Intelligent Trading Agent for Power Trading in Wholesale Market
Department of Telecommunications' master thesis explores the development of the CrocodileAgent, an intelligent software agent designed to minimize negative impacts on power market balancing. The thesis delves into the evolution of the energy market, the concept of smart grids, and the significance of wholesale markets in enabling energy trade. It highlights the role of multi-agent models and advanced forecasting techniques in optimizing energy trading strategies, with a focus on the CrocodileAgent's participation in the PowerTAC competition.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
Department of Telecommunications MASTER THESIS Nr. 608 INTELLIGENT TRADING AGENT FOR POWER TRADING THROUGH WHOLESALE MARKET Ivo Buljevi 2012/2013 Zagreb, July 2013
Contents Department of Telecommunications Introduction Smart grid Wholesale market CrocodileAgent 2013 Conclusion 2 of 12 Zagreb, July 2013
Introduction Department of Telecommunications Characteristics of the traditional energy market: Centralized Vertically integrated market structure No competition Liberalization and deregulation of the traditional energy market Increased number of renewable energy sources Progressive transformation of traditional power systems into evolved systems called smart grids 3 of 12 Zagreb, July 2013
Smart grid Department of Telecommunications A modernization concept of the electricity delivery system Enables real-time banacing of energy supply and demand A two-way flow of electricity and information Multi-agent market models Entities are represented by intelligent software agents Opportunity to test software solutions in order to prevent market crashes (California 2001) 4 of 12 Zagreb, July 2013
Wholesale market Department of Telecommunications Result of liberalization and deregulation of the traditional energy market, enables energy trade between market entities Power exchanges and power pools Day-ahead market Examples of wholesale markets: Chile Great Britain and Wales Nord Pool California 5 of 12 Zagreb, July 2013
Wholesale market (2) Department of Telecommunications Energy load forecasting Statistical approach Similar-day method Exponential smoothing Regression methods Artifficial intelligence based tecniques Reinforcement learning Energy price forecasting Spike preprocessing Time series models with exogenous variables Interval forecasts 6 of 12 Zagreb, July 2013
CrocodileAgent 2013 Department of Telecommunications Intelligent software agent developed at University of Zagreb Participant of PowerTAC 2013 Main emphasis: Development of wholesale bidding strategy which will minimize negative effects on the balancing market Responsive and context- aware agent design 7 of 12 Zagreb, July 2013
CrocodileAgent 2013 Modular architecture Department of Telecommunications CrocodileAgent 2013 BIDDING STRATEGIES LEARNING MODULE FUTURE ENERGY USAGE/PRICES GENERATED ORDERS CLEARING INFORMATION ENERGY PRICES MARKET REPOSITORY TARIFF REPOSITORY PAST USAGE FORECAST MANAGER Contribution of this master thesis NEEDED ENERGY MARKET MANAGER TARIFF MANAGER OTHER TARIFF SPECIFICATION, TRANSACTION PUBLISH TARIFFS BIDS/ASKS ALL FORECASTED DATA CURRENT WHOLESALE STATE MAIN SERVICE (MESSAGE SENDER/ RECEIVER) CUSTOMER MARKET WHOLESALE MARKET PAST CLEARING PRICES PAST ENERGY USAGE SEND TO SERVER OTHER BROKERS BID/ASK TARIFFS GENCOS Frosty storage Heat Pump Office complex Village types Centerville homes Solar C2 C3 C1 Wind PRODUCTION CONSUMPTION INTERUPTABLE CONSUMPTION WEATHER 8 of 12 Zagreb, July 2013
CrocodileAgent 2013 Learning module Department of Telecommunications Based on reinforcement learning Erev-Roth method specially adapted for PowerTAC wholesale market Enables broker to adapt to various market conditions Key features: Multiple strategies Advanced strategy evaluation based on its efficiency Initialization Choose strategy Set rewards RL module Simulator Execute Results 9 of 12 Zagreb, July 2013
CrocodileAgent 2013 Learning module (2) Department of Telecommunications Uses basic order as an input Generated by forecast module, based on past usage of subscribers on the retail market Holt-Winters method Life cycle: Initialization Choose strategy Place order Set reward Strategies used to model amount of energy and unit price 10 of 12 Zagreb, July 2013
CrocodileAgent 2013 Results Department of Telecommunications Broker progressively learns to adapt to current market conditions manifestation of the learning period Minimization of balancing cost Broker buys an excessive amount of energy on the wholesale market Results from May trial indicates that broker buys 125% of energy needed on the retail market A need to optimize basic order generation (energy load forecasting) 11 of 12 Zagreb, July 2013
Conclusion Department of Telecommunications Robustness of the CrocodileAgent s wholesale module Broker is able to adapt to changes in competition environment Adapted Erev-Roth algorithm was proved to be suitable for the PowerTAC wholesale market Future work: Improvement of energy load forecasting Improvement in unit price calculation Design of intelligent strategies 12 of 12 Zagreb, July 2013
