基于数据挖掘的短期电力负荷风险预测分析

doi:10.12052/gdutxb.170044

摘要/Abstract

摘要：

电力负荷风险越来越成为电力生产行业关注的热点，传统的电力负荷风险预测仅仅从单因素测评台区的风险度，缺乏全面和系统性.因此，传统的预测方法，不能准确地预测风险因素造成的电力故障隐患.为解决此问题，从供电局客服数据、机器监测台区记录、天气等多数据源着手，对电力负荷风险进行分析和预测.首先，对数据进行清洗和分类.然后，利用K-Mean聚类筛选出与电力负荷相关性强的因素作为模型的变量.并在此基础上，构建基于贝叶斯判别的台区电力风险预测模型.通过数据实验，该模型能够以99.53%的准确度来预估台区的负荷风险，从而进行有效的电力故障预测判断，为电力企业传送电的风险防范和控制决策提供支持，降低客户的用电故障，提高客户满意度.

关键词: 数据挖掘, 电力负荷, 风险预测, 聚类, 贝叶斯模型

Abstract:

The risk of power load becomes the hot spot in the electric power industry; however, due to the single factor evaluation, the traditional power load forecasting model is not adequately comprehensive and systematic. Hence, it cannot accurately predict the risk and may cause hidden danger of power failures. To address this issue, the risk of power load is analyzed and forecast by collecting data from multiple sources:customer service center, machine, and historical weather records and so on. First by cleaning and sorting the data and then by the K-Mean clustering, variables are chosen which have strong correlation with risk degree of transformer to construct the Bayesian discriminant models. The experimental results show that this model can accurately predict the risk of transformer at a certain probability of 99.53%. In the practical aspect, this model can provide prevention scheme and control decisions to power supply security and contribute to reduce customer's electricity failure and improve customer satisfaction.

Key words: data mining, electric load, prediction of risk, clustering, Bayesian

中图分类号:

TM714

陈丽, 曹熙, 林俊杰, 高鸿铭, 刘飞雅, 李艳艳. 基于数据挖掘的短期电力负荷风险预测分析[J]. 广东工业大学学报, 2017, 34(03): 105-109.

Chen Li, Cao Xi, Lin Jun-jie, Gao Hong-ming, Liu Fei-ya, Li Yan-yan. Prediction of Short-Term Load Based on Big Data Mining[J]. Journal of Guangdong University of Technology, 2017, 34(03): 105-109.

参考文献

[1] 何洋, 邹波, 李文启, 等. 基于混沌理论的电力系统短期负荷预测的局域模型[J]. 华北电力大学学报(自然科学版), 2013, 40(4):43-50. HE Y, ZOU B, LI W Q. A chaos theory based local model for short-term load forecasting[J]. Journal of North China Electric Power University (Natural Science Edition), 2013, 40(4):43-50.
[2] 牛东晓, 吕海涛, 张云云. 贝叶斯框架下最小二乘支持向量机的中长期电力负荷组合预测[J]. 华北电力大学学报(自然科学版), 2008, 35(6):62-66. NIU D X, LV H T, ZHANG Y Y. Bayesian framework LSSVM the long term load forecasting[J]. Journal of North China Electric Power University (Natural Science Edition), 2008, 35(6):62-6.
[3] 廖旎焕, 胡智宏, 马莹莹,. 电力系统短期负荷预测方法综述[J]. 电力系统保护与控制, 2011, 39(1):147-152. LIAO N H, HU Z H, MA Y Y. Summary of forecasting methods of power system short-term load[J]. Power System Protection and Control, 2011, 39(01):147-52.
[4] 彭鹏, 彭佳红. 基于多元线性回归模型的电力负荷预测研究[J]. 中国安全生产科学技术, 2011, 7(9):158-161. PENG P, PENG J H. Power load based on multiple linear regression model prediction[J]. Journal of Safety Science and Technology, 2011, 07(9):158-61.
[5] 陈娟, 吉培荣, 卢丰. 指数平滑法及其在负荷预测中的应用[J]. 三峡大学学报(自然科学版), 2010, 32(3):37-41. CHEN J. JI P R. LU F. Exponential smoothing method and its application in Load Forecasting[J]. Journal of China Three Gorges University (Natural Sciences), 2010, 32(3):37-41.
[6] 樊一娜. 基于马尔科夫链的短期电力负荷预测[J]. 青海大学学报(自然科学版), 2012, 3:11-14. FAN Y N. Short term load forecasting based on markov chain[J]. Journal of Qinghai University (Nature Science Edition), 2012, 3:11-4.
[7] 张素香, 赵丙镇, 王风雨. 海量数据下的电力负荷短期预测[J]. 中国电机工程学报, 2015, 35(1):37-42. ZHANG S X, ZHAO B Z, WANG F Y. Term load forecasting based on massive data[J]. Proceedings of the CSEE, 2015, 35(1):37-42.
[8] 侯慧, 李元晟, 杨小玲. 冰雪灾害下的电力系统安全风险评估综述[J]. 武汉大学学报(工学版), 2014, 47(3):414-419. HOU H, LI Y C, YANG X L. An overview of power system risk assessment under ice disaster[J]. Engineering Journal of Wuhan University, 2014, 47(3):414-419.
[9] 李知艺, 丁剑鹰, 吴迪. 电力负荷区间预测的集成极限学习机方法[J]. 华北电力大学学报, 2014, 41(2):78-88. LI Z Y, DING J Y, WU D. An ensemble model of the extreme learning machine for load interval prediction[J]. Journal of North China Electric Power University, 2014, 41(2):78-88.
[10] 熊小伏, 李磊, 方丽华. 基于可靠性和气象因素的配电网短期维修决策方法[J]. 电力系统保护与控制, 2013(20):61-66. XIONG X F, LI L, FANG L F. A decision method of short-term distribution network maintenance schedule based on reliability and meteorological factors[J]. Power System Protection and Control, 2013(20):61-66.
[11] 何剑, 程林, 孙元章. 计及天气预测的电力系统运行可靠性短期评估[J]. 电力系统保护与控制, 2010, 38(10):31-38. HE J, CHENG L, SUN Y Z. Power system short-term operational reliability evaluation considering weather forecast[J]. Power System Protection and Control, 2010, 38(10):31-38.
[12] 张小易, 徐兵, 张岩. 利用气象等影响要素的电力系统故障元件识别与故障原因分析[J]. 华北电力大学学报, 2014, 41(6):14-21. ZHANG X Y, XU B, ZHANG Y. Fault section estimation and fault cause analysis employing meteorological and other impacting factors[J]. Journal of North China Electric Power University, 2014, 41(6):14-21.
[13] 陈璟华, 陈少华, 杨宜民, 等. 电力系统二级电压的多智能体协调控制[J]. 广东工业大学学报, 2003, 20(1):28-31. CHEN J H, CHEN S H, YANG Y M, et al. Multi-agent based on secondary voltage coordination control in power system[J]. Journal of Guangdong University of Technology, 2003, 20(1):28-31.
[14] 索智勇, 李日隆. 地方电网最大负荷供应能力的研究[J]. 广东工业大学学报, 2004, 21(2):64-67. SUO Z Y, LI R L. LSC study on local power network[J]. Journal of Guangdong University of Technology, 2004, 21(2):64-67.
[15] 白雪峰, 蒋国栋. 基于改进K-means聚类算法的负荷建模及应用[J]. 电力自动化设备, 2010, 30(7):80-83. BAI X F, JIANG G D. Load modeling based on improved K-means clustering algorithm and its application[J]. Electric Power Automation Equipment, 2010, 30(7):80-83.
[16] 陈宏义, 李存斌, 施立刚. 基于聚类分析的短期负荷智能预测方法研究[J]. 湖南大学学报(自然科学版). 2014, 41(5):94-98. CHEN H Y, LI C B, SHI L G. A new forecasting approach for short-term load intelligence based on cluster method[J]. Journal of Hunan University (Natural Sciences), 2014, 41(5):94-98.
[17] 栗然, 高聪颖, 张烈勇. 基于粗糙集-贝叶斯方法的分布式电网故障诊断[J]. 华北电力大学学报. 2010, 37(2):1-7. LI R, GAO C Y, ZHANG L Y. The distributed fault diagnosis of power networks based on Bayesian rough set method[J]. Journal of North China Electric Power University, 2010, 37(2):1-7.
[18] 于烨, 陈鹏, 李斌. 决策支持技术在电能质量监测中的应用研究[J]. 太原理工大学学报, 2010, 41(6):717-722. YU Y, CHEN P, LI B. Development and realization of decision support technology in power quality monitoring[J]. Journal of Taiyuan University of Technology, 2010, 41(6):717-722.

Metrics

Viewed

Full text

2851

HTML			PDF

Just accepted	Online first	Issue	Just accepted	Online first	Issue
0	0	0	0	0	2851

From	Others	local

Times	426	2425
Rate	15%	85%

Abstract

493

Just accepted	Online first	Issue

0	0	493

From	Others	local

Times	174	319
Rate	35%	65%

Cited

Web of Science	Crossref	ScienceDirect	Search for Citations in Google Scholar >>


This page requires you have already subscribed to WoS.

Shared

Discussed