Department of Telecommunications MASTER THESIS Nr. 608 MASTER THESIS Nr. 608 INTELLIGENT TRADING AGENT FOR POWER TRADING THROUGH WHOLESALE MARKET Ivo Buljević.

Slides:



Advertisements
Similar presentations
June Intelligently Connecting Plug-In Vehicles & the Grid.
Advertisements

Management and Control of Domestic Smart Grid Technology IEEE Transactions on Smart Grid, Sep Albert Molderink, Vincent Bakker Yong Zhou
17 th UPDEA CONGRESS IMPROVEMENT IN THE MANAGEMENT OF ELECTRICAL INFRASTRUCTURES FOR A BETTER PERFORMANCE OF AFRICAN POWER UTILITIES By Mr. Cheikh KA (SENELEC,
Strategies for Wind Power Trading in Sequential Short–Term Electricity Markets Franck Bourry and George Kariniotakis Center for Energy and Processes EWEC.
Document number Finding Financial Solutions & Models for Microgrids Maryland Clean Energy Summit Panel Wednesday, October 16, 2013.
GridWise ® Architecture Council Becky Harrison GridWise Alliance Future of the Grid Evolving to Meet America’s Needs.
Tom Standish Group President & COO Regulated Operations CenterPoint Energy Visions of the Smart Grid: Deconstructing the traditional utility to build the.
1 © 2012 Lockheed Martin Corporation, All Rights Reserved Intelligent Microgrid Solutions Efficient, Reliable and Secure Solutions for Today’s Energy Challenges.
PinPoint Pricing Looking for ways to maximize your net revenue through the charge master? PinPoint Pricing is the solution!
Department of Telecommunications Zagreb, July 2013 MASTER THESIS Nr. 605 VISUALIZATION MODULE FOR A SIMULATION PLATFORM FOR POWER TRADING Tomislav Briševac.
Inpassing PV Arnhem, November 19, 2014 Prof. Wil Kling
Susan Covino Senior Consultant, Emerging Markets March 31, 2015
SmartMeter Program Overview Jana Corey Director, Energy Information Network Pacific Gas & Electric Company.
Supply Chain Management
By Lauren Felton. The electric grid delivers electricity from points of generation to consumers, and the electricity delivery network functions via two.
Utility Regulation March 10, 2011 Raj Addepalli Deputy Director, Electric, Office of Electric,Gas and Water New York State Department of Public Service.
The Natural Number of Forward Markets for Electricity 9 th Annual POWER Conference on Electricity Industry Restructuring March 19, 2004 Hiroaki Suenaga.
Market Overview in Electric Power Systems Market Structure and Operation Introduction Market Overview Market Overview in Electric Power Systems Mohammad.
A Survey of Home Energy Management Systems in Future Smart Grid Communications By Muhammad Ishfaq Khan.
Smart Integrated Infrastructure The Progression of Smart Grid Presentation to National League of Cities Martin G. Travers – President, Telecommunications.
Oracle Demantra Overview & Utilization in a Demand Driven Supply Network Curtis Ardle February 22, 2008.
Demand Response in MISO Markets NASUCA Panel on DR November 12, 2012.
Smart Cities & Smart Utility
DOE’s Smart Grid R&D Needs Steve Bossart Energy Analyst U.S. Department of Energy National Energy Technology Laboratory Materials Challenges in Alternative.
Costs of Ancillary Services & Congestion Management Fedor Opadchiy Deputy Chairman of the Board.
Performance modeling of a hybrid Diesel generator-Battery hybrid system Central University of Technology Energy Postgraduate Conference 2013.
Copyright © 2011 Power Analytics Corp. The Evolution of the Microgrid A microgrid is an integrated energy system with: –Co-located power generation sources.
Efficiency and Demand Response NARUC Washington, DC February 14, 2006 Steve Specker President & CEO.
© 2009 IBM Corporation Smart Grid Research Consortium Customer Operations Transformation Global E&U Industry January 2011.
Smart Grid- An Introduction
Load Management Strategies to Support Grid Integration of Intermittent Renewable Resources Paulina Jaramillo and Lester Lave.
Department of Telecommunications MASTER THESIS Nr. 610 INTELLIGENT TRADING AGENT FOR POWER TRADING BASED ON THE REPAST TOOLKIT Ivana Pranjić.
Living Together in the Multi-cultural Society Proceedings of the 2010 EMUNI Research Souk 14 June 2010 A Sustainable Smart Grid Project for a Mediterranean.
Irwin/McGraw-Hill Copyright © 2001 by The McGraw-Hill Companies, Inc. All rights reserved. 1-1.
An Online Procurement Auction for Power Demand Response in Storage-Assisted Smart Grids Ruiting Zhou †, Zongpeng Li †, Chuan Wu ‡ † University of Calgary.
August Intelligently Connecting Plug-In Vehicles & the Grid.
Electric vehicle integration into transmission system
Consumer Empowerment Consumer Empowerment May 15, 2012 Presented by: Alparslan Bayraktar Commissioner Energy Market Regulatory Authority of Turkey (EPDK)
FCC Field Hearing on Energy and the Environment Monday November 30, 2009 MIT Stratton Student Center, Twenty Chimneys Peter Brandien, Vice President System.
Demand Response Workshop September 15, Definitions are important Demand response –“Changes in electricity usage by end-use customers from their.
Leader-Follower Framework For Control of Energy Services Ali Keyhani Professor of Electrical and Computer Engineering The Ohio State University
Brussels Workshop Use case 3 11/09/2015 Mario Sisinni.
PJM©2013www.pjm.com Economic DR participation in energy market ERCOT April 14, 2014 Pete Langbein.
Nord Pool Spot and Europe
A Study of Central Auction Based Wholesale Electricity Markets S. Ceppi and N. Gatti.
Artificial intelligence methods in the CO 2 permission market simulation Jarosław Stańczak *, Piotr Pałka **, Zbigniew Nahorski * * Systems Research Institute,
Energy Imbalance Market Presented at: The Governor’s Utah Energy Development Summit 2015 Caitlin Liotiris Energy Strategies Power Through Ideas.
Smart Grid Introduction
Outline The key findings What the SGA Summit did Smart City Amsterdam Some more detail on the disrupters – Ecosystem of the Grid – Distributed Generation.
BY: A. Mahmood, M. N. Ullah, S. Razzaq, N. Javaid, A. Basit, U. Mustafa, M. Naeem COMSATS Institute of Information Technology, Islamabad, Pakistan.
REAL TIME BALANCING OF SUPPLY AND DEMAND IN SMART GRID BY USING STORAGE, CONTROLLABLE LOADS AND SMART GENERATIONS Abdulfetah Shobole, Dr. Arif Karakaş.
We hear much about energy problems; supply shortages, pollution issues and high prices, but the solutions to these problems are here now in the form of.
Intelligent Supply Chain Management Strategic Supply Chain Management
Phoenix Convention Center Phoenix, Arizona Transactive Energy in Building Clusters [Innovation][Regional Innovation in Arizona] Teresa Wu Arizona State.
1 Seema Thakur (st107641) Advisor: Dr. Weerakorn Ongsakul Optimal Generation Scheduling of Cascaded Hydro-thermal and Wind Power Generation By Particle.
Intelligent Agent Based Auction by Economic Generation Scheduling for Microgrid Operation Wu Wen-Hao Oct 26th, 2013 Innovative Smart Grid Technologies.
SMART GRID A smart grid for intelligent energy use. By: Suhani Gupta.
Smart Grid Schneider Electric Javier Orellana
A Nordic vision for 2025 Nordic TSO Cooperation – more focused and effective.
Artificial Intelligence for Data Mining in the Context of Enterprise Systems Thesis Presentation by Real Carbonneau.
IEEE International Conference on Fuzzy Systems p.p , June 2011, Taipei, Taiwan Short-Term Load Forecasting Via Fuzzy Neural Network With Varied.
1 Master’s Thesis Project Presentation Author: Oleg Gulich Fortum supervisor: Ville Karttunen LUT professor:Jarmo Partanen Date: 29/04/2010 TECHNOLOGICAL.
THE NEW GENERATION TRANSMISSION By Ashroo M. Das 6 th sem, EEE & Deepak Kumar 6 th sem, EEE.
Author : Peng Han, Jinkuan Wang, Yinghua Han, and Qiang Zhao Source : 2012 IEEE International Conference on Information Science and Technology Wuhan, Hubei,
PGDM/ / II Trimester/E-Business. What is supply chain management?  Supply chain management is the co- ordination of entities, activities, information.
EE5900 Cyber-Physical Systems Smart Home CPS
“Internet of Things” – The new age drivers of Power Distribution Automation Speaker: Jayant Sinha Date of session: 2 Oct, 2015.
System Control based Renewable Energy Resources in Smart Grid Consumer
Optimal Electricity Supply Bidding by Markov Decision Process
Presentation transcript:

Department of Telecommunications MASTER THESIS Nr. 608 MASTER THESIS Nr. 608 INTELLIGENT TRADING AGENT FOR POWER TRADING THROUGH WHOLESALE MARKET Ivo Buljević 2012/2013 Zagreb, July 2013

Department of TelecommunicationsContents  Introduction  Smart grid  Wholesale market  CrocodileAgent 2013  Conclusion Zagreb, July of 12

Department of TelecommunicationsIntroduction  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 Zagreb, July of 12

Department of Telecommunications Smart grid  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 Zagreb, July of 12  Multi-agent market models  Entities are represented by intelligent software agents  Opportunity to test software solutions in order to prevent market crashes (California 2001)

Department of Telecommunications Wholesale market  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 Zagreb, July of 12

Department of Telecommunications Wholesale market (2)  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 Zagreb, July of 12

Department of Telecommunications CrocodileAgent 2013  Intelligent software agent developed at University of Zagreb  Participant of PowerTAC 2013  Main emphasis: Zagreb, July of 12  Development of wholesale bidding strategy which will minimize negative effects on the balancing market  Responsive and context- aware agent design

Department of Telecommunications CrocodileAgent 2013 Modular architecture Zagreb, July of 12 Contribution of this master thesis

Department of Telecommunications CrocodileAgent 2013 Learning module  Based on reinforcement learning  Erev-Roth method specially adapted for PowerTAC wholesale market  Enables broker to adapt to various market conditions  Key features: Zagreb, July of 12  Multiple strategies  Advanced strategy evaluation based on its efficiency RL module Simulator InitializationChoose strategy ExecuteResults Set rewards

Department of Telecommunications CrocodileAgent 2013 Learning module (2)  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: Zagreb, July of 12  Initialization  Choose strategy  Place order  Set reward  Strategies used to model amount of energy and unit price

Department of Telecommunications CrocodileAgent 2013 Results  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 Zagreb, July of 12  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)

Department of TelecommunicationsConclusion  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 Zagreb, July of 12