{"id":2705,"date":"2022-11-22T15:12:27","date_gmt":"2022-11-22T15:12:27","guid":{"rendered":"https:\/\/iot-ngin.eu\/?p=2705"},"modified":"2022-11-22T15:13:31","modified_gmt":"2022-11-22T15:13:31","slug":"online-learning-service-for-power-generation-prediction-in-electric-grids","status":"publish","type":"post","link":"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/","title":{"rendered":"Online Learning service for Power Generation prediction in Electric Grids"},"content":{"rendered":"\n<p>IoT applications, in many common scenarios, need to take smart decisions based on contextual information they have access to, information that is gathered from the environment by bound IoT devices. We encounter several examples in the use-cases of the IoT-NGIN Living Labs (LLs). In the human-centred twin smart cities LL, the application for predicting the traffic flow and the parking availability leverages weather forecast data, as well as the road conditions and public transportation information collected in real-time. The crowd management app developed in the same LL relies on images recorded through cameras and other data collected from radars at road intersection points in real-time as well. In the smart agriculture LL application domain, the application for crop-disease prediction leverages images and real-time video analysis of the crop and the leaves captured from visual and multi-spectral cameras located on semi-autonomous drones flying over the orchard. In the energy grid active monitoring\/control LL, several applications for predicting the power generation, consumption and energy demand leverage electric metrics collected by different sensors located at the nodes of the grid.<\/p>\n\n\n\n<p>In all these situations, contextual data is continuously collected and dispatched, from IoT devices, to applications, commonly through MQTT subscription channels. As app decisions are taken based on this changing contextual information, the application intelligence needs to be updated to this evolving context over time.<\/p>\n\n\n\n<p>Online Learning [1] (see figure below) is a service of the IoT-NGIN ML as a Service (MLaaS) platform [2] that facilitates i) the continuous training of ML models (i.e., the application intelligence) and ii) the inference of intelligence predictions, from online data collected from IoT devices over the time. That is, the online learning service can be subscribed to multiple MQTT\/Kafka topics where contextual data, collected through IoT devices, is published over time. Then, this data is used to dynamically fine-train the ML models associated to those topics, which are retrieved from the MLaaS model storage, and finally to return updated predictions. Online Learning can save model snapshots into the MLaaS storage when the performance of the trained models gains a noticeable improvement, and furthermore provide explainable AI (XAI) models that offer insights to AI developers to understand the inference decisions taken by these models. Online Learning service leverages KServe pipelines, consisting of transformers, predictors and explainers, for a customizable training\/inference management of multiple ML models with different input datasets.<\/p>\n\n\n\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"530\" height=\"332\" src=\"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-2.png\" alt=\"\" class=\"wp-image-2706\" srcset=\"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-2.png 530w, https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-2-300x188.png 300w\" sizes=\"(max-width: 530px) 100vw, 530px\" \/><\/figure><\/div>\n\n\n\n<p>Online learning has been successfully adopted for the continuous training of ML models that forecast the power generation and consumption in concrete nodes of the electric grid of the Smart Energy LL (see figure below). From online published training sets, consisting of features describing the grid power consumption over the last 24-36 hours (averaged every hour), the model is continuously re-trained and the next hour prediction forecasted. Models have been further improved by adding additional features to the training set, including the weather observations at the grid site location, and the days of weeks, in order to better capturing and predicting the consumption oscillations due to seasonal weather conditions and weekly customer habits.<\/p>\n\n\n\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"540\" height=\"304\" src=\"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-3.png\" alt=\"\" class=\"wp-image-2707\" srcset=\"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-3.png 540w, https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-3-300x169.png 300w\" sizes=\"(max-width: 540px) 100vw, 540px\" \/><figcaption>Future work will improve forecasts after the analysis of the XAI insights and the continuous training with larger datasets.<\/figcaption><\/figure><\/div>\n\n\n\n<hr class=\"wp-block-separator is-style-wide\">\n<p><meta charset=\"utf-8\"><strong>References<\/strong><\/p>\n\n\n\n<p>[1] D3.3 Enhanced IoT federated deep learning\/reinforcement ML. IoT-NGIN technical report. 2022. To be published.<\/p>\n\n\n\n<p>[2] <a href=\"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/10\/IoT-NGIN_D3.1_v2.pdf\">https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/10\/IoT-NGIN_D3.1_v2.pdf<\/a><\/p>\n\n\n\n<div style=\"height:100px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n","protected":false},"excerpt":{"rendered":"<p>IoT applications, in many common scenarios, need to take smart decisions based on contextual information they have access to, information that is gathered from the environment by bound IoT devices. We encounter several examples in the use-cases of the IoT-NGIN &hellip;<\/p>\n","protected":false},"author":2,"featured_media":2706,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_mi_skip_tracking":false,"footnotes":""},"categories":[17],"tags":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v17.6 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Online Learning service for Power Generation prediction in Electric Grids - IOT NGIN<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Online Learning service for Power Generation prediction in Electric Grids - IOT NGIN\" \/>\n<meta property=\"og:description\" content=\"IoT applications, in many common scenarios, need to take smart decisions based on contextual information they have access to, information that is gathered from the environment by bound IoT devices. We encounter several examples in the use-cases of the IoT-NGIN &hellip;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/\" \/>\n<meta property=\"og:site_name\" content=\"IOT NGIN\" \/>\n<meta property=\"article:published_time\" content=\"2022-11-22T15:12:27+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-11-22T15:13:31+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-2.png\" \/>\n\t<meta property=\"og:image:width\" content=\"530\" \/>\n\t<meta property=\"og:image:height\" content=\"332\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Giannis Tsichlas\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebSite\",\"@id\":\"https:\/\/iot-ngin.eu\/#website\",\"url\":\"https:\/\/iot-ngin.eu\/\",\"name\":\"IOT NGIN\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/iot-ngin.eu\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/#primaryimage\",\"inLanguage\":\"en-US\",\"url\":\"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-2.png\",\"contentUrl\":\"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-2.png\",\"width\":530,\"height\":332},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/#webpage\",\"url\":\"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/\",\"name\":\"Online Learning service for Power Generation prediction in Electric Grids - IOT NGIN\",\"isPartOf\":{\"@id\":\"https:\/\/iot-ngin.eu\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/#primaryimage\"},\"datePublished\":\"2022-11-22T15:12:27+00:00\",\"dateModified\":\"2022-11-22T15:13:31+00:00\",\"author\":{\"@id\":\"https:\/\/iot-ngin.eu\/#\/schema\/person\/dac2bc3c10805a89083986685c5801d1\"},\"breadcrumb\":{\"@id\":\"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/iot-ngin.eu\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Online Learning service for Power Generation prediction in Electric Grids\"}]},{\"@type\":\"Person\",\"@id\":\"https:\/\/iot-ngin.eu\/#\/schema\/person\/dac2bc3c10805a89083986685c5801d1\",\"name\":\"Giannis Tsichlas\",\"image\":{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/iot-ngin.eu\/#personlogo\",\"inLanguage\":\"en-US\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/740c19c414d2291ee24fcbe553ee2609?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/740c19c414d2291ee24fcbe553ee2609?s=96&d=mm&r=g\",\"caption\":\"Giannis Tsichlas\"},\"url\":\"https:\/\/iot-ngin.eu\/index.php\/author\/tsichlas\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Online Learning service for Power Generation prediction in Electric Grids - IOT NGIN","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/","og_locale":"en_US","og_type":"article","og_title":"Online Learning service for Power Generation prediction in Electric Grids - IOT NGIN","og_description":"IoT applications, in many common scenarios, need to take smart decisions based on contextual information they have access to, information that is gathered from the environment by bound IoT devices. We encounter several examples in the use-cases of the IoT-NGIN &hellip;","og_url":"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/","og_site_name":"IOT NGIN","article_published_time":"2022-11-22T15:12:27+00:00","article_modified_time":"2022-11-22T15:13:31+00:00","og_image":[{"width":530,"height":332,"url":"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-2.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Written by":"Giannis Tsichlas","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebSite","@id":"https:\/\/iot-ngin.eu\/#website","url":"https:\/\/iot-ngin.eu\/","name":"IOT NGIN","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/iot-ngin.eu\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"ImageObject","@id":"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/#primaryimage","inLanguage":"en-US","url":"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-2.png","contentUrl":"https:\/\/iot-ngin.eu\/wp-content\/uploads\/2022\/11\/Picture-1-2.png","width":530,"height":332},{"@type":"WebPage","@id":"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/#webpage","url":"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/","name":"Online Learning service for Power Generation prediction in Electric Grids - IOT NGIN","isPartOf":{"@id":"https:\/\/iot-ngin.eu\/#website"},"primaryImageOfPage":{"@id":"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/#primaryimage"},"datePublished":"2022-11-22T15:12:27+00:00","dateModified":"2022-11-22T15:13:31+00:00","author":{"@id":"https:\/\/iot-ngin.eu\/#\/schema\/person\/dac2bc3c10805a89083986685c5801d1"},"breadcrumb":{"@id":"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/iot-ngin.eu\/index.php\/2022\/11\/22\/online-learning-service-for-power-generation-prediction-in-electric-grids\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/iot-ngin.eu\/"},{"@type":"ListItem","position":2,"name":"Online Learning service for Power Generation prediction in Electric Grids"}]},{"@type":"Person","@id":"https:\/\/iot-ngin.eu\/#\/schema\/person\/dac2bc3c10805a89083986685c5801d1","name":"Giannis Tsichlas","image":{"@type":"ImageObject","@id":"https:\/\/iot-ngin.eu\/#personlogo","inLanguage":"en-US","url":"https:\/\/secure.gravatar.com\/avatar\/740c19c414d2291ee24fcbe553ee2609?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/740c19c414d2291ee24fcbe553ee2609?s=96&d=mm&r=g","caption":"Giannis Tsichlas"},"url":"https:\/\/iot-ngin.eu\/index.php\/author\/tsichlas\/"}]}},"cc_featured_image_caption":{"caption_text":"","source_text":"","source_url":""},"_links":{"self":[{"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/posts\/2705"}],"collection":[{"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/comments?post=2705"}],"version-history":[{"count":3,"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/posts\/2705\/revisions"}],"predecessor-version":[{"id":2710,"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/posts\/2705\/revisions\/2710"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/media\/2706"}],"wp:attachment":[{"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/media?parent=2705"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/categories?post=2705"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/iot-ngin.eu\/index.php\/wp-json\/wp\/v2\/tags?post=2705"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}