Effective load scheduling of residential consumers based on dynamic pricing with price prediction capabilities

Demand response (DR) sustains an influential role in today's smart grid. DR program is an initiative to enhance the performance of electricity price market and the stability of the power system. Price based DR programs have a significant part in the residential customer activities. In the present scenario, the flat tariffs are replaced by real-time pricing (RTP) models due to their economic benefits and the environment supportive behave. The RTP models are capable of providing a chance to customers to reduce their electricity bills. The customers can communicate their demand information to the utility and get back the prices via smart metering technologies. In this paper, an automatic load control approach with dynamic pricing models is implemented for residential consumers. In real time pricing environment, it is necessary to have price prediction capabilities. Here, the linear prediction model (LPM) and artificial neural network are implemented for predicting the prices. For optimization purpose mixed binary linear programming (MBLP) computations are used. To validate the performance of system simulation results has shown the better performance with the different scenario.