A Reinforcement Learning Algorithm for Agent-Based Modeling of Investment in Electricity Markets
نویسندگان
چکیده
We develop a reinforcement-learning algorithm to model investment in electricity markets, by extending the n-armed bandit algorithm, and prove its equilibrium properties. We show that there is a stationary state of the investment game in which no additional investment or retirement of plants takes place. We model a spot electricity market together with investment decisions. Our experiments suggest that in the long-run electricity markets will tend to be short of capacity, we further analyze the evolution of the technological mix of the market.
منابع مشابه
Development of Reinforcement Learning Algorithm to Study the Capacity Withholding in Electricity Energy Markets
This paper addresses the possibility of capacity withholding by energy producers, who seek to increase the market price and their own profits. The energy market is simulated as an iterative game, where each state game corresponds to an hourly energy auction with uniform pricing mechanism. The producers are modeled as agents that interact with their environment through reinforcement learning (RL...
متن کاملProgram on Technology Innovation: Using Q-Learning for Adaptive Agents in a Simulated Electricity Market Model
This is an EPRI Technical Update report. A Technical Update report is intended as an informal report of continuing research, a meeting, or a topical study. It is not a final EPRI technical report. Agents that can develop policies through trial-and-error interaction with their environments are especially interesting for use in agent-based modeling of economic processes such as spot markets. Well...
متن کاملMarket Design Using Agent-Based Models
This chapter explores the state of the emerging practice of designing markets by the use of agent-based modeling, with special reference to electricity markets and computerized (on-line) markets, perhaps including real-life electronic agents as well as human traders. The paper first reviews the use of evolutionary and agent-based techniques of analyzing market behaviors and market mechanisms, a...
متن کاملUtilizing Generalized Learning Automata for Finding Optimal Policies in MMDPs
Multi agent Markov decision processes (MMDPs), as the generalization of Markov decision processes to the multi agent case, have long been used for modeling multi agent system and are used as a suitable framework for Multi agent Reinforcement Learning. In this paper, a generalized learning automata based algorithm for finding optimal policies in MMDP is proposed. In the proposed algorithm, MMDP ...
متن کاملA Multiagent Reinforcement Learning algorithm to solve the Community Detection Problem
Community detection is a challenging optimization problem that consists of searching for communities that belong to a network under the assumption that the nodes of the same community share properties that enable the detection of new characteristics or functional relationships in the network. Although there are many algorithms developed for community detection, most of them are unsuitable when ...
متن کامل