A Two-Stage Stochastic Framework for an Electricity Retailer Considering Demand Response and Uncertainties Using a Hybrid Clustering Technique

Due to the highly volatile prices of pool market, a main source of an electricity retailer to meet its clients’ demand, retailers generally sign forward contracts in order to protect themselves from being exposed to the risk imposed by the uncertain pool prices. These contracts, however, decrease the retailer’s expected profit owing to their higher average prices compared with the pool market. In this paper, focusing on price-based demand response programs, a two-stage scenario-based stochastic framework is presented for the medium-term decision-making problem of an electricity retailer. This study would demonstrate that demand response programs can be an effective tool to hedge against the risk and an appropriate alternative yielding less involvement in costly forward agreements. The proposed model decides the optimal level of participation in the pool as well as forward market and determines the electricity rates offered to the clients. The objective is maximizing the expected value of the retailer’s profit, whereas the exposure risk is confined to a pre-specified level. Moreover, the scenarios required for the stochastic programming problem are generated using a hybrid clustering technique based on K-means and particle swarm optimization algorithms. The proposed model is mathematically described as a mixed-integer linear problem which is solvable through commercial software packages. The efficiency of the provided approach is evaluated via a realistic case study according to the available data from Spain electricity market.