Demand forecasting based on ann integrating solar distributed generation

The most important requirement of any energy utility is the accurate prediction of their energy demand. They can use the predicted data to manage their load despatch. Even now many of the energy utilities are using semi human based load prediction techniques for their operation. But these techniques are prone to high errors and are getting obsolete. A number of load prediction models have been developed over the decades using various techniques. It extends from mathematical models to data mining. Such model use regression methods, SVMs, ANNs etc for load forecasting. Till few years the power generation was concentrated in generating stations and its stationary nature made the prediction easy. With the introduction of renewable energy sources, distributed generation has grown into a significant portion as compared to fixed generation. In the present situation the solar distributed generation has become a considerable amount and its uncertainty in production poses a serious challenge to load prediction. This study aims at exploring a suitable model for load prediction integrating distributed generation.