A Stochastic-Based Decision-Making Framework for an Electricity Retailer: Time-of-Use Pricing and Electricity Portfolio Optimization

TLDR

The study proposes a stochastic programming framework for an electricity retailer to set time‑of‑use prices and manage a contract portfolio, aiming to maximize profit while minimizing multi‑period risk. The framework models supply from the pool, self‑generation, and forward, option, and interruptible contracts, uses CVaR for risk, incorporates a market‑share function for customer and competitor responses, and solves the resulting mixed‑integer stochastic program via decomposition and branch‑and‑bound.

Abstract

This paper proposes a decision-making framework, based on stochastic programming, for a retailer: 1) to determine the sale price of electricity to the customers based on time-of-use (TOU) rates, and 2) to manage a portfolio of different contracts in order to procure its demand and to hedge against risks, within a medium-term period. Supply sources include the pool, self-production facilities and several instruments such as forward contracts, call options, and interruptible contracts. The objective is to maximize the profit and simultaneously to minimize the risks in terms of a multi-period risk measure. Moreover, the risks are measured using conditional value at risk (CVaR) methodology. The reaction of the customers to the retailers' selling prices as well as the competition between the retailers is modeled through a market share function. The problem is formulated as a mixed-integer stochastic programming. It is solved by a decomposition technique, and the decomposed parts are solved by a branch-and-bound algorithm.