Application of a Customers’ Behavior Learning Machine for Profit Maximization of a Retail Electric Provider in Smart Grid

Autor: S. R. Goldani, Mohammad R. Aghaebrahtmi, Hossein Taherian
Rok vydání: 2019
Předmět:
Zdroj: 2019 IEEE 13th International Conference on Compatibility, Power Electronics and Power Engineering (CPE-POWERENG).
DOI: 10.1109/cpe.2019.8862346
Popis: A retail electric provider (REP) acts as an intermediary between energy producers companies and end-users at electricity markets. The main goal of a REP is to maximize its profit. To this end, it is necessary to adopt an optimal bidding strategy by considering reaction patterns of customers to the announced prices. In this paper, a realistic and meaningful scenario in the smart grids environment is considered where a REP serves customers without smart meters. At the upper-level, REP firstly announces its electricity prices of the next 24 hours, and at the lower-level, customers behave based on their preferences accordingly. In this paper, a hybrid framework consisting of customers’ behavior learning machine (CBLM) and profit optimization program is proposed. By extracting reaction patterns of customers based on historical data, the proposed model forecasts their electricity usage behaviors and then REP optimizes its prices. The simulation results show that the optimized prices determined based on the customers’ behavior not only benefit the customers but also increase the retailer’s profits.
Databáze: OpenAIRE
načítá se...