A New Day-Ahead Hourly Electricity Price Forecasting Framework

被引:0
|
作者
Ghofrani, M. [1 ]
Azimi, R. [2 ]
Najafabadi, F. M. [1 ]
Myers, N. [1 ]
机构
[1] Univ Washington Bothell, Elect Engn Sch, STEM, Bothell, WA 98011 USA
[2] Islamic Azad Univ, Qazvin Branch, Young Researchers & Elite Club, Qazvin, Iran
来源
2017 NORTH AMERICAN POWER SYMPOSIUM (NAPS) | 2017年
关键词
Bayesian learning; clustering; electricity price; forecasting; game theory; neural networks; persistence method; self-organizing map; NEURAL-NETWORK; ARIMA MODELS; MARKETS;
D O I
暂无
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
This paper develops a hybrid electricity price-forecasting framework to improve the accuracy of prediction. A novel clustering method is proposed that uses a modified game theoretic self-organizing map (GTSOM) and neural gas (NG) along with competitive Hebbian Learning (CHL) to provide a better vector quantization (VQ). To resolve the deficiency of the original SOM, five strategies are proposed to enable the non-winning neurons to participate in the learning phase. Using GTSOM, the price-load input data are clustered into proper number of subsets. A novel cluster-selection method is proposed to select the most appropriate subset whose time-series data is processed to provide the inputs for the neural networks. Finally, Bayesian method is used to train the networks and forecast the electricity price. Market price data from an independent system operator is used to evaluate the algorithm performance. Furthermore, a comparison of the proposed method against other state-of-the-art forecasting techniques shows a significant improvement in the accuracy of the price forecast.
引用
收藏
页数:6
相关论文
共 50 条
  • [1] Day-ahead electricity price forecasting by a new hybrid method
    Zhang, Jinliang
    Tan, Zhongfu
    Yang, Shuxia
    COMPUTERS & INDUSTRIAL ENGINEERING, 2012, 63 (03) : 695 - 701
  • [2] Forecasting Day-ahead Electricity Price Using a Hybrid Improved Approach
    Hu, Jian-Ming
    Wang, Jian-Zhou
    JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY, 2017, 12 (06) : 2166 - 2176
  • [3] Day-ahead electricity price analysis and forecasting by singular spectrum analysis
    Miranian, Arash
    Abdollahzade, Majid
    Hassani, Hossein
    IET GENERATION TRANSMISSION & DISTRIBUTION, 2013, 7 (04) : 337 - 346
  • [4] Forecasting day-ahead price spikes for the Ontario electricity market
    Sandhu, Harmanjot Singh
    Fang, Liping
    Guan, Ling
    ELECTRIC POWER SYSTEMS RESEARCH, 2016, 141 : 450 - 459
  • [5] Forecasting day-ahead electricity prices: Utilizing hourly prices
    Raviv, Eran
    Bouwman, Kees E.
    van Dijk, Dick
    ENERGY ECONOMICS, 2015, 50 : 227 - 239
  • [6] Electricity price forecasting for PJM day-ahead market
    Mandal, Paras
    Senjyu, Tomonobu
    Urasaki, Naomitsu
    Funabashi, Toshihisa
    Srivastava, Anurag K.
    2006 IEEE/PES POWER SYSTEMS CONFERENCE AND EXPOSITION. VOLS 1-5, 2006, : 1321 - +
  • [7] A Deep Learning Based Hybrid Framework for Day-Ahead Electricity Price Forecasting
    Zhang, Rongquan
    Li, Gangqiang
    Ma, Zhengwei
    IEEE ACCESS, 2020, 8 : 143423 - 143436
  • [8] DAY-AHEAD ELECTRICITY PRICE FORECASTING: LITHUANIAN CASE
    Bobinaite, Viktorija
    ELECTRICAL AND CONTROL TECHNOLOGIES, 2011, : 169 - 174
  • [9] Neural Network Approaches to Electricity Price Forecasting in Day-Ahead Markets
    Rosato, Antonello
    Altilio, Rosa
    Araneo, Rodolfo
    Panella, Massimo
    2018 IEEE INTERNATIONAL CONFERENCE ON ENVIRONMENT AND ELECTRICAL ENGINEERING AND 2018 IEEE INDUSTRIAL AND COMMERCIAL POWER SYSTEMS EUROPE (EEEIC / I&CPS EUROPE), 2018,
  • [10] Dense Skip Attention Based Deep Learning for Day-Ahead Electricity Price Forecasting
    Li, Yuanzheng
    Ding, Yizhou
    Liu, Yun
    Yang, Tao
    Wang, Ping
    Wang, Jingfei
    Yao, Wei
    IEEE TRANSACTIONS ON POWER SYSTEMS, 2023, 38 (05) : 4308 - 4327