Jian Xu
ABSTRACT
Electricity is the "blood" of society. Electricity is a special commodity that is not storable, so its production and load should always be balanced to maintain a tightly regulated system frequency. Electricity production and load both depend on many factors, such as the weather, temperature, and wind. These characteristics make the dynamics of electricity price very different from that of any other commodities or financial assets. The electricity price can exhibit hourly, daily, and seasonal fluctuations, as well as abrupt unanticipated spikes. Now almost all electricity market participants use wind/load/price forecasting tools in their daily operations to optimize their operation plans, and bidding and hedging strategies, in order to maximize the profits and avoid price risks. However, the unreliable and inaccurate predictions with current forecasting tools have caused many serious problems, which can cause system instabilities and result in extreme prices even in the absence of scarcity. This paper presents an implementation of state of the art machine learning approaches into the forecasting tools for the ERCOT Day-Ahead market to improve the reliability and accuracy of electricity price prediction.
- Dogan Keles, Jonathan Scelle, Florentina Paraschiv, and Wolf Fichtner. Extended Forecast Methods for Day-Ahead Electricity Spot Prices applying Artificial Neural Networks. Applied Energy, 162:218--230, 2016.Google Scholar
Cross Ref
- Hamidreza Zareipour, Claudio A. Canizares, and Kankar Bhattacharya. Economic Impact of Electricity Market Price Forecasting Errors: A Demand-Side Analysis. IEEE Transactions on Power Systems, 25:254--262, 2007.Google ScholarCross Ref
- Tao Hong. Crystal Ball Lessons in Predictive Analytics. EnergyBiz, pages 35--37, 2015.Google Scholar
- Hao Chen, Keli Xiao, Jinwen Sun, and Song Wu. A Double-Layer Neural Network Framework for Highfrequency Forecasting. ACM Trans. Manage. Inf. Syst, 7(4), January 2017. Google ScholarDigital Library
- Vinayak Sharma, Umit Cali, Veit Hagenmeyer, Ralf Mikut, and Jorge Angel González Ordiano. Numerical Weather Prediction Data Free Solar Power Forecasting with Neural Networks. In e-Energy '18 Proceedings of the Ninth International Conference on Future Energy Systems, pages 604--609, New York, NY, USA, 2018. ACM. Google ScholarDigital Library
- Binbin Yong, Zijian Xu, Jun Shen, Huaming Chen, Yanshan Tian, and Qingguo Zhou. Neural Network Model with Monte Carlo Algorithm for Electricity Demand Forecasting in Queensland. In ACSW '17 Proceedings of the Australasian Computer Science Week Multiconference, 2017. Google ScholarDigital Library
- Mohammadsaleh Zakerinia and Seyed Farid Ghaderi. Short Term Wind Power Forecasting using Time Series Neural Networks. In EAIA '11 Proceedings of the 2011 Emerging M&S Applications in Industry and Academia Symposium, pages 17--22, 2011.Google ScholarDigital Library
- Tiago A. E. Ferreira, Germano C. Vasconcelos, and Paulo J. L. Adeodato. A New Evolutionary Method for Time Series Forecasting. In GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation, pages 2221--2222, 2005. Google ScholarDigital Library
- Cielito C. Olegario, Andrei D. Coronel, Ruji P. Medina, and Bobby D. Gerardo. A Hybrid Approach towards Improved Artificial Neural Network Training for Short-Term Load Forecasting. In DSIT '18 Proceedings of the 2018 International Conference on Data Science and Information Technology, pages 53--58, 2018. Google ScholarDigital Library
- Apostolos N. Adamakos and Michalis K. Titsias. Short-Term Load Forecasting using a Cluster of Neural Networks for the Greek Energy Market. In SETN '16 Proceedings of the 9th Hellenic Conference on Artificial Intelligence, page 15, 2016.Google Scholar
- Rafałt Weron. Electricity Price Forecasting: A Review of the State-of-the-art with a Look into the Future. International Journal of Forecasting, 30(4):1030--1081, 2014.Google ScholarCross Ref
- J.P.S. Catalão, S.J.P.S. Mariano, V.M.F. Mendes, and L.A.F.M. Ferreira. Short-term Electricity Prices Forecasting in a Competitive Market: A Neural Network Approach. Electric Power Systems Research, 77(10):1297--1304, 2014.Google ScholarCross Ref
- Jun Zhang and Chuntian Cheng. Short-Term Load Forecasting using a Cluster of Neural Networks for the Greek Energy Market. In Day-ahead electricity price forecasting using artificial intelligence, 2008.Google Scholar
- Nima Amjady. Day-Ahead Price Forecasting of Electricity Markets by a New Fuzzy Neural Network. IEEE Transactions on Power Systems, 21(2):887--896, 2006.Google ScholarCross Ref
- N. M. Pindoriya, S. N. Singh, and S. K. Singh. An Adaptive Wavelet Neural Network-Based Energy Price Forecasting in Electricity Markets. IEEE Transactions on Power Systems, 23(3):1423--1432, 2008.Google ScholarCross Ref
- H.Z. Wang, G.B. Wang, G.Q.Li, J.C.Peng, and Y.T. Liu. Deep Belief Network based Deterministic and Probabilistic Wind Speed Forecasting Approach. Applied Energy, 182(15):80--93, 2016.Google ScholarCross Ref
- Igor M. Coelho, Vitor N. Coelho, Eduardo J. da S. Luz, Luiz S. Ochi, Frederico G. Guimarães, and Eyder Rios. A GPU Deep Learning Meta-heuristic based Model for Time Series Forecasting. Applied Energy, 201(1):412--418, 2017.Google ScholarCross Ref
- Alex Graves. Generating Sequences with Recurrent Neural Networks. arXiv preprint arXiv, 1308(0850), 2014.Google Scholar
- Shubham Khandelwal, Benjamin Lecouteux, and Laurent Besacier. Comparing GRU and LSTM for Automatic Speech Recognition. Research Report, 2016.Google Scholar
- Umut Ugurlu, Ilkay Oksuz, and Oktay Tas. Electricity Price Forecasting Using Recurrent Neural. Energies, 11(5):1255, 2018.Google Scholar
Index Terms
- Day-Ahead Price Forecasting in ERCOT Market Using Neural Network Approaches
Recommendations
Computation of Time Series Scaling Exponent for Electricity Prices Forecasting
CompSysTech '19: Proceedings of the 20th International Conference on Computer Systems and TechnologiesElectricity is a product traded on the organized markets and has become a commodity having dynamic trade characteristics not typical to other market products. The dynamic of the trade parameters is due to the fact that this product is non-storable, need ...
A soft computing system for day-ahead electricity price forecasting
Hourly energy prices in a competitive electricity market are volatile. Forecast of energy price is key information to help producers and purchasers involved in electricity market to prepare their corresponding bidding strategies so as to maximize their ...
Forecasting next-day price of electricity in the Spanish energy market using artificial neural networks
In this paper, next-day hourly forecasts are calculated for the energy price in the electricity production market of Spain. The methodology used to achieve these forecasts is based on artificial neural networks, which have been used successfully in ...
Comments