Data-driven dynamic energy pricing

Demand side management has attracted a lot of attention as a method to regulate customer behavior and improve system reliability. In this paper, we solve the day-ahead energy pricing problem in the distribution electricity system by taking into account the fact that customers can change their consumption behavior in response to price changes. We propose two pricing models under two different scenarios. In the first scenario, customers' consumption profiles at different prices are available data. We propose an integer programming model to maximize the revenue of the utility company. In the second scenario, we assume only the consumption profiles at the current price, which is static, are available. A game theoretic bilevel optimization model is built to describe the relationship between electricity price and customers' behavior. We then compare and analyze the results of the two models.