Load Forecasting Based Dynamic Pricing Model for Power Sharing in Solar Home Systems

A dynamic pricing-based peer to peer electricity sharing among solar homes in an off-grid rural area is presented here. The price is based on the forecasted supply and demand gap. Recurrent neural networks have been used for forecasting. All the solar homes are categorized into different clusters and are connected to a DC grid for power sharing. A producer and consumer, defined as prosumer, can invest in a relatively larger solar home system and sell energy to the consumers who cannot afford the initial high investment. The prosumer can also run an energy storage system from which he can earn money by supplying energy at the peak hour. The analysis shows that the system is able to run smoothly both on sunny and overcast rainy days. The proposed model may create a marketplace to effectively trade energy at an affordable price in microgrids which is beneficial to both prosumers and consumers.