ESO starts using machine learning for analysing clients PV generation data

Posted by Vytautas Keršiulis

The main Lithuanian distribution network operator ESO launched a new service for private clients who has solar panels in their properties. Owners of solar panels will be informed about PV performance failure or if there are any discrepancies in their generation when compared to other similar generating units. The data is analysed based on machine learning algorithm and client is informed by SMS or email. Using such information clients will be able take an action immediately and contact technical equipment supervisors for solving possible PV problems.

ESO believes new service will prevent clients from losing their generation. Currently there are aprox. 8,5 thousand prosumers that are using their own solar panels for generating electricity and till now clients had to monitor their internal systems to check the status of their PV.

To enable such service, data from automated metering system is used, where data about generated and consumed electricity is gathered. This enables to apply data analytics in order to check energy consumption and generation patterns and compare data with other nearby generating units. All private clients who own solar panels by default will be provided with the new service without additional requests.

Also Read

Cookie settings
Mandatory cookies help make a website usable by enabling basic functions like page navigation and access to secure areas of the website. The website cannot function properly without these cookie.
Functional cookies enable a website to remember information that changes the way the website behaves or looks, like your preferred language or the region that you are in. Functional cookies are currently unused.
Statistic cookies help website owners to understand how visitors interact with websites by collecting and reporting information anonymously. Statistical cookies are currently unused.
Marketing cookies are used to track visitors across websites. The intention is to display ads that are relevant and engaging for the individual user and thereby more valuable for publishers and third party advertisers. Marketing cookies are currently unused.