Generation Expansion Equilibria with Predictive Dispatch Model

TL;DR

This paper introduces a predictive modeling approach to efficiently solve generation expansion equilibrium problems in electricity markets, capturing market dynamics with reduced computational effort.

Contribution

It presents a novel methodology combining predictive models with bi-level optimization and diagonalization algorithms for strategic generation investment decisions.

Findings

Achieves significant computational efficiency improvements.

Accurately captures market characteristics and dynamics.

Enables strategic investment analysis in electricity markets.

Abstract

This paper proposes a methodology to solve generation expansion equilibrium problems by using a predictive model to represent the equilibrium in a simplified network constrained electricity market. The investment problem for each generation company (Genco) is a bi-level problem with the investment decision made in the upper level and market clearing condition in the lower level, which traditionally is represented as a Mathematical Program with Equilibrium Constraint (MPEC). The predictive model is trained for estimating the system-wide revenues for each technology type across energy, ancillary services and capacity markets given the amount of technology-specific installed capacity on the grid. The profit maximization investment problem for each Genco is solved using a global search algorithm, which uses the predictive model to evaluate the objective function. To solve for the strategic equilibrium, each Genco's problem is plugged into a diagonalization algorithm that is generally used in multi-leader, single-follower bi-level problems. The methodology presented here enables significant computational improvements while still capturing the desired market characteristics and dynamics of traditional equilibrium modeling approaches