Our objective is to implement certain automated data analysis procedures capable of running analysis for all the PV plants under management. This is done to further develop machine-learning-based decision-making and automated processes, which help us to constantly improve our services for our clients.
“No doubt, that AI will become a key component going forward, as it offers exceptional solutions for the main challenges when operating and maintaining solar assets. We are seeing in our day to day application of AI a high accuracy of the data analysis as well as efficiency in deploying the AI applications.” says Sebastian Nieding, Head of Technical Operations of ENcome Group.
One of ENcome’s approaches in using AI, is focussing on orientation detection: Orientation detection categorizes strings and inverters in a variety of clusters. Thus, alarm handling and monitoring processes are becoming more precise and case-sensitive. This can bridge the gap between actual monitoring data and the lack of accurate as-built documents. Overall, the results of the analysis show high accuracy, of course depending on the number of existing orientations and the quality of data.
Another machine-learning approach refers to partial shading detection. Taking advantage of clustering methods, ENcome can detect partially shaded strings with high accuracy. As our claim slogan says EVERY WATT COUNTS, any shaded string can reduce production efficiency. Therefore, ENcome is firmly committed to find and offer solutions to further increase the output of our client’s solar assets.
The ENcome Group is a leading independent service provider for the technical operation of photovoltaic power plants and the offering of respective engineering and advisory services. In managing and planning the power plants entrusted, the service of the ENcome Group focuses on maximizing short-term availability, production performance as well as long-term value.