Power data analysis based on financial technical indicators

doi:10.11772/j.issn.1001-9081.2021030447

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (3): 904-910.DOI: 10.11772/j.issn.1001-9081.2021030447

• Data science and technology • Previous Articles Next Articles

Power data analysis based on financial technical indicators

An YANG¹, Qun JIANG², Gang SUN², Jie YIN³, Ying LIU¹()

^1.College of Information Science & Electronic Engineering，Zhejiang University，Hangzhou Zhejiang 310027，China
^2.Marketing Service Center，State Grid Zhejiang Electric Power Company Limited，Hangzhou Zhejiang 311121，China
^3.Zhejiang Huayun Information Technology Company Limited，Hangzhou Zhejiang 310012，China

Received:2021-03-23 Revised:2021-07-06 Accepted:2021-07-07 Online:2022-04-09 Published:2022-03-10
Contact: Ying LIU
About author:YANG An， born in 1998， Ph. D. candidate. His research interests include data mining， transfer learning.
JIANG Qun， born in 1989， M. S.， engineer. Her research interests include electric energy measurement， power information acquisition， power marketing service.
SUN Gang， born in 1987， M. S.， senior engineer. His research interests include marketing measurement.
YIN Jie， born in 1982， senior engineer. His research interests include power information acquisition， data analysis.

基于金融技术指标的用电数据分析

杨安¹, 蒋群², 孙钢², 殷杰³, 刘英¹()

^1.浙江大学信息与电子工程学院，杭州 310027
^2.国网浙江省电力有限公司营销服务中心，杭州 311121
^3.浙江华云信息科技有限公司，杭州 310012

通讯作者: 刘英
作者简介:杨安（1998—），男，山东聊城人，博士研究生，主要研究方向：数据挖掘、迁移学习
蒋群（1989—），女，浙江杭州人，工程师，硕士，主要研究方向：电能计量、用电信息采集、电力营销服务
孙钢（1987—），男，浙江余杭人，高级工程师，硕士，主要研究方向：营销计量
殷杰（1982—），男，浙江海宁人，高级工程师，主要研究方向：用电信息采集、数据分析；

Abstract

Abstract:

Considering the lack of effective trend feature descriptors in existing methods， financial technical indicators such as Vertical Horizontal Filter （VHF） and Moving Average Convergence/Divergence （MACD） were introduced into power data analysis. An anomaly detection algorithm and a load forecasting algorithm using financial technical indicators were proposed. In the proposed anomaly detection algorithm， the thresholds of various financial technical indicators were determined based on statistics， and then the abnormal behaviors of user power consumption were detected using threshold detection. In the proposed load forecasting algorithm， 14 dimensional daily load characteristics related to financial technical indicators were extracted， and a Long Shot-Term Memory （LSTM） load forecasting model was built. Experimental results on industrial power data of Hangzhou City show that the proposed load forecasting algorithm reduces the Mean Absolute Percentage Error （MAPE） to 9.272%， which is lower than that of Autoregressive Integrated Moving Average （ARIMA）， Prophet and Support Vector Machine （SVM） algorithms by 2.322， 24.175 and 1.310 percentage points， respectively. The results show that financial technical indicators can be effectively applied to power data analysis.

Key words: power data analysis, smart grid, financial technical indicator, anomaly detection, load forecasting, Long Short-Term Memory (LSTM) network

摘要：

针对已有用电数据分析缺乏有效描述趋势性特征的不足，适应性地将金融领域中十字过滤线（VHF）、异同移动平均线（MACD）等技术指标迁移至用电数据分析中，提出了基于金融技术指标的异动检测算法和负荷预测算法。所提异动检测算法通过统计各指标的统计情况划定阈值，并采用阈值检测捕捉用户异常用电行为。所提负荷预测算法通过提取14项与金融技术指标相关的日负荷特征，构建了长短期记忆网络（LSTM）负荷预测模型。在杭州市工业用电数据上的实验结果表明，所提负荷预测算法将平均绝对百分比误差（MAPE）降低至9.272%，相较于差分整合移动平均自回归（ARIMA）算法、Prophet算法和支持向量机（SVM）算法，分别将MAPE降低了2.322、24.175和1.310个百分点，能够较好地应用于用电数据分析中。

关键词: 用电数据分析, 智能电网, 金融技术指标, 异动检测, 负荷预测, 长短期记忆网络

CLC Number:

TM714.3

An YANG, Qun JIANG, Gang SUN, Jie YIN, Ying LIU. Power data analysis based on financial technical indicators[J]. Journal of Computer Applications, 2022, 42(3): 904-910.

杨安, 蒋群, 孙钢, 殷杰, 刘英. 基于金融技术指标的用电数据分析[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 904-910.

Figures/Tables 12

Fig.1 Daily average load curve and corresponding VHF of a company in Hangzhou City in 2018

Fig. 2 Daily average load curve and corresponding MACD of a company in Hangzhou City in first half of 2018

Fig.3 Daily average load curve and corresponding MA and LSMA of a company in Hangzhou City in 2018

Fig.4 Daily average load curve and corresponding BOLL curves of a company in Hangzhou City in first half of 2018

Fig.5 Numerical statistics of VHF and ZLMACD of all the industry users in Hangzhou City in 2018

Fig.6 Results of anomaly detection of an industry user by combining VHF and ZLMACD

Fig.7 Candlestick chart of power load

Tab. 1 14-dimensional daily load feature vector

指标类型	特征参数	含义
K线核心参数	$P m a x$	日最大负荷
	$P m i n$	日最小负荷
	$P p e a k_a v g$	日尖峰平均负荷
	$P t r o u g h_a v g$	日平谷平均负荷
均线	LSMA（14）	最小二乘移动平均值
VHF指标	VHF（28）	十字过滤线指标值
ZLMACD 指标	ZLMA（12）	零滞后快速移动平均值
	ZLMA（26）	零滞后慢速移动平均值
	ZLDIF	零滞后差离值
	ZLMACD	零滞后异同移动平均值
布林线指标	BOLL_UP	布林线上轨线
布林线指标	BOLL_DN	布林线下轨线
社会因素	Day	周期参数，指示周一到周日
社会因素	Holiday	节假日参数，是否节假日

Tab. 1 14-dimensional daily load feature vector

指标类型	特征参数	含义
K线核心参数	$P m a x$	日最大负荷
	$P m i n$	日最小负荷
	$P p e a k_a v g$	日尖峰平均负荷
	$P t r o u g h_a v g$	日平谷平均负荷
均线	LSMA（14）	最小二乘移动平均值
VHF指标	VHF（28）	十字过滤线指标值
ZLMACD 指标	ZLMA（12）	零滞后快速移动平均值
	ZLMA（26）	零滞后慢速移动平均值
	ZLDIF	零滞后差离值
	ZLMACD	零滞后异同移动平均值
布林线指标	BOLL_UP	布林线上轨线
布林线指标	BOLL_DN	布林线下轨线
社会因素	Day	周期参数，指示周一到周日
社会因素	Holiday	节假日参数，是否节假日

Fig.8 Schematic diagram of the structure of LSTM cell

Fig.9 Schematic diagram of LSTM load forecasting model based on financial technical indicators

Fig.10 Candlestick chart of model prediction results for 10 consecutive days

Tab. 2 Performance comparison of different algorithms

MAPE/%	$P m a x$	$P p e a k_a v g$	$P m e a n$	$P t r o u g h_a v g$	$P m i n$
LSTM-FI	8.450	7.394	9.071	7.194	14.253
LSTM-noFI	12.018	11.416	14.326	12.288	23.684
ARIMA	8.517	16.845	11.031	10.784	10.793
Prophet	48.666	46.020	39.156	28.043	5.352
SVM	11.144	16.274	12.207	7.648	5.636

Tab. 2 Performance comparison of different algorithms

MAPE/%	$P m a x$	$P p e a k_a v g$	$P m e a n$	$P t r o u g h_a v g$	$P m i n$
LSTM-FI	8.450	7.394	9.071	7.194	14.253
LSTM-noFI	12.018	11.416	14.326	12.288	23.684
ARIMA	8.517	16.845	11.031	10.784	10.793
Prophet	48.666	46.020	39.156	28.043	5.352
SVM	11.144	16.274	12.207	7.648	5.636

References 21

1	梁跃.基于机器学习的电力用户用电异常检测技术研究［D］.北京：北京邮电大学，2019：1-2.
	LIANG Y. Research on electric anomaly detection technology for power users based on machine learning ［D］. Beijing： Beijing University of Posts and Telecommunications， 2019：1-2.
2	张荣昌.基于数据挖掘的用电数据异常的分析与研究［D］.北京：北京交通大学，2017：1-3.
	ZHANG R C. Analysis of abnormal electro-data based on data mining ［D］. Beijing： Beijing Jiaotong University， 2017：1-3.
3	程海花，李晓明，黄军高，等.窃电检测在电能量计量计费系统中的应用［J］.电力系统及其自动化学报，2001（6）：53-57. 10.3969/j.issn.1003-8930.2001.06.014
	CHENG H H， LI X M， HUANG J G， et al. Applying of detecting the theft of electricity in the power energy billing system ［J］. Proceedings of the CSU-EPSA， 2001（6）： 53-57. 10.3969/j.issn.1003-8930.2001.06.014
4	付青，匡文凯，薛阳，等.基于高斯核密度估计法的路灯窃电检测方法［J］.电力系统及其自动化学报， 2021，31（10）：18-23.
	FU Q， KUANG W K， XUE Y， et al. Gauss kernel density estimation based detection of street lamp electricity theft ［J］. Proceedings of the CSU-EPSA， 2021，31（10）：18-23.
5	庄池杰，张斌，胡军，等.基于无监督学习的电力用户异常用电模式检测［J］.中国电机工程学报，2016，36（2）：379-387.
	ZHUANG C J， ZHANG B， HU J， et al. Anomaly detection for power consumption patterns based on unsupervised learning ［J］. Proceedings of the CSEE， 2016， 36（2）： 379-387.
6	田力，向敏.基于密度聚类技术的电力系统用电量异常分析算法［J］.电力系统自动化，2017，41（5）：64-70. 10.7500/AEPS20160510003
	TIAN L， XIANG M. Abnormal power consumption analysis based on density-based spatial clustering of applications with noise in power systems ［J］. Automation of Electric Power Systems， 2017， 41（5）： 64-70. 10.7500/AEPS20160510003
7	MURTHY T S， GOPALAN N P， RAMACHANDRAN V. A Naive Bayes classifier for detecting unusual customer consumption profiles in power distribution systems—APSPDCL ［C］// Proceedings of the 2019 3rd International Conference on Inventive Systems and Control. Piscataway： IEEE， 2019： 673-678. 10.1109/icisc44355.2019.9036460
8	ESTEVES P R， VIEGAS J L， VIEIRA S M. Clustering-based novelty detection for identification of non-technical losses ［J］. International Journal of Electrical Power & Energy Systems， 2018， 101： 301-310. 10.1016/j.ijepes.2018.03.031
9	刘士进，孙立华，郭鹏.基于EEDM-ARIMA算法的某地区电力系统负荷预测及算例分析［J］.电子测量技术，2020，43（7）：185-188.
	LIU S J， SUN L H， GUO P. Load forecasting and analysis of power system based on EEDM-ARIMA algorithm ［J］. Electronic Measurement Technology， 2020， 43（7）： 185-188.
10	李震，张思，任娴婷，等.基于数据驱动的线性聚类ARIMA长期电力负荷预测［J］.科学技术与工程，2020，20（16）：6497-6504. 10.3969/j.issn.1671-1815.2020.16.029
	LI Z， ZHANG S， REN X T， et al. Long-term power load forecasting based on data-driven linear clustering ARIMA ［J］. Science Technology and Engineering， 2020， 20（16）：6497-6504. 10.3969/j.issn.1671-1815.2020.16.029
11	彭湃，刘敏.基于Prophet-LSTM组合模型的短期负荷预测方法［J］.电力系统及其自动化学报， 2021， 33（11）： 15-20.
	PENG P， LIU M. Short-term load forecasting method based on Prophet-LSTM combined model ［J］. Proceedings of the CSU-EPSA， 2021， 33（11）： 15-20.
12	李玉凯，韩佳兵，王全，等.基于Fbprophet负荷预测与用户满意度约束的综合能源供能优先调度研究［J］.华北电力大学学报（自然科学版）， 2021， 48（5）： 81-89.
	LI Y K， HAN J B， WANG Q， et al. Integrated energy load priority scheduling model based on Fbprophet prediction algorithm and customer satisfaction constraints ［J］. Journal of North China Electric Power University （Natural Science Edition）， 2021， 48（5）： 81-89.
13	王克杰，张瑞.基于改进BP神经网络的短期电力负荷预测方法研究［J］.电测与仪表，2019，56（24）：115-121. 10.46300/9106.2020.14.109
	WANG K J， ZHANG R. Research on short-term power load forecasting method based on improved BP neural network ［J］. Electrical Measurement & Instrumentation， 2019， 56（24）： 115-121. 10.46300/9106.2020.14.109
14	刘晓悦，孙海鹤.基于模糊灰色聚类AMPSO-BP短期负荷预测［J］.微电子学与计算机，2019，36（5）：70-75.
	LIU X Y， SUN H H. Short-term load forecasting based on fuzzy gray correlation clustering and AMPSO-BP neural network ［J］. Microelectronics & Computer， 2019， 36（5）： 70-75.
15	肖勇，郑楷洪，郑镇境，等.基于多尺度跳跃深度长短期记忆网络的短期多变量负荷预测［J］.计算机应用，2021，41（1）：231-236. 10.11772/j.issn.1001-9081.2020060929
	XIAO Y， ZHENG K H， ZHENG Z J， et al. Multi-scale skip deep long short-term memory network for short-term multivariate load forecasting ［J］. Journal of Computer Applications， 2021， 41（1）： 231-236. 10.11772/j.issn.1001-9081.2020060929
16	庄家懿，杨国华，郑豪丰，等.并行多模型融合的混合神经网络超短期负荷预测［J］.电力建设，2020，41（10）：1-8. 10.12204/j.issn.1000-7229.2020.10.001
	ZHUANG J Y， YANG G H， ZHENG H F， et al. Ultra-short-term load forecasting using hybrid neural network based on parallel multi-model combination ［J］. Electric Power Construction， 2020， 41（10）： 1-8. 10.12204/j.issn.1000-7229.2020.10.001
17	洪发.基于深度学习的短期电力负荷预测方法［D］.广州：广东工业大学，2020：31-44.
	HONG F. Research on fault location of distribution network based on matrix method ［D］. Guangzhou： Guangdong University of Technology， 2020：31-44.
18	李丹.基于多视角特征数据的股票预测研究［D］.西安：西北大学，2018：11-13.
	LI D. Research on stock forecasting based on the multi-view feature data ［D］. Xi’an： Northwest University， 2018：11-13.
19	胡博然.基于改进布林线与KDJ指标相结合的量化策略研究［D］.哈尔滨：哈尔滨工业大学，2019：10-17.
	HU B R. Research on quantitative strategy based on improved Bollinger band and KDJ index ［D］. Harbin： Harbin Institute of Technology， 2019：10-17.
20	刘瀚琳.基于数据挖掘的电力负荷预测与偏差预警［D］.杭州：浙江大学，2009：7-24. 10.29252/jafm.12.03.28662
	LIU H L. Power load forecasting and its deviation warning based on data mining ［D］. Hangzhou： Zhejiang University， 2019：7-24. 10.29252/jafm.12.03.28662
21	郑国和，贺民，郑瑞云，等.基于多表融合数据的用户短期用电量预测［J］.电力系统及其自动化学报，2019，31（3）：146-150.
	ZHENG G H， HE M， ZHENG R Y， et al. Short-term electricity consumption forecasting based on multi-meter data fusion ［J］. Proceedings of the CSU-EPSA， 2019， 31（3）： 146-150.

[1]	Tingwei CHEN, Jiacheng ZHANG, Junlu WANG. Random validation blockchain construction for federated learning [J]. Journal of Computer Applications, 2024, 44(9): 2770-2776.
[2]	Hong CHEN, Bing QI, Haibo JIN, Cong WU, Li’ang ZHANG. Class-imbalanced traffic abnormal detection based on 1D-CNN and BiGRU [J]. Journal of Computer Applications, 2024, 44(8): 2493-2499.
[3]	Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557.
[4]	Xinrui LIN, Xiaofei WANG, Yan ZHU. Academic anomaly citation group detection based on local extended community detection [J]. Journal of Computer Applications, 2024, 44(6): 1855-1861.
[5]	Fan MENG, Qunli YANG, Jing HUO, Xinkuan WANG. EraseMTS： iterative active multivariable time series anomaly detection algorithm based on margin anomaly candidate set [J]. Journal of Computer Applications, 2024, 44(5): 1458-1463.
[6]	Zimeng ZHU, Zhixin LI, Zhan HUAN, Ying CHEN, Jiuzhen LIANG. Weakly supervised video anomaly detection based on triplet-centered guidance [J]. Journal of Computer Applications, 2024, 44(5): 1452-1457.
[7]	Yongjiang LIU, Bin CHEN. Pixel-level unsupervised industrial anomaly detection based on multi-scale memory bank [J]. Journal of Computer Applications, 2024, 44(11): 3587-3594.
[8]	Pei ZHAO, Yan QIAO, Rongyao HU, Xinyu YUAN, Minyue LI, Benchu ZHANG. Multivariate time series anomaly detection based on multi-domain feature extraction [J]. Journal of Computer Applications, 2024, 44(11): 3419-3426.
[9]	Xiaoyu HUA, Dongfen LI, You FU, Kejun BI, Shi YING, Ruijin WANG. Industrial chain risk assessment and early warning model combining hierarchical graph neural network and long short-term memory [J]. Journal of Computer Applications, 2024, 44(10): 3223-3231.
[10]	Hui JIANG, Qiuyan YAN, Zhujun JIANG. Symmetric positive definite autoencoder method for multivariate time series anomaly detection [J]. Journal of Computer Applications, 2024, 44(10): 3294-3299.
[11]	Lishuo YE, Zhixue HE. Multiscale time series anomaly detection incorporating wavelet decomposition [J]. Journal of Computer Applications, 2024, 44(10): 3300-3306.
[12]	Yuhao TANG, Dezhong PENG, Zhong YUAN. Fuzzy multi-granularity anomaly detection for incomplete mixed data [J]. Journal of Computer Applications, 2024, 44(10): 3097-3104.
[13]	Yuning ZHANG, Abudukelimu ABULIZI, Tisheng MEI, Chun XU, Maierdana MAIMAITIREYIMU, Halidanmu ABUDUKELIMU, Yutao HOU. Anomaly detection method for skeletal X-ray images based on self-supervised feature extraction [J]. Journal of Computer Applications, 2024, 44(1): 175-181.
[14]	Li’an CHEN, Yi GUO. Text sentiment analysis model based on individual bias information [J]. Journal of Computer Applications, 2024, 44(1): 145-151.
[15]	Zhiping ZHU, Yan YANG, Jie WANG. Scene graph-aware cross-modal image captioning model [J]. Journal of Computer Applications, 2024, 44(1): 58-64.

Power data analysis based on financial technical indicators

基于金融技术指标的用电数据分析

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 21

Related Articles 15

Recommended Articles

Metrics