Predictive energy management strategy in PV/ESS/DIESEL system for battery degradation reduction using artificial neural network.

• Main Authors: M. Saud, Muhammad Noor, Md. Rasid, Madihah, Md. Sapari, Noorazliani, Syed Nasir, Syed Norazizul
• Format: Conference or Workshop Item
• Published: 2023
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utm.my/107921/; http://dx.doi.org/10.1109/ISWTA58588.2023.10249913

Renewable Energy Sources (RES) power generation has increasingly evolved as RES power technology and becoming a valuable substitute for traditional power generation. Energy storage system (ESS), with its flexible charging and discharging features, is most typically utilized to collaborate with RES power generation to efficiently stabilize the process of connecting to the grid and improve power controllability due to variable RES power output. However, the high charging and discharging rate of ESS can lead ESS to degrade faster and shorten the lifetime than it should. Therefore, predictive EMS is introduced in this study. The predicted capacity fading of the ESS is utilized in the EMS to optimize the schedule of ESS operation. The ANN algorithm is implemented to forecast the data. The result shows that the degradation and degradation cost achieved 0.01% and 18.39% reduction with the proposed method.