK0f3d6/u7p5bWToagilMeMPrbkPOxuPFI0eOLi4sF3m5emh1aWl5UPZX1pdsYdWIkhqLWeZya8WHl3emSHDrrbdOZvPNrZ15m6Jg1bShDZa6MyYihD76mPxoOOhRr22isS6zGSmBArnc9YoRa2qqpp4rKBCAREvsICSNbGGGYAfFuOco+QByZvv6kXted+d9d29PJ5OkS0eODw4dqmKcNGF3GnenlQ9NiK1FEodxf7q3tnzi6iu/+/tfeSip+/j3fHzz0gsAAH77cH+8Mh6dufo7g5JyWALffOELv4Z48Dd/4q9dx+y//MUvfeErD/fEW762n47nG2+ant86c+Zccn3MC5EsWn9lb79Fv768EQTq0EiK0fjdZro136uqmcttr9cT1f1ZVft2Pp9nWcFIV3d2pyG1PgpAAu2+MSKgQMSafGhKY5fLfqh1j4UTK7phf8zpYF7Nxr2ccswhi7WooLU2UMskYGBBq8gyZXOu6s0CLdrjz335xajpJ+69/dTR8ROP7BxM5vfff/+xIyvXTxwLVXtt31+/cuX6zu6l3bl10FeBnf3nq+unbXU142J5lL33PUefffqsSBwuHXvua/9X3Safb588dodzW8t3v+3o7R966OlfOrN15J/+xuXf/hf/e9/4UWZyut2rutGKGZ68cO2F4eIScv/0ld0TK+Vetf/y5pVDa0fyrGyqWagrSexjKyKuzEyWCblJVdetVyRwZta0Z85enM5n1tqgEmNkAUFQ0CTMKjH5vss2BqMlpKthisToijol03gFk2W5iFQ2L6zBGCEycNKkwVo01gpQsP182LZ205vrBpYW15vZ9ZdeqVeO7pbFAsT5Fz/zmbe+5a47Tp0s1g8XB9snbl9rZnF/d2L+/t/9j33u+nm8/OSfzvano1V+4P7bVxbKW5anOrinN7rruWf+j5XVhQ9/9Gey4rsffPrCc5cj8AdPX731H/z6V77+0HMLupWJxGxlMDRaggfpF4P5/p4289jWyZpbBmWvP9qr6pfOXbi4vb03n23t7s7qqle6oiyscVVVzRu/O5ntzqt5TJMmTqaTg/k8puRjDDECInNKIECURHwMwunQcHx8cSlr+YBnjXIwFm1RFoPoOcZkcwvGskoUVmcEUBRK4zKgmlTswNiBEc1NRIqNYiwWz+9mj5++EiFP7P7oj/74sSe+sb2zNa9lqejlWZ7nbrgwNP/Z3/p4YdaC3z5/9aFBnwdDWFxbEDx1/uKjC+Xti0unjt31QJsdeeip8tN/Hl65cuzRc+0Xv/HEU0+cmV272nNVAoiMpcswHyMAR1MMDvdX1q5snWubvWE+PL46cDbTiFvXdkEpxugUloej0Xg8GIzaGDevH0x8mAbZOqiqAHuxqqIPKZFxICBJQDEzBhM0KdYpAMIoK1aK0qkoxGlInIAgM2CzogAD86Yqi15unSoaazkEUM6MMS5XWyhD7jJrUUhs0SObWWMMR4N2MuPL16qglJXWh3D54u58quP1Q8+fv0axXlhesfnoVs64X64dWrx7/bCz41s45QMXl/MTRWG//swLf/CFs8+/sn919xVBKXtUHcyj99K2hNp9f4FBEzDERBZDahtfLw0Wlg4d3Tu3s3Owd/7a4NCyqepmPB6Xgz6D1tNJUfRTSsKAaAS0bsKkaQ9mFTkfJSirCjIzK4GCqpDaRoQVCIxDyMkQqgp3hyLRkLEWM2eMiZxuWIRAAGBNFm2EFLqThZFjlmXOubwoQlJrs+68etCgyv0eHEyme9vm8Mo9x1ZP7e6fXr11mGvz/MsvczrCtme1LAM2GSzddd+PNe2FvH8bCwC9lB979y//5rl/+WfX/EBcn6tqBiHV+zuD/BCwGEuJbQjQ/c+fyAESSNvmg6HJTBSzsnYK/u+i7iTW1uy6C/hqdvM1p7vn3ndfU+9V48SOcZlgO1JwEBNQmJABmTBlwpARE4TEjAEzhAQDUIQIIFCiSCCSiCASFAUERMhxSGunXC676r169d67/Wm+bu+91mLw3TKzoyN9Z/B1Z++11/+3h7vd3Wcfvb7qMz5Yr9999vT67rZyfnX+2Iodu/0w3hQAY58tDbkkKSJlkmICBDz3aKgqKGSdBpk72rFmtwpVTWQmCuKInENhb86RY0hKREhOwFTNO/bei6p3HlxQQTE1BAUoIgY5xnruzSxa0HITYer02GH2UXkN9ca3i/okLk/jbrpzguohlALk17X/SRMwhl/41Y/+03/9g4vPAvk1w8jd9QmMKQl4TwTOQyBPFkCCxJpHGIexahnImjoI6qHLp8355uydjy+ev7rrNttzjqGK7rStkF2o2iJ4+Ozw+vKyAGbE/TiNRcC5nIskQWQEEjEAMyQz0TKbOxgRF86tgm8ci+as4gODWDZwOEcNgZmNmICKSgQidAUm8o7YCUARmSOXqsUQApIhsA+oqkU8Rm50LDe7Sev65NNXze5mT3HThmXfg1PzwcCRAkoBuj7kf/9r/+OXf+uj4VgtKznZpNvDNA0AY8lgq7N37w7XJoWiM2Ig7ygyCVApuQ/BD4d9ocJuLVRl9QJ46POQJIMqyOl2NQyTqo7jcBin3TANOWfg45j6Ikk0lyJiRAoGAgaEhKRgCuYRAmHDbu390vtAMAIAGBsYcjFCZHKB2RN7AwTCOQODTAAIhmIoooDMPhJ7IAEiJEegRNT1fc2hHw4hEEVXOlFsXn9W/uTVD9uT7me++tbY7x3PSo8kBf2zz27+/j/6Vx9+fPf22+8+fIjHi26YIjQ25MPuZldV26iublZSRiAFdgZBxKs6x+FwuABdFWZasq9IgQx8XW8E7KMXn7WV3777lKqmIt9l/eEPX952E4YqZ93342SWRIdxnKMcet84PdftikpWsI0LVQyr4JbeRUZCIyMEAhFmDxDBRceR0HkfkaOqAKEoBB8LDwoGZqKGbo7UIjk3xxfmbuAQAtiomnzYKrWqPTMDdmu4vDtMHz3/+Ovvf5HIBCCDDx/v8B/8419+fmF1tZyGq2GqipX9cCnOn5w9i55tvMuHW0Z2HMAoKZBvXL1U9oMIlEPqDqzkkVQGckzsmYNidXPMf/T953/w/Y+fX97tkrza7d503VBsAuhy2Q3DsR/7Ybqf9DEzMzIhz46YIaJ3tI3+rInny+WmqRzq50kgR0TORx9adhWyA6Dg6xDbUgoY3afl2KsCIiNiXS0BvRh579VQoPjAIhJC6PvDNE1qpFjVzRpKyuPrsdtFbP7KX/rrf+dv/12HaoB4MPl7/+xffLJ3T84evXn5YTcsqkUJOI6lL33jYhMApnzMeRemygjGKXXHoa1Xi82JQepSB6mHUpNaGQd0dYjUAUgx5Oia8GZ3vf/D73zvgw9PTza95C5PweJxGA/dOImK3WeCtEhonBlaKXrPnGgMrq7rFeKiiqtFFcymXmROvDF5854iYwRiUwRA8r6q6m4HwKCqBjR32AMJADTNEhCLgXextwkRfQzD0OecARDZDSm3rW/a5c2nH+yvLgdI3/jxZ3/r5/9GHWsHoInCP/wnv/Kdb3dnzx6Lv3VV2n/6aeUm1zyQo+XLG3l3k1dnJfVtHgeRRePzza67uFy+vZrquopP6mG4O+4Ajy6zlmdSwggUV41CRFutG1/Gw3HoBsU/e/0i52m5qhG8IigYEpoURo1MpAaoxXROLDjAxrlNW6+aeObrhw1lgWMR8zg5TtnOffmQqsO0cG1IudO8ZgiJu07ZQ8g5Q7UQ14q74ElL8s12I84BAAKlUpyrinA/KPkFRQdvpEGnq3Vq1jRc7a4+CJEkfDlL6jRTxzSx+5e/9Fv/5Td/9+zJepLdOLr1yds99K9efjr2RzPJKtM0OReQnCnmnKWkcehMEpiIiII7OX8SQjUMU855DkGM4wjEJ9sz8Efw6uuFib73ePU3f+6bP/vT7y8MUrcfdruSMhhRaMC3vfgBYrfvc1+gSEQ+qasnJ6tnm/WT9fJ8vZyIByrslAAi+mUdOFKPzWJx2sRV5RZiWoiYKh0n9Pdt8ESEyCVLCMGHCu6/oxDC3M83jiMRSTcW64uLjIsay9WnHyB4bh+1m+aDDz/7N//u1+PJlr/+cz//T3/hP1SbpxOOahk1mqILdvfqFZKvYkwqylR5Hg97z4HrBdm0v3hNqqFuMjlAruo27a66w3W7WGareXFysl0fr193t9cpH4qB45C6/UnQb77/xZ/+6p//xp97f9HSKnq20h1209ARoGZhonUVV2170tTbpn60Xj5Zt9vGrxyAaa9gIGRTUQSiOiAQvIDHSRgsLJrV6qS9uHpTJlk3iy7dqoGPy6quNXdTN7arLcZqTrXN03IDnANgi8VK9re3+xdhdb5YP9u9/mi6/sFyfQ6Lx8wi2f/et//w0ZMH3G++shtL1SymUT36nHpTQWywvzse9quTk0I0pGnZtuPhyArc1P3++nB1Eb13MWKozUcMNRxvDvubEAK4VVyekuNxdxlM8iDZKFaBTeXQxyTn6/V23XzzL3zpy194+oW3zs/auKn4fF09WtePNtX5cvFwszxdVNs2nC6qVeU8Cqn0MgIHVhAVq6qmgSrw0dpr91TJqmoRQ9Ud35Q0qrDzMOS9cy35xsUKTKZuaNolVDXjfeh+TPeACLNvmkb6q0O3P3v0LE/lzfPvrarYbh5NtEAb6rh89erNRx9/6C6vtaoXx8NuEU8lJ7aSUva8rZq664dpGKmqdBxU1VVt6Y6Q+nTsckpWVUU1GqhiNsTYVov1MEybTUSDu7ubNoSkICLeBwV29RJkuuz668PtZF23g1i3Tx+cPDxZd13XjcPUd13XpVR+xGcyEqhpQQPyHEygIBauQx1OQirc3vQn404gQliGcXf83p/83yePnlJoh9ITkQ+1ciiILq6ArnOZWnYillXuSTRVZu+9R8QhHaLfeNVXr79bNQvfLjJ4NmMMKY+PHp9/8vzCBV+lSUiIIZmlsS+rzaZk6QFiFcZxjKH2pmkcYt10+x1MHagw+aTmTEuaspIPMbYb8k0as5lpSd6TIzZ2QAOhk5QZyZpwOd1ddtcnJ08GC8NQYDhWIVZVHaO3ZTOObRnHUspUSsmaRUu24kgFeCxiGZqq8aFFC86n5ZM9LI8v36yrGANf3l2GyKWUuPBUh3SzJwpGQTlSCD7Ufd9VJYGLlgWMvJ8viSGTmHbDkWF1d33lKbfrtwDrqRyZkio4D5YlhgWVscMCDqnv7obh4EPVj0lpAhfnjCMDsmkeJiSXNaept1ycCwWdmGkpKMUk1aszjg2xFxEm9Ix3t9fb001ollM/pGMH5jYP37O4/eTTq+FwLBiSOUU/ifZjGnPJUlzwLkby3vnoQmQXKER0lZLP6ELVnKxX54tq1cSufnJXvwMcyLtNu+ouL24vXp6cPhR2wCGPZsUII7gqA6OrV9tTldztdjMS9XkSmeeod84ZjRTHKU/b07fQsXoEYitZAYk9sgMAKqUgGTuYcgLCJOnY7wwtNO0wDIQOETVlydOYppQzWsk5Ox9dCFlMcnFgaRrQx/PHbzkfxnEMIThHL1++/MGH33/29tcW7dpyur3aEZ0vF1/aX5fbN5eE4lBr79gUQKPjOWNjrjZXs6vZReSA5MxwmPLkYtsu1uzr0pOn2+bBla2oG548e7t2zfMPvu8U1IiaBYUIxXsOMbTsq7GIkT89fRCjT92w3+8/BwEMCL33IQQAcOIUuti2QBvnHGByoSLv0PlsJEYueH7nG3+1qEw5AZBnmIaOEHLRxaLti/A4CihUDQAhihz3Ngk6V0wDu9wnjlVYrIyoaKlOHiWumHldxf31jY13F5/8UYHy6J333LK+vv70eLiI66XE+s1xetS45foMkQMR+yCuVaOlQ3HSlUmZzWLRUNghyIoUvWfhqoJjtb1a/sXv3AF7OQmnS5++96ffutu93j56VHyrXNVNk4b9BLDanIOhY0NnBUO9OD0e71B7GCYL3mLkrAbgqwhjuXz5+6F60K7fMu+KmIOIzEIKQmDISEWEH3zxZwwsuDClAQHNNE1T5aOChOi76121WrXLZXc4xiZOx2OZ+hn5ntOo5APFoIZaxMdYBe8RppTGYdB0QO278QhUnT14Z5ykO3Zjd1y0a6Jl2r85Oz2pQ0AfONZVdKtF3U/ZEgVaQwneUfRgWQRCXiw5jauW1Z1d+MeHpu0Tn63fevBo+du/+euH492iXXBcYFhwbLerzfXFJRLU7RZcZQ7YcQghOAeoJU0MLM4BO1BDJl/FYXdIx5c+nmBcACEzMzkFAxSHzlRNiqnw9r2f1iJNU085pZKZXJ4mNhtSCjHqOGUzCFGL+irmYZC+MwQkMgVEMiBf1egdG5YijIQm0zghcxr30+GqbmMqnKTdPnrHB3fYXZeJuXp8zH0Z7jbBqnalrpYiDo1ChEz9oMvlusjYHW+Z/Ji1qPruDrYPvzs+eemfVQ82K4/5+upb/+c33rx+vd1uyUWMK65PF4utZDncXPvaV4st+grI0LEjdszkUFNhIGAH3pORC8FX4Xhzk/tLX63RN+Scc04BRQRJNQGYzCaCcy4cDrsQXeXdIWdVrXxIXW9NHIahXaz2eeqOAylkEUM2k/muyqIOSOdD2OWS0qhoGp0zYkAwQgUTgUXbJAGoNptzKN3tcTdgLuofHZ9/L8r0ZeR6+5hC7HMhmQQMGxuoF3ICFQd42DQ3b253zeOL/DQ9e//Mx1d/+rsvvvu/9jc3/b584es/NR37rs/rxQNxC1e16XBZZGzCKfuozgOC9wxKkwg6X7WrfOiMaJ5SueABVCSrIbN3PrIPiDSDTPdpUr2XU6hpl0XS9eWld1zXtYgxs5QEWeZARLtc1DH2x4HQgfOiWa3YPbbDiCg55TTiDA9KIfahbgAZkRmJoDYz5/XN1WVx9eL0cVxF8kdptof2C396TR98/NnVy493l2+mjAVjNmzrBsmLX1TtsnGEse6Wzz7Z/CQ++uqKxw9++xd/71f/7e3LHxbP737jr62X54deoADHUQAADMpJREFUjGoKTbNci6lBNhh9aNB7RSCiECIzmyKH6KplKp+jbSE6H1NKMvUzlx9CcM4pGAI7580MmMgx8lziaGJV17cXr/Nw2rTrqcsikwucp0k8TFld8uyqOY3O3uGMN+fsXERE51hyGbpu2SzMUZfSJBrrtpTikEzUjNWsia6oJDVu1n36wbvnUp+fHNLpq8+q4eWHfff87Sdp30/15tSNJR5kcfIAK5zGI0i8kvUPVw/j5q3y5pPv/u/f+ODPvh02D5596RvYbN3i/OLFD1KGxarmWBUwdjj2vXfknAcgUSOHDFjEkJ0SYiBBZ2CVczE0RE5ykWlCx8hOAEzURMgQAVQ1p2nR1AWhm3ZuAltu1v3d1e311RpDbOqpn8AjF5hKrp0bus4H9Y5Kue9NNDMVYQdm6LwTs5LzkCYfIjFPRbyj+1oSIlDxPuYpOw5DPy3a5TjJd7/97S+8XzdPfuL8C189fOq/c/2Bur3j/QNBUJR+Wu4PJ9tFEtiFx/vm4XGXXvzOf9z94Du7y8vNu1/zj9+1zbvrenl39XwYOjOpmhjrcHXsT5aNiJAgAquAoHlmKUWyYIhF1cdYtY1gjjE6dilnFNWc0DtCVlVDIEQVNbD5ObXPXSkaS67bZrVa7O/u9ne7pmmd9wqGKnkc5rcamIEooCKDqs6WyYyAMPO90gdWTA1hSgmYvPcEbAIG05STw9CEmHNO4L78la9XwhevPrn4wR8fbq42732Nnv7UHSxzzuVwZZXe4MH4WOVde/LwbvXOf/vWH/zPX/rnn3zrdwrBe1//5vL8x9if+vU6o2FhJA2RfaC+PywWDRhNQyaMMPsryNHFGT/0c3HG+dg0M5GjCkM/mRaU8iPVjojI+bkNlZnbth3HcRzHtm2JjkNXwumjt5d07F/+8e76DcY1YF0gmZahjK6UZVP7B60WwUnJOQCK3pdSjA0cK0BJ2SNXBkuyINPxbsexxlCZi6YBTUUmdLSs4nS388uH4ct/WbI2y+2+7y4vvrdcTUc5Pr/e7UZaKrnC+6ueTr7wsVa/9iu/+Ml//89Vu33r6z97/uWfnRY/Ls3ZZnUS+5S6XaomTIlNhd1EjffLGrQJLpGbUlIQZOKwTMKTDADK6sso9bpZrB6MRzxMXd34fByK7rJbJgAXHBGNacqQffR13N4d7sZxbNoTxiXloYcyUhUW588OfRquLrwk8/6+uigqkg/H/fHQ3/ezfm5+zp9nhNB7X0RSSmrmnJtHYT4GIFQpTKAmM26GiN3QP3j0mDL0ly9WrdNculevdxf7q73eDt3zVy8JcP3o2R8+v/jXv/xrl8f85MffX5+cr1brpmmqpubAVVXN/UaWpYiQd/PeSvOCgqoaktg9xqeqBCqSZ0WKCAxpfv9679FAS7rXAWcXD7mqqqZpxODm5qZkXa5XxJB1IhkG6Xa77lidv7M+e+vmxff7qxeuXhA6mBl7k5JyTomZ5yUAQ/58IRPmKsfsCeUyAQA7pwiGHOpGEUAKo5kULQkAvI/jOLWL1eLtr1zd7KYh+7hVt03LH4On37ihzcXdjUzj6Krf/3QXVm89evsr0myTODBSQ0Mixy5wkUwqKKUUDbEmH4g9EUm6B7qNGJkQEUHns5DSeH/6xAzAOXLkVWQYupwzAnsf5wGpc64fh91uBwBnZw+cCzlPzEbJcr+71pRHiOsnb6uM+4uXmqaqqlR1HDoynY93Lsw5dO/vJ5azl/C5XGNmBmg6a8iMPgRBBBOTMgNrKSUfAyAfu7F+8hRDfffiUxunUp/4Zz9x8hNfe3V0n76+CCjXw2SnT+vNk6RO46KqGjMGICAMMaoWk2JFSj+KAvvK0DkXUGXojykl9lWsGkNm8ogIKoz3jLuqijEyzS655pSm3syqqgImERmnqe/7lFJVVdvtthTNOaNjgULNZtUd93YcrVhYb6qzk9u7K7m7qqrGM0/DcRyOaMLkzSxrRvbI9y9C+Bxwc85JTrOraGZAjIjkA5K73ylJhQhmFNK5MAzTqsGnz55o9xruPkHLagnSUUOAuLy5ueqz7hIOwxCYY710xAUQnJ/h0KHvQbVM0zT06JyvWiWP7FWkPx5KKVXdxnoBNNf51FQJZhDkvh9eCQGU7rXz5IPzMapAMZiRqsVqudqsk5SpH1QMEBWI6uVivTm7vbzU45333Jw/SQrjm+cgWtWBQIbukKfk7plYm584InIhso8wk7FEkqeScimFDBDRDIk9szcgRCw2u1JkUgjQM3X7cfP4bT7ZvLm97o+dU5hyOf/S+yVsrw9dNqwWm+2qtfEYnCsoGQjJExGqTN0Rci4llZJCrF2ojJiINOc09g6palrn471ypyaS75XgIqqaBYqpWAE1EFFJzrk0FUQGI3Lcti2Tm6ZpvuOYWQRjtaCh77dPnlH0++vn/d3V4uzt1enD/ZuPLy+vg/Mhuq475Cl5F3UWJImBmF2YL9I8gAAtJprGvqQJAEDvN2Hx3htS0Rm3ygQwo3WR3e1A5pqH73110vjm9WdTPyWthwlw9e6r/TgKrtanajk67A4dBKfeY3AxRsuFzTSnnHMxDaFiHwx4pqhUMjOTC4YE7JBJVdEUzcqU5teZCoipkiKyFUl5vEfuwFQVjIww5ywi7WIhkpk5VDWQJxnTccynD891OtxdXLBrQ70GGN+8eaNaHGFOk6qGEAAol8LMMcZ5/ebzQC7P91oppeQ8D3ByzozknFO8Vy1FRCSrKkgxLTHG42cvHrbrp289q+Swv/rEcuLbG4lnbnU6Fru6vFUtaRy8i4VoKpKLImKZkjOUnCVPYkrOMbn5AZthu3sybwZ+ieZpndm9Vuq9B8LZvHPEZlbypKqxqUsW9m7ec857v1gs+r6ff6GqGlMmnsrx1RtQWD15ezcchusX5+vaFmexfzEeO41bzx53FylfQbRanWtPRoVj3xlkRgFURD4OZeKM0WedhU7MVkYirZcoCcqkKbEoSmEDIicKrfVj2LwaZPv40frRO+m4m65/mGN18rANyy9mXaL1ZRKuVrHxXn3LsSbQccw5i4ejHrphWLgTf3IysSOG2ud+vNxjGXxQogmVAhYZCkxjyUUhhuBEnJnwJDlUVk95TOM+wOB9KxCNHZCxsxBC0ywMyMzMEQZnqByARIrkdNztq1A/fPj45nqXBepmJWU6Xr1ZxhhivdvfajGwuNhspXRs2TklVMSMMqFN3luUGAv7ZLX5BoMXrsRHjQAKBMighIKgjtTRhCgKMYQ0DdOUT84e1+vT2/2hP9xe7fepWmC7WG2Xy/NTv94IkXnPde2rhRoiMohCyY6AGWtaOGwQolfXSqgGW6KvydUYMUGFMai3UWUUEkTFrsvEgb0rprmknDMaMnudzJmPXAeqIkQ2j8Ik7CE0vsVCkSoa+mvHojpe37wKwa3Xq8OxJ3ZARtaXsVutNgWmfn+IXIkVyE6zk8FsQqfBYUMWWXxSscAUCYIqlwI5o1DwaEAqYKKSpSQ0c4yOtKq96YilV81c16uzs+hxf/miO9zW20fNZtWEDCCTlGnsCK1oKjalqSfLko5p6g1SiDiBlcgSXUYVmSxPvsIchCIJiTlLJFhRcjJAHiAjqGkuuXec2ck4HFOemFk8YOMh0GBpn7p96hIUqB3WUYMrjhKBQ14qVGYYoxuTb1cPwapxKLlaoUcLLUWXCEPTbrePXg83YbmxYcxlBACuax+aopbF0Bofa/Yorg71CjCiqW8fIC+MWubWxSbGRazrGe3Lpa5bcC4JEjXbk+pMrB33N86tmsV7OZfj/nbogXkTPEYX/dlDVkTsYwyToG8KIlYnD3Bzhs0yhNg4zIudVFfWnMXNY6bG1y7W1XA4+IVQwgTsw6quVhSVArVNyHJMtDb3wMLj1enTum3IcVF1voQfzRMBRaSOMI4jLh++a0aETlmOY94sz73l4fB6GAbnTfikDnG4+7jZvuOW75ThM9MkUkzuVV5ysYghshdlF4jVQAvXynVDQIfL3d0VOQ++MvZIzvs4D30mosBcShlzjlUTg9PxqGNXyDeLJ7kccr5DqKq4REtaDNZNHtPY9bX3JkOSkgvEeuFZjSJRCKA67LrjLrRLDU1QmhcFp7HzqHnosyCH6NHlBku24GlKJoeddp/69tlydQKISQoiGoJnp7NlSTQzjzlnBAJQYmbRDABg3pGSypxzL+YJIEAekQFbslHBwGRuBgKAuQECgBAmg/vd7AwJMIJJkKRz+xcAoPv/Jj/CXOkBICAClTksDgBKAOKABLxBBjACMtB5vykCYDBFELr3l6PhBIBgHlBRCtzvJecQwWweswuCEgAhZCMHWgJAcYAG6hxq0JwBCsxeOeCP/kA/362ImeeJyv8De1RSstlfRLMAAAAASUVORK5CYII=\\" alt=\\"image.png\\" rel=\\"4\\" /></p>\n<p><strong>Guillermo Ribeiro Jiménez</strong> is a Sr Data Scientist at Cepsa with a PhD. in Nuclear Physics. He has 6 years of experience with data science projects, mainly in the telco and energy industry. He is currently leading data scientist teams in Cepsa’s Digital Transformation department, with a focus on the scaling and productization of machine learning projects.</p>\\n<p><img src=\\"data:image/png;base64,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\\" alt=\\"image.png\\" rel=\\"5\\" /></p>\n<p><strong>Guillermo Menéndez Corral</strong> is a Solutions Architect at AWS Energy and Utilities. He has over 15 years of experience designing and building SW applications, and currently provides architectural guidance to AWS customers in the energy industry, with a focus on analytics and machine learning.</p>\n"}
目录
亚马逊云科技解决方案 基于行业客户应用场景及技术领域的解决方案
联系亚马逊云科技专家
亚马逊云科技解决方案
基于行业客户应用场景及技术领域的解决方案
联系专家
0
目录
关闭