{"id":782119,"date":"2021-10-06T06:32:11","date_gmt":"2021-10-06T13:32:11","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&p=782119"},"modified":"2022-10-11T14:51:07","modified_gmt":"2022-10-11T21:51:07","slug":"vasudha","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/vasudha\/","title":{"rendered":"Vasudha"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t\"Vasudha\t\t<\/div>\n\t\t\n\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\n\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n

Vasudha<\/h1>\n\n\n\n

AI & IoT for Sustainability<\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n

Transportation and Electricity generation are the two major sectors contributing to more than 55% of greenhouse gas (GHG) emissions and related climate change concerns. Hence, the primary pathways for decarbonization include the fast adaption of renewable energy sources in the energy mix and the use of more sustainable transportation alternatives like electric vehicles. The rapid adaption of renewable energy and e-mobility demands new technology solutions and business models to reduce their CAPEX and OPEX to make the technology affordable. Additionally, it demands intelligent infrastructure for robust and safe operations.<\/p>\n\n\n\n

Vasudha<\/strong> is a collection of projects that offer AI and IoT-enabled technology solutions to drive sustainability goals and address the challenges mentioned above.<\/p>\n\n\n\n

We are currently working on the following research problems:<\/p>\n\n\n\n

  1. Optimization of distributed energy resources (DERs) for carbon and price arbitrage under the stochasticity of energy generation and market prices using discrete and stochastic optimization<\/strong> techniques.<\/li>
  2. Developing Vision AI algorithms<\/strong> to reduce manufacturing and operational inefficiencies such as solar panel manufacturing fault detection using automated approaches.<\/li>
  3. Driving EV efficiency by modelling EVs energy consumption<\/strong> under real-world conditions and EV battery State-Of-Health<\/strong><\/li><\/ol>\n\n\n\n\n\n

    Over the last decade, there has been a significant increase in the development and deployment of photovoltaic solar energy generation across the globe. As of 2020, nearly 105 countries have invested in Solar Energy with a total of 580GW of installed capacity.<\/p>\n\n\n\n

    Photo Voltaic (PV) modules are the commercially avaialble basic building block in the solar deployment. One PV module typically consists of multiple PV cells which are arranged in matrix form of 12×6 or 12×5 fashion. With the increasing capacity of PV modules, it is important to monitor the quality and performance of these modules during manufacturing time as well as during their operations. Due to various real-world conditions during the PV modules manufacturing process, there is a possibility of certain PV cells inside PV modules getting damaged or causing an abnormal behavior with a fall in performance. If these defects are identified during early stages of manufacturing process, the affected cells can be replaced, thereby effectively saving major losses in plant efficiency and performance as well as monetary losses and warranty issues.<\/p>\n\n\n\n

    Many of these defects are extremely small in size and are localized  to a small part of a cell. So, such defects are difficult to be detected with bare eyes or through imaging techniques like infrared imaging. Therefore, Electroluminescence (EL) Imaging is more commonly used practice in detecting faults and degradation in cells from an EL image of PV cell.<\/p>\n\n\n\n

    In this work we design and develop an “AI-assisted system towards quality assurance of PV modules<\/a><\/strong>“. The proposed system accurately classifies (accuracy > 96%) the faulty modules form the working ones, as well as correctly identifies the PV cell (inside the PV module) that contains the fault and the type of fault. It also helps in correctly detecting the location of the fault inside the PV cell.  The performance of this system is evaluated on open EL image dataset as well as on real-world manufacturing dataset.<\/p>\n\n\n\n

    This is a joint collaboration with Azure Global team.<\/p>\n\n\n\n

    \"Vision<\/figure>\n\n\n\n

    <\/p>\n\n\n","protected":false},"excerpt":{"rendered":"

    Vasudha is a collection of projects that offer AI and IoT-enabled technology solutions to drive sustainability goals. This includes developing Vision AI algorithms for solar panel quality assurance or optimization and multi-agent simulations for renewable control decisions under uncertainties.<\/p>\n","protected":false},"featured_media":782188,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556,13562,198583,13568],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-782119","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-research-area-computer-vision","msr-research-area-ecology-environment","msr-research-area-technology-for-emerging-markets","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[796942,861837],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Tanuja Ganu","user_id":38883,"people_section":"Section name 0","alias":"taganu"},{"type":"user_nicename","display_name":"Akshay Nambi","user_id":38169,"people_section":"Section name 0","alias":"akshayn"}],"msr_research_lab":[199562],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/782119"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":26,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/782119\/revisions"}],"predecessor-version":[{"id":885096,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/782119\/revisions\/885096"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/782188"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=782119"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=782119"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=782119"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=782119"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=782119"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}