基于可信度加权组合的电价波动模式日前预报方法

doi:10.3969/j.issn.1000-7229.2018.07.003

电力建设 ›› 2018, Vol. 39 ›› Issue (7): 24-31.doi: 10.3969/j.issn.1000-7229.2018.07.003

• 电力市场关键问题研究栏目主持陈启鑫副教授 • 上一篇下一篇

基于可信度加权组合的电价波动模式日前预报方法

姜利辉, 周立栋，任建国，柯鹏，田林静，王飞

1. 华润电力控股有限公司，广东省深圳市 518001；2.国网山东省电力公司潍坊供电公司，山东省潍坊市 261000；3. 华北石油管理局水电厂，河北省任丘市 062552；4. 新能源电力系统国家重点实验室（华北电力大学），河北省保定市 071003；5. 华北电力大学电力工程系，河北省保定市 071003

出版日期:2018-07-01
作者简介:姜利辉（1962），男，硕士，高级工程师，主要从事电力及新能源建设、发电运营、电力市场等方面工作；周立栋（1992），男，硕士，主要从事智能电网、预测模型与算法、微网优化等方面的研究工作；任建国（1971），男，硕士，高级工程师，主要从事火电及新能源发电、综合能源系统、电力市场等方面的规划设计与技术开发工作；柯鹏（1982），男，本科，高级工程师，主要从事华北油田电力建设的规划设计与生产运行工作；田林静（1977），男，硕士，工程师，主要从事华北油田电力建设的规划设计与生产运行工作；王飞（1973），男，博士（后），教授，主要从事需求响应与综合能源、新能源发电功率预测、电价与负荷预测等方面的研究工作。
基金资助:
国家自然科学基金项目（51577067）；新能源电力系统国家重点实验室开放基金（LAPS18008）；国家电网公司科技项目（NY7116021）

Day-ahead Prediction Approach of Electricity Price Fluctuation Pattern based on Credibility Weighted Combination

JIANG Lihui, ZHOU Lidong, REN Jianguo, KE Peng, TIAN Linjing, WANG Fei

1. China Resources Power Holdings Company Limited, Shenzhen 518001, Guangdong Province, China；2.Weifang Power Company of State Grid Shandong Electric Power Company, Weifang 261000, Shandong Province, China；3. The Hydropower Plant of Huabei Oilfield Company, Renqiu 062552, Hebei Province,China；4. State Key Laboratory of Alternate Electrical Power System with Renewable Energy Source（North China Electric Power University）, Baoding 071003, Hebei Province,China；5. The Department of Electrical Engineering, North China Electric Power University, Baoding 071003, Hebei Province,China

Online:2018-07-01
Supported by:
This work is supported by National Natural Science Foundation of China （No. 51577067）,State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources（No. LAPS18008）,and State Grid Corporation of China Research Program（No.NY7116021）.

摘要/Abstract

摘要： 准确的日前电价预测对电力市场参与者的优化决策具有重要意义。目前，大多数日前电价预测方法并不区分每天电价的波动模式而采用统一模型进行预测，当被预测日的波动模式与历史数据出现较大差异时无法保证预测的准确性。根据不同的日波动模式采用相似历史数据进行分类建模是解决此问题的有效途径，这就需要建立针对历史数据不同波动模式的分类识别模型和针对未来波动模式的日前预报模型。为此，文章提出一种针对分类预测的电价日波动模式日前加权组合预报方法。第一，采用K-means算法对日电价序列进行聚类分析，在分析聚类结果特性的基础上提取反映每日波动模式差异的特征向量，利用支持向量机分类（support vector machine for classification, SVC）方法建立电价数据日波动模式的识别模型；第二，利用多种常规方法建立日前电价预测模型对日前电价进行预测，并将预测结果输入日波动模式识别模型得到对应的模式识别结果；第三，根据多个方法波动模式预测结果对历史数据表现出来的不同精度，设计了基于可信度的组合机制，实现考虑预测准确性的加权组合预测，从而得到最终的日波动模式预测结果。利用美国PJM电力市场电价数据进行的仿真分析表明，提出的日前电价波动模式预测方法能得到较为准确的模式预测结果；利用电价波动模式日前预报进行分类预测的精度相对统一预测有显著提高。

关键词: 日前电价预测, 分类预测, 日波动模式, 加权组合预报

Abstract: Accurate forecasting of day-ahead electricity price is of great significance to the decision-making optimization for electricity market participants. At present, most day-ahead electricity price forecasting methods do not distinguish daily fluctuations of electricity prices and adopt unified models. When the forecasted day's fluctuation pattern is different from historical data, the forecasting accuracy cannot be guaranteed. Based on different fluctuation patterns, classification modeling that uses similar historical data is an effective way to solve this problem. As a result, it is necessary to establish a classification recognition model for different patterns of historical data and a prediction model for future fluctuations. For this reason, this paper proposes a day-ahead weighted combination forecasting method for daily fluctuations of electricity price that serves for classification forecasting. Firstly, the K-means algorithm is used to cluster the daily electricity price series. On the basis of clustering analysis results, the feature vector reflecting the difference of daily fluctuation patterns is extracted. The support vector machine for classification （SVC） method is used to establish a recognition model for daily fluctuation patterns of electricity price data. Secondly, multiple conventional methods are applied to establish day-ahead electricity price forecasting models, and the forecasting results are input into the daily fluctuation pattern recognition model to obtain corresponding pattern recognition results. On the basis of the different pattern forecasting precisions of historical results from multiple models, a credibility based combination mechanism is designed to realize weighted combination forecasting considering the prediction accuracy, and the final forecasting results of the daily fluctuation model is obtained. Simulation analysis using the electricity price data of the PJM electricity market in the United States shows that the proposed forecasting method for future electricity price fluctuations can obtain relatively accurate forecasting results|and compared with unified forecasting the accuracy using this method for classification forecasting of electricity price is improved.

Key words: day-ahead electricity price forecasting, classification forecasting, daily fluctuation pattern, weighted combination prediction

中图分类号:

姜利辉, 周立栋，任建国，柯鹏，田林静，王飞. 基于可信度加权组合的电价波动模式日前预报方法[J]. 电力建设, 2018, 39(7): 24-31.

JIANG Lihui, ZHOU Lidong, REN Jianguo, KE Peng, TIAN Linjing, WANG Fei. Day-ahead Prediction Approach of Electricity Price Fluctuation Pattern based on Credibility Weighted Combination[J]. Electric Power Construction, 2018, 39(7): 24-31.

参考文献

［1］刘达. 电力市场中电价预测模型方法及应用研究［D］. 北京：华北电力大学, 2008.

LIU Da. Modeling methodology and its application for price forecasting in electricity market ［D］. Beijing ：North China Electric Power University , 2008.

［2］WANC, XU Z, WANG Y, et al. A hybrid approach for probabilistic forecasting of electricity price ［J］.IEEE Transactions on Smart Grid, 2014, 5（1）: 463-470.

［3］周明,聂艳丽,李庚银,等. 基于小波分析的短期电价ARIMA预测方法［J］. 电网技术, 2005,29（9）: 50-55.

ZHOU Ming, NIE Yanli, LI Gengyin, et al. Wavelet analysis based ARIMA hourly electricity prices forecasting approach ［J］. Power System Technology, 2005,29（9）: 50-55.

［4］CONTRERAS J, ESPNOLA R, NOGALES F J, et al. ARIMA models to predict next-day electricity prices ［J］, IEEE Transactions on Power Systems, 2003, 18（3）: 1014-1020.

［5］刘达,牛东晓,邢棉,等. 基于GARCH误差校正的遗传支持向量机日前电价预测［J］. 电力系统自动化, 2007,31（11）: 31-34.

LIU Da, NIU Dongxiao, XING Mian, et al. Day-ahead price forecast with genetic-algorithm-optimized support vector machines based on GARCH error calibration ［J］. Automation of Electric Power Systems, 2007,31（11）: 31-34.

［6］GARCIA R C, CONTRERAS J, VAN AKKEREN M, et al. A GARCH forecasting model to predict day-ahead electricity prices ［J］. IEEE Transactions on Power Systems, 2005, 20（2）: 867-874.

［7］刘正国,付祥明,高伏英,等. 基于神经网络的浙江发电市场清算电价预测方法［J］. 电力系统自动化, 2002,26（9）: 49-52.

LIU Zhengguo, FU Xiangming, GAO Fuying, et al. Forecasting market-clearing price in Zhejiang generation market using neural network ［J］. Automation of Electric Power Systems, 2002,26（9）: 49-52.

［8］KELES D, SCELLE J, PARASCHIV F, et al. Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks ［J］.Applied Energy, 2016, 162: 218-230.

［9］彭春华,刘刚,相龙阳. 基于Relief相关性特征提取和微分进化支持向量机的短期电价预测［J］. 电工技术学报, 2013, 28（1）: 277-284.

PENG Chunhua, LIU Gang, XIANG Longyang. Short-Term electricity price forecasting using relief-correlation analysis based on feature selection and differential evolution support vector machine ［J］. Transactions of China Electrotechnical Society, 2013, 28（1）: 277-284.

［10］GAO C, BOMPARD E, NAPOLI R, et al. Price forecast in the competitive electricity market by support vector machine ［J］. Physica A: Statistical Mechanics and its Applications, 2007, 382（1）:98-113.

［11］曾鸣,冯义,刘达,等. 基于证据理论的多模型组合电价预测［J］. 中国电机工程学报, 2008,28（16）: 84-89.

ZENG Ming, FENG Yi, LIU Da, et al. Electricity price forecasting based on multi-models combined by evidential theory ［J］. Proceedings of the CSEE, 2008,28（16）: 84-89.

［12］DARUDI A, BASHARI M,JAVIDI M H. Electricity price forecasting using a new data fusion algorithm ［J］. IET Generation, Transmission & Distribution, 2015, 9（12）: 1382-1390.

［13］王飞,米增强,甄钊,等. 基于天气状态模式识别的光伏电站发电功率分类预测方法［J］. 中国电机工程学报, 2013, 33（34）: 75-82.

WANG Fei, MI Zengqiang, ZHEN Zhao, et al. A classified forecasting approach of power generation for photovoltaic plants based on weather condition pattern recognition ［J］. Proceedings of the CSEE, 2013, 33（34）: 75-82.

［14］MARTNEZ LVAREZ F, TRONCOSO A, RIQUELME J C, et al. Energy time series forecasting based on pattern sequence similarity ［J］. IEEE Transactions on Knowledge and Data Engineering, 2011, 23（8）: 1230-1243.

［15］JIN C H, POK G, LEE Y, et al. A SOM clustering pattern sequence-based next symbol prediction method for day-ahead direct electricity load and price forecasting ［J］. Energy Conversion and Management, 2015, 90: 84-92.

［16］王雅,曾成碧,苗虹,等. 基于K-means聚类的有序充放电多目标调度模型［J］. 电力建设, 2016, 37（7）: 99-104.

WANG Ya, ZENG Chengbi, MIAO Hong, et al. Multi-objective scheduling model for coordinated charging and discharging based on K-means clustering ［J］. Electric Power Construction, 2016, 37（7）: 99-104.

［17］苏适,周立栋,万筱钟,等. 计及气象因素的用电负荷短期分时分类预测模型与方法［J］. 电力建设, 2017, 38（10）: 76-83.

SU Shi, ZHOU Lidong, WAN Xiaozhong, et al. Time-sharing and classified prediction model for short-term load considering meteorological factors ［J］. Electric Power Construction, 2017, 38（10）: 76-83.

［18］张强,王毅,李鼎睿,等. 基于X-12-ARIMA季节分解与年度电量校正的月度电量预测［J］. 电力建设, 2017, 38（1）: 76-83.

ZHANG Qiang, WANG Yi, LI Dingrui, et al. Monthly electricity forecast based on X-12-ARIMA seasonal decomposition and annual electricity correction ［J］. Electric Power Construction, 2017, 38（1）: 76-83.

［19］XU Xiaobo, LIU Wenxia, XI Zhou, et al. Short-term load forecasting for the electric bus station based on GRA-DE-SVR ［C］. IEEE Innovative Smart Grid Technologies-Asia Conf. （ISGT ASIA）, 2014: 388-393.

［20］赵希梅,金鸿雁. 基于Elman神经网络的永磁直线同步电机互补滑模控制［J］.电工技术学报, 2018, 33（5）: 973-979.

ZHAO Ximei, JIN Hongyan. Complementary sliding mode control for permanent magnet linear synchronous motor based on Elman neural network ［J］. Transactions of China Electrotechnical Society, 2018, 33（5）: 973-979.

［21］殷豪,董朕,马留洋. 基于可变模式分解和NWCSO优化极限学习机的短期风速预测［J］. 电力建设, 2017, 38（6）: 36-43.

YIN Hao, DONG Zhen, MA Liuyang. Short-term wind speed forecasting based on variational mode decomposition and extreme learning machine optimized by NW small world crisscross optimization ［J］. Electric Power Construction, 2017, 38（6）: 36-43.

［22］李永明,王玉强,徐禄文,等. 变电站噪声预测和仿真分析［J］. 电力建设, 2013, 34（7）: 63-67.

LI Yongming, WANG Yuqiang, XU Luwen, et al. Audible noise prediction and simulation analysis in substation ［J］. Electric Power Construction, 2013, 34（7）: 63-67.

基于可信度加权组合的电价波动模式日前预报方法

Day-ahead Prediction Approach of Electricity Price Fluctuation Pattern based on Credibility Weighted Combination

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价