Bidding in Non-Stationary Energy Markets
نویسندگان
چکیده
The PowerTAC competition has gained attention for being a realistic and powerful simulation platform used for research on retail energy markets, in part because of the growing number of energy markets worldwide. Agents in this complex environment typically use multiple strategies, changing from one to another, posing a problem for current learning algorithms. This paper introduces DriftER, an algorithm that learns an opponent model and tracks its error rate. We compare our algorithm in the PowerTAC simulator against the champion of the 2013 competition and a state of the art algorithm tailored for interacting against switching (nonstationary) opponents. The results show that DriftER outperforms the competition in terms of profit and accuracy.
منابع مشابه
Optimal Bidding Strategies of GENCOs in Day-Ahead Energy and Spinning Reserve Markets Based on Hybrid GA-Heuristic Optimization Algorithm
In an electricity market, every generation company (GENCO) attempts to maximize profit according to other participants bidding behaviors and power systems operating conditions. The goal of this study is to examine the optimal bidding strategy problem for GENCOs in energy and spinning reserve markets based on a hybrid GA-heuristic optimization algorithm. The heuristic optimization algorithm used...
متن کاملPrice-takers’ bidding strategies in joint energy and spinning reserve pay-as-bid markets
Strategic bidding in joint energy and spinning reserve markets is a challenging task from the viewpoint of generation companies (GenCos). In this paper, the interaction between energy and spinning reserve markets is modeled considering a joint probability density function for the prices of these markets. Considering pay-as-bid pricing mechanism, the bidding problem is formulated and solved as a...
متن کاملOpponent Modeling against Non-stationary Strategies: (Doctoral Consortium)
Most state of the art learning algorithms do not fare well with agents (computer or humans) that change their behaviour in time. This is the case because they usually do not model the other agents’ behaviour and instead make some assumptions that for real scenarios are too restrictive. Furthermore, considering that many applications demand different types of agents to work together this should ...
متن کاملA Comprehensive Survey on GenCos’ Optimal Bidding Strategy Problem in Competitive Power Markets
This paper represents a complete survey on Generation Companies’ (GenCos’) optimal bidding strategy problem in restructured power markets. In this regard after an introduction to competitive electricity markets, concept of optimal bidding strategy is presented. Considering large amount of works accomplished in this area a novel classification is implemented in order to categorize the existing d...
متن کاملProbabilistic GENCOs Bidding Strategy in Restructured Two-Side Auction Power Markets
As a matter of course, power market uncertainties escalation is by product of power industry restructure on one hand and the unrivalled penetration of renewable energies on the other. Generally, the decision making process in such an uncertain environment faces with different risks. In addition, the performance of real power markets is very close to oligopoly markets, in which, some market play...
متن کامل