Profit maximization for an electricity retailer using a novel customers’ behavior leaning in a smart grid environment

Abstract

With the establishment of the smart grids platform, demand response (DR) programs have improved the operation and reliability of the power grid by increasing the participation of customers. This article investigates the issue of bidding strategy for an electricity retailer, which interacts with a set of residential customers. In this environment, the price-responsive customers react to the announced prices optionally. Thus, the retailer requires to learn the behavior of its customers. The proposed model enlisting the analytic hierarchy process (AHP) and a strength deep learning (DL) algorithm represents a pioneer study of applying a data-driven method into the bidding strategy problem. Herein, the energy usage patterns of customers in response to the dynamic pricing are firstly extracted, and a profit maximization problem of the retailer for the DR management is then developed with the consideration of the market constraints. The numerical results show the good performance of the proposed approach for improving the profitability of the retailer.