A Profit Maximization Approach to Demand Response Management with Customers Behavior Learning in Smart Grid

• Published in: IEEE transactions on smart grid Vol. 7; no. 3; pp. 1516 - 1529
• Main Authors: Meng, Fan-Lin, Zeng, Xiao-Jun
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.05.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Customer behavior learning; Customers; day-ahead pricing; demand response (DR) management; Energy consumption; Fashion models; genetic algorithms (GAs); Home appliances; Learning; Load modeling; Management; Mathematical models; Optimization; Pricing; Profits; Smart grid; smart grids (SGs); Smart meters; Switches; genetic algorithms (GAs); day-ahead pricing; demand response (DR) management; Customer behavior learning; smart grids (SGs)
• ISSN: 1949-3053; 1949-3061
• DOI: 10.1109/TSG.2015.2462083

In this paper, we propose a profit-maximization-based pricing optimization model for the demand response (DR) management with customer behavior learning in the context of smart grids. By recognizing the different consumption patterns between shiftable and curtailable appliances, two different and distinguished behavior models are proposed. For shiftable appliances whose energy consumption can be shifted from high price periods to low price periods but total energy consumption is fixed, a probabilistic behavior model and its learning algorithm are proposed to model an individual customer's shifting probabilities dependent on different hourly prices. For curtailable appliances whose energy consumption cannot be shifted but total energy consumption can be adjusted, a regression model is proposed to model an individual customer's usage patterns dependent on prices and temperatures. After proposing the learning algorithms to identify these proposed behavior models, this paper further develops a genetic algorithm-based distributed pricing optimization algorithm for DR management with the aim to maximize the retailer's profit. Numerical results indicate the applicability and effectiveness of the proposed models and their benefits to the retailer by improving its profit.