Modeling and Optimal Pricing of Time-Based Demand Response Programs in Competitive Retail Market

The current study makes a model of interaction between the retailer and customer using demand response programs in order to maximize the retailer’s benefit and gain customer’s satisfaction through investigation of customer’s reaction. Additionally, using two pricing models including Time of Use (TOU) and Real Time Pricing (RTP), it is suggested to retail companies to maximize their benefit which results from participation in energy market and selling energy to the final customer with optimal use and implementation of energy pricing plans for its customers. To do this, optimal prices of TOU and RTP obtained from solving an optimization problem by means of Q-Learning algorithm. Moreover, the effect of implementing these pricing programs on the benefit of retail company will be analyzed. Finally, the results will be compared and discussed.

کلیدواژه ها:

q-learning algorithm (QL) ، demand response program ، time of use pricing (TOU) ، real time pricing (RTP)