Sufficient A Priori Conditions for the Linear Relaxation of the Energy Storage Scheduling Problem

TL;DR

This paper introduces new a priori conditions that ensure the linear relaxation of energy storage scheduling models avoids simultaneous charge and discharge, expanding applicability to various system characteristics.

Contribution

It establishes mathematically validated conditions based on storage system properties that guarantee optimal solutions without complex constraints, and proposes a simplified mixed-integer linear model.

Findings

Conditions valid for negative prices and inefficiencies

Mathematically proven conditions for relaxation validity

Reduced binary variables in the mixed-integer model

Abstract

When modeling energy storage systems, an essential question is how to account for the physical infeasibility of simultaneous charge and discharge. The use of complementarity constraints or of binary variables is common, but these formulations do not scale well. Alternatively, assumptions such as perfect efficiencies or positive prices are often used to justify the choice of a linear model. In this paper, we establish new a priori conditions that guarantee the existence of an optimal solution without simultaneous charge and discharge when solving the linear relaxation of the storage scheduling problem. They are based on the characteristics of the storage system, in particular, the duration of charge. They can be valid for negative prices and with inefficiencies, thereby enlarging the set of conditions for which the complementarity constraints can be relaxed. We prove mathematically the validity of these conditions and illustrate them with practical examples. We also introduce a refined mixed-integer linear equivalent, in which the number of binary variables can be drastically reduced.