CN112597440A - Power consumption transaction analysis method based on financial technical indexes - Google Patents

Power consumption transaction analysis method based on financial technical indexes Download PDF

Info

Publication number
CN112597440A
CN112597440A CN202011503212.3A CN202011503212A CN112597440A CN 112597440 A CN112597440 A CN 112597440A CN 202011503212 A CN202011503212 A CN 202011503212A CN 112597440 A CN112597440 A CN 112597440A
Authority
CN
China
Prior art keywords
index
dissimilarity
line index
power consumption
line
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011503212.3A
Other languages
Chinese (zh)
Inventor
王伟峰
孙钢
姚一杨
程清
陈政波
郁春雷
李帮准
葛岳军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
State Grid Zhejiang Electric Power Co Ltd
Zhejiang Huayun Information Technology Co Ltd
Information and Telecommunication Branch of State Grid Zhejiang Electric Power Co Ltd
Marketing Service Center of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
State Grid Zhejiang Electric Power Co Ltd
Zhejiang Huayun Information Technology Co Ltd
Information and Telecommunication Branch of State Grid Zhejiang Electric Power Co Ltd
Marketing Service Center of State Grid Zhejiang Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, State Grid Zhejiang Electric Power Co Ltd, Zhejiang Huayun Information Technology Co Ltd, Information and Telecommunication Branch of State Grid Zhejiang Electric Power Co Ltd, Marketing Service Center of State Grid Zhejiang Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202011503212.3A priority Critical patent/CN112597440A/en
Publication of CN112597440A publication Critical patent/CN112597440A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/80—Management or planning
    • Y02P90/82—Energy audits or management systems therefor

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Educational Administration (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Mathematical Analysis (AREA)
  • Tourism & Hospitality (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Quality & Reliability (AREA)
  • Public Health (AREA)
  • Game Theory and Decision Science (AREA)
  • Water Supply & Treatment (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Algebra (AREA)
  • Primary Health Care (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Technology Law (AREA)

Abstract

The invention discloses a power consumption transaction analysis method based on financial technical indexes, and relates to the field of power consumption transaction analysis. At present, abnormal analysis of power consumption data is mostly limited to abnormal conditions of mining power consumption data, and abnormal conditions caused by production transformation, economic operation and the like of enterprises are difficult to capture. The method comprises the steps of depicting the characteristics of an electric load sequence through cross filter lines, zero-lag dissimilarity movement mean lines and a brink line index, adaptively setting index parameters to meet specific scenes of a dissimilarity analysis task, setting a reasonable threshold according to an index probability distribution diagram in the same industry, determining the character exceeding the index threshold as dissimilarity, effectively describing load curve characteristics, realizing effective grabbing of a dissimilarity phenomenon, and ensuring that a dissimilarity analysis result has certain interpretability. The remarkable abnormal change of the electricity utilization data can be accurately and effectively screened out; and the detection of power utilization mutation is captured by the aid of the auxiliary forest line indexes, so that capture work of abnormal movement is realized, and the effectiveness of abnormal movement analysis is further ensured.

Description

Power consumption transaction analysis method based on financial technical indexes
Technical Field
The invention relates to the field of power consumption transaction analysis, in particular to a power consumption transaction analysis method based on financial technical indexes.
Background
The power utilization data analysis lays a necessary foundation for operation and service optimization of the power industry in China. The power consumption transaction analysis can not only expose the aging fault of the power physical information acquisition system, reveal the power stealing and stealing situation of an enterprise to a certain extent, but also evaluate the development activity of the enterprise from the power consumption perspective, further adjust the power supply policy, improve and improve the economic benefit. At present, the analysis of abnormal change of electricity consumption data mainly comprises two main methods. The first method generally sets a certain priori abnormal motion threshold value aiming at a single-day load curve, such as load rate, daily peak-valley difference rate, flat-period load rate, maximum and minimum load and the like, and performs abnormal motion analysis. Although the indexes have definite physical significance and explanatory significance, the characteristic selection has strong subjectivity, and information for comprehensively representing load variation is difficult to obtain. The second major method mainly adopts data mining methods such as clustering or neural networks to mine the abnormal movement data, and although the subjectivity of manually selecting characteristics is weakened, the abnormal movement detection result lacks reasonable explanation and clear physical significance. In addition, it should be noted that most of the two methods are limited to mining abnormal situations of electricity consumption data, and it is difficult to capture abnormal situations caused by enterprise production modification, economic operation and the like. Therefore, it is necessary to research an interpretable index that can characterize a long-term load curve, capture the power consumption fluctuation of an enterprise in real time, and understand the operation state of the enterprise.
Disclosure of Invention
The technical problem to be solved and the technical task to be solved by the invention are to perfect and improve the prior technical scheme and provide a power consumption transaction analysis method based on financial technical indexes so as to achieve the purpose of capturing power consumption transactions of enterprises in real time. Therefore, the invention adopts the following technical scheme.
A power consumption transaction analysis method based on financial technical indexes comprises the following steps:
1) acquiring power consumption data of power consumers, calculating the average load of each consumer, and performing data completion and standardization on the average load data;
2) based on the average load, calculating a cross filter line index VHF and a zero lag dissimilarity movement average line index ZLACD;
3) according to the index distribution condition of the industry, counting the frequency distribution of a cross filter line index VHF and a zero lag dissimilarity movement average line index ZLMACD index in the same industry; calculating the threshold values of the corresponding cross filter line index VHF and the zero lag dissimilarity movement average line index ZLMACD, and determining an index dissimilarity data section when the cross filter line index VHF and the zero lag dissimilarity movement average line index ZLMACD exceed the threshold values simultaneously;
4) calculating transaction data segments
Figure BDA0002844220050000021
Value of, wherein rabsThe absolute value of the difference value r of the synchronous ratio of the data of 30 days before and after the transaction data section and the data of the previous yearrelRepresenting the relative value of the difference value of the synchronous ratio of the data of 30 days before and after the transaction data segment and the data of the previous year according to the same industry
Figure BDA0002844220050000022
Determining a threshold value through the frequency distribution of the values, eliminating periodic factors through the threshold value, and re-determining the power consumption abnormal data section;
5) calculating a Booth line index BOLL based on the average load, determining an upper track and a lower track, and considering the Booth line index BOLL as an index transaction data section when the Booth line index BOLL exceeds the upper track or is lower than the lower track; the detection of power utilization mutation is captured by using a Boolean line index BOLL, and the capture work of abnormal motion is realized;
6) and (5) integrating the steps 4) and 5) to obtain a final index transaction data segment, and outputting the final index transaction data segment.
As a preferable technical means: in step 2), the cross filter line index VHF is calculated by the formula:
Figure BDA0002844220050000031
wherein P isj，Pj-1And PkRepresenting the average load at times j, j-1 and k, respectively,
Figure BDA0002844220050000032
represents the maximum value of the average load difference between any pair of time points j and k satisfying i-n +1 ≦ j, and k ≦ i, and the numerator in the above formula represents the average negative of any two consecutive time points from j ═ i to j ═ i-n +1Sum of absolute values of the charge difference, VHF(P,n)Representing an n-day cross filter line index based on the sequence P, taking the parameter n as the number of days in a month (typically 28 days) in view of the load fluctuation periodicity, i.e. the load trend with the time span of months.
As a preferable technical means: in step 2), the calculation formula of the zero-lag iso-moving average line index zlacd is as follows:
Figure BDA0002844220050000033
Figure BDA0002844220050000034
DIF(P,(p,q))＝ZLMA(P,p)-ZLMA(P,q)
Figure BDA0002844220050000035
wherein, PiEMA representing the average load at time i(P,n)Representing an exponential moving average line of n days, EMA, based on the average load sequence P(EMA(P,n),n)Is represented by EMA(p,n)Sequence-based n-day exponential moving average, ZLMA(P,n)Representing the n-day zero lag moving average. Because p < q, ZLMA(,P)pRepresenting the fast zero-lag moving average line, ZLMA(P,q)Representing the slow zero-lag moving average line, ZLACD(P,(p,q,β))Representing fast-slow based zero lag line difference sequence DIF(P,(p,q))The beta day index moving average line of (1) is the index of the zero lag dissimilarity moving average line.
As a preferable technical means: in view of the load fluctuation periodicity, the parameters p-14, q-28, and β -9 are selected.
As a preferable technical means: in step 5), the calculation formula of the brining line index BOLL is as follows:
Figure BDA0002844220050000041
Figure BDA0002844220050000042
Figure BDA0002844220050000043
wherein the content of the first and second substances,
Figure BDA0002844220050000044
represents the first n of the ith day2The standard deviation of the data for the sequence of days P,
Figure BDA0002844220050000045
represents n based on the sequence P1Daily least squares moving average, BOLLUPBeing upper track, BOLLDNFor the lower trajectory, the band range can be controlled by alpha, and when alpha is larger, the better the Boolean line is to the data containment, the less easy it is to give a warning signal.
As a preferable technical means: in the step 3), selecting the greater value of the VHF average value and the 95% quantile of the double cross filtering line index as the threshold value of the VHF index; the zero-lag dissimilarity moving average line index ZLMACD threshold is selected to be outside three times of standard deviation of the mean value, and the quantile with the absolute value not less than 2.5% and the quantile with the absolute value of 97.5% are used as the upper threshold and the lower threshold of the ZLMACD index, and when the absolute value is higher than the upper threshold or lower than the lower threshold, the index dissimilarity data segment is considered.
As a preferable technical means: in step 6), the abnormal data section obtained by the forest line index BOLL, the abnormal data section obtained by the cross filtering line index VHF and the zero lag dissimilarity moving average line index ZLMACD are compared, and when the differences exist, the cross filtering line index VHF, the zero lag dissimilarity moving average line index ZLMACD and the forest line index BOLL are corrected.
Has the advantages that: the technical scheme is characterized in that the electricity load sequence is characterized by cross filter lines (VHF), zero-lag dissimilarity moving average lines (ZLMACD) and a Boolean line (BOLL) index, specific scenes that index parameters meet a dissimilarity analysis task are adaptively set, a reasonable threshold is set according to an index probability distribution diagram in the same industry, the qualitative mode exceeding the index threshold is dissimilarity, the load curve characteristic is effectively described, the effective grabbing of the dissimilarity phenomenon is realized, and the dissimilarity analysis result is ensured to have certain interpretability. The remarkable abnormal change of the electricity utilization data can be accurately and effectively screened out; and the detection of power utilization mutation is captured by the aid of the auxiliary forest line indexes, so that capture work of abnormal movement is realized, and the effectiveness of abnormal movement analysis is further ensured.
Drawings
FIG. 1 is a flow chart of the present invention.
Fig. 2 is a VHF, zmacd indicator profile for all users of the industry of the present invention.
FIG. 3 is a graph showing the results of transaction analysis according to the present invention.
FIG. 4 is a graph showing the results of transaction analysis according to the present invention.
Detailed Description
The technical scheme of the invention is further explained in detail by combining the drawings in the specification.
As shown in fig. 1, the present invention comprises the steps of:
s1, acquiring the electricity consumption data of the power users, calculating the average load of each user, and performing data completion and standardization on the average load data;
s2, calculating a cross filter line index VHF and a zero lag dissimilarity movement average line index ZLMACD based on the average load;
and recording the average load sequence P of a user, and calculating a technical index aiming at P.
The calculation formula of the cross filter line index VHF is as follows:
Figure BDA0002844220050000051
wherein P isj，Pj-1And PkRepresenting the average load at times j, j-1 and k, respectively,
Figure BDA0002844220050000052
represents the maximum value of the average load difference of any pair of time points j and k satisfying i-n +1 ≦ j, k ≦ i, and the numerator in the above formula represents the sum of the absolute values of the average load differences of any two consecutive time points from j ═ i to j ═ i-n +1, VHF(P,n)Representing an n-day cross filter line index based on the sequence P, taking the parameter n as the number of days in a month (typically 28 days) in view of the load fluctuation periodicity, i.e. the load trend with the time span of months.
Secondly, the calculation formula of the zero-lag dissimilarity moving average line index ZLMACD is as follows:
Figure BDA0002844220050000061
Figure BDA0002844220050000062
DIF(P,(p,q))＝ZLMA(P,p)-ZLMA(P,q)
Figure BDA0002844220050000063
wherein, PiEMA representing the average load at time i(P,n)Representing an exponential moving average line of n days, EMA, based on the average load sequence P(EMA(P,n),n)Is represented by EMA(p,n)Sequence-based n-day exponential moving average, ZLMA(P,n)Representing the n-day zero lag moving average. Because p < q, ZLMA(,P)pRepresenting the fast zero-lag moving average line, ZLMA(P,q)Representing the slow zero-lag moving average line, ZLACD(P,(p,q,β))Representing fast-slow based zero lag line difference sequence DIF(P,(p,q))The beta day index moving average line of (1) is the index of the zero lag dissimilarity moving average line. In view of the load fluctuation periodicity, the parameters p-14, q-28, and β -9 are selected herein.
S3, according to the index distribution condition of the industry, counting the frequency distribution of cross filter line index VHF and zero lag dissimilarity movement average line index ZLMACD index of the same industry; calculating the threshold values of the corresponding cross filter line index VHF and the zero lag dissimilarity movement average line index ZLMACD, and determining an index dissimilarity data section when the cross filter line index VHF and the zero lag dissimilarity movement average line index ZLMACD exceed the threshold values simultaneously;
as shown in fig. 2, the frequency distribution graph is a frequency distribution graph for counting VHF and zlacd indexes in the same industry. As can be seen from fig. 2, VHF shows tail distribution, and the zlacd indicator approximately follows normal distribution, so the larger value of the double VHF mean and the 95% quantile is selected as the threshold of the VHF indicator; the ZLMACD threshold is selected to be out of three standard deviations of the mean value, and the absolute value is not less than 2.5% quantile and 97.5% quantile. Based on the results of the VHF and zlacd indicators determination, if both exceed the threshold at the same time, it is considered as a transaction. The forest line index is a non-trend index, so that abnormal movement can be screened independently by selecting reasonable parameter values.
S4 calculating transaction data segment
Figure BDA0002844220050000071
Value of, wherein rabsThe absolute value of the difference value r of the synchronous ratio of the data of 30 days before and after the transaction data section and the data of the previous yearrelRepresenting the relative value of the difference value of the synchronous ratio of the data of 30 days before and after the transaction data segment and the data of the previous year according to the same industry
Figure BDA0002844220050000072
Determining a threshold value through the frequency distribution of the values, eliminating periodic factors through the threshold value, and re-determining the power consumption abnormal data section;
s5, calculating a Boolean line index BOLL based on the average load, determining an upper track and a lower track, and considering the Boolean line index BOLL as an index transaction data segment when the Boolean line index BOLL exceeds the upper track or is lower than the lower track; the detection of power utilization mutation is captured by using a Boolean line index BOLL, and the capture work of abnormal motion is realized;
the calculation formula of the brink line index BOLL is as follows:
Figure BDA0002844220050000073
Figure BDA0002844220050000074
Figure BDA0002844220050000075
wherein the content of the first and second substances,
Figure BDA0002844220050000076
represents the first n of the ith day2The standard deviation of the data for the sequence of days P,
Figure BDA0002844220050000077
represents n based on the sequence P1Daily least squares moving average, BOLLUPBeing upper track, BOLLDNFor the lower trajectory, the band range can be controlled by alpha, and when alpha is larger, the better the Boolean line is to the data containment, the less easy it is to give a warning signal.
And S6, integrating the steps S4 and S5 to obtain the final index transaction data segment and outputting the final index transaction data segment.
In order to improve the accuracy of analysis, the abnormal data section obtained by the Boolean line index BOLL, the abnormal data section obtained by the cross filtering line index VHF and the zero lag dissimilarity moving average line index ZLMACD are compared, and when the differences exist, the cross filtering line index VHF, the zero lag dissimilarity moving average line index ZLMACD and the Boolean line index BOLL are corrected.
When the cross filtering line index VHF and the zero lag dissimilarity moving average line index ZLMACD of a certain data segment both exceed the threshold value and pass through
Figure BDA0002844220050000081
It is determined that the data segment is to be treated as a transaction data segment, as a non-periodic factor. And outputting and displaying the abnormal change result, wherein the abnormal change is the abnormal change marked after the VHF and the MACD are abnormal simultaneously and periodic factors are eliminated, as shown in figures 3 and 4.
The method for the abnormal-action screening process can accurately and effectively screen out the obvious abnormal change of the electricity utilization data. The abnormal motion capture work is realized by assisting the detection of the power utilization mutation captured by the forest line index, and the effectiveness of the proposed abnormal motion analysis method based on the financial technical index is verified to a certain extent by an experimental result.
The method for analyzing power consumption fluctuation based on financial technical indexes shown in fig. 1 is a specific embodiment of the present invention, has shown the substantial features and progress of the present invention, and can make equivalent modifications in shape, structure and the like according to the practical use requirements and under the teaching of the present invention, all of which are within the protection scope of the present solution.

Claims (7)

1. A power consumption transaction analysis method based on financial technical indexes is characterized by comprising the following steps:
1) acquiring power consumption data of power consumers, calculating the average load of each consumer, and performing data completion and standardization on the average load data;
2) based on the average load, calculating a cross filter line index VHF and a zero lag dissimilarity movement average line index ZLACD;
3) according to the index distribution condition of the industry, counting the frequency distribution of a cross filter line index VHF and a zero lag dissimilarity movement average line index ZLMACD index in the same industry; calculating the threshold values of the corresponding cross filter line index VHF and the zero lag dissimilarity movement average line index ZLMACD, and determining an index dissimilarity data section when the cross filter line index VHF and the zero lag dissimilarity movement average line index ZLMACD exceed the threshold values simultaneously;
4) calculating transaction data segments
Figure FDA0002844220040000011
Value of, wherein rabsThe absolute value of the difference value r of the synchronous ratio of the data of 30 days before and after the transaction data section and the data of the previous yearrelRepresenting the relative value of the difference value of the synchronous ratio of the data of 30 days before and after the transaction data segment and the data of the previous year according to the same industry
Figure FDA0002844220040000012
Determining a threshold value through the frequency distribution of the values, eliminating periodic factors through the threshold value, and re-determining the power consumption abnormal data section;
5) calculating a Booth line index BOLL based on the average load, determining an upper track and a lower track, and considering the Booth line index BOLL as an index transaction data section when the Booth line index BOLL exceeds the upper track or is lower than the lower track; the detection of power utilization mutation is captured by using a Boolean line index BOLL, and the capture work of abnormal motion is realized;
6) and (5) integrating the steps 4) and 5) to obtain a final index transaction data segment, and outputting the final index transaction data segment.
2. The power consumption transaction analysis method based on financial technical indexes as claimed in claim 1, wherein: in step 2), the cross filter line index VHF is calculated by the formula:
Figure FDA0002844220040000021
wherein P isj，Pj-1And PkRepresenting the average load at times j, j-1 and k, respectively,
Figure FDA0002844220040000022
represents the maximum value of the average load difference of any pair of time points j and k satisfying i-n +1 ≦ j, k ≦ i, and the numerator in the above formula represents the sum of the absolute values of the average load differences of any two consecutive time points from j ═ i to j ═ i-n +1, VHF(P,n)Representing an n-day cross filter line index based on the sequence P, taking the parameter n as the number of days in a month, i.e. the load trend over a time span of months, in view of the load fluctuation periodicity.
3. The power consumption transaction analysis method based on financial technical indexes as claimed in claim 2, wherein: in step 2), the calculation formula of the zero-lag iso-moving average line index zlacd is as follows:
Figure FDA0002844220040000023
Figure FDA0002844220040000024
DIF(P,(p,q))＝ZLMA(P,p)-ZLMA(P,q)
Figure FDA0002844220040000025
wherein, PiEMA representing the average load at time i(P,n)Representing an exponential moving average line of n days, EMA, based on the average load sequence P(EMA(P,n),n)Is represented by EMA(p,n)Sequence-based n-day exponential moving average, ZLMA(P,n)Represents the zero lag moving average line of n days; because p < q, ZLMA(,P)pRepresenting the fast zero-lag moving average line, ZLMA(P,q)Representing the slow zero-lag moving average line, ZLACD(P,(p,q,β))Representing fast-slow based zero lag line difference sequence DIF(P,(p,q))The beta day index moving average line of (1) is the index of the zero lag dissimilarity moving average line.
4. The power consumption transaction analysis method based on financial technical indexes as claimed in claim 3, wherein: in view of the load fluctuation periodicity, the parameters p-14, q-28, and β -9 are selected.
5. The power consumption transaction analysis method based on financial technical indexes as claimed in claim 4, wherein: in step 5), the calculation formula of the brining line index BOLL is as follows:
Figure FDA0002844220040000031
Figure FDA0002844220040000032
Figure FDA0002844220040000033
wherein the content of the first and second substances,
Figure FDA0002844220040000034
represents the first n of the ith day2The standard deviation of the data for the sequence of days P,
Figure FDA0002844220040000035
represents n based on the sequence P1Daily least squares moving average, BOLLUPBeing upper track, BOLLDNFor the lower trajectory, the band range can be controlled by alpha, and when alpha is larger, the better the Boolean line is to the data containment, the less easy it is to give a warning signal.
6. The power consumption transaction analysis method based on financial technical indexes as claimed in claim 5, wherein: in the step 3), selecting the greater value of the VHF average value and the 95% quantile of the double cross filtering line index as the threshold value of the VHF index; the zero-lag dissimilarity moving average line index ZLMACD threshold is selected to be outside three times of standard deviation of the mean value, and the quantile with the absolute value not less than 2.5% and the quantile with the absolute value of 97.5% are used as the upper threshold and the lower threshold of the ZLMACD index, and when the absolute value is higher than the upper threshold or lower than the lower threshold, the index dissimilarity data segment is considered.
7. The power consumption transaction analysis method based on financial technical indexes as claimed in claim 1, wherein: in step 6), the abnormal data section obtained by the forest line index BOLL, the abnormal data section obtained by the cross filtering line index VHF and the zero lag dissimilarity moving average line index ZLMACD are compared, and when the differences exist, the cross filtering line index VHF, the zero lag dissimilarity moving average line index ZLMACD and the forest line index BOLL are corrected.
CN202011503212.3A 2020-12-17 2020-12-17 Power consumption transaction analysis method based on financial technical indexes Pending CN112597440A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011503212.3A CN112597440A (en) 2020-12-17 2020-12-17 Power consumption transaction analysis method based on financial technical indexes

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011503212.3A CN112597440A (en) 2020-12-17 2020-12-17 Power consumption transaction analysis method based on financial technical indexes

Publications (1)

Publication Number Publication Date
CN112597440A true CN112597440A (en) 2021-04-02

Family

ID=75199222

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011503212.3A Pending CN112597440A (en) 2020-12-17 2020-12-17 Power consumption transaction analysis method based on financial technical indexes

Country Status (1)

Country Link
CN (1) CN112597440A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113659623A (en) * 2021-08-17 2021-11-16 广西大学 Wind storage combined system optimization method and system based on brining line theory

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20170056985A (en) * 2015-11-16 2017-05-24 (주)에이치앤와이증권투자연구소 Calculation system for stock score and the method thereof
CN107292742A (en) * 2017-05-25 2017-10-24 武汉楚鼎信息技术有限公司 A kind of system and implementation method invested in stock according to any indicator combination
CN109636949A (en) * 2017-10-09 2019-04-16 贝尔直升机德事隆公司 The system and method for being suitable for trend-monitoring for element condition indicator data
CN110070204A (en) * 2019-01-04 2019-07-30 国网浙江省电力有限公司 A kind of customer charge trend forecasting method based on Moving Average
CN111027742A (en) * 2019-10-31 2020-04-17 北京币世界网络科技有限公司 Market situation prediction method and system based on data indexes

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20170056985A (en) * 2015-11-16 2017-05-24 (주)에이치앤와이증권투자연구소 Calculation system for stock score and the method thereof
CN107292742A (en) * 2017-05-25 2017-10-24 武汉楚鼎信息技术有限公司 A kind of system and implementation method invested in stock according to any indicator combination
CN109636949A (en) * 2017-10-09 2019-04-16 贝尔直升机德事隆公司 The system and method for being suitable for trend-monitoring for element condition indicator data
CN110070204A (en) * 2019-01-04 2019-07-30 国网浙江省电力有限公司 A kind of customer charge trend forecasting method based on Moving Average
CN111027742A (en) * 2019-10-31 2020-04-17 北京币世界网络科技有限公司 Market situation prediction method and system based on data indexes

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李宁;王伟峰;蔡慧;汪伟;王颖;: "基于电量离群点挖掘的窃电辨识方法研究", 中国计量大学学报, no. 03, 15 September 2018 (2018-09-15) *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113659623A (en) * 2021-08-17 2021-11-16 广西大学 Wind storage combined system optimization method and system based on brining line theory
CN113659623B (en) * 2021-08-17 2023-09-26 广西大学 Optimization method and system of wind-storage combined system based on Boolean line theory

Similar Documents

Publication Publication Date Title
Guan et al. Very short-term load forecasting: wavelet neural networks with data pre-filtering
CN108763729B (en) Process industry electromechanical system coupling state evaluation method based on network structure entropy
Cody et al. Decision tree learning for fraud detection in consumer energy consumption
CN110097297A (en) A kind of various dimensions stealing situation Intellisense method, system, equipment and medium
CN110135612A (en) The monitoring of material supply quotient&#39;s production capacity and abnormity early warning method based on analysis of electric power consumption
CN109978230B (en) Intelligent power sale amount prediction method based on deep convolutional neural network
Guerrieri et al. Can macro variables used in stress testing forecast the performance of banks?
CN109784388A (en) Stealing user identification method and device
CN103366091B (en) Based on the abnormal tax return data detection method of multilevel threshold exponent-weighted average
CN111241208B (en) Abnormality monitoring method and device for periodic time sequence data
CN111275255A (en) Construction method of concrete dam deformation monitoring and forecasting model
CN106649755A (en) Threshold self-adaption setting abnormity detection method for multi-dimensional real-time power transformation device data
CN108921409B (en) Voltage sag severity grade determination method
CN106682159A (en) Threshold configuration method
CN114202103A (en) Machine learning-based holiday scenic spot passenger flow prediction method
CN108898248B (en) Power load influence factor quantitative analysis method, device, equipment and medium
CN110991985A (en) Project progress data processing method
CN112597440A (en) Power consumption transaction analysis method based on financial technical indexes
CN107871212A (en) A kind of Analysis of Engineering Construction Cost method based on bill of quantities data and data model analysis technology
CN113902062A (en) Transformer area line loss abnormal reason analysis method and device based on big data
CN110059126B (en) LKJ abnormal value data-based complex correlation network analysis method and system
CN112785057B (en) Method, device, equipment and storage medium for predicting quantity of parts based on exponential smoothing
CN103761449A (en) Criminal propensity and risk degree quantifying method and system based on AHP
CN110414776B (en) Quick response analysis system for power utilization characteristics of different industries
CN109949101B (en) Big data concept-based cigarette material cost analysis method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination