CN111027830A - Power supply reliability index grading prediction method based on machine learning - Google Patents

Power supply reliability index grading prediction method based on machine learning Download PDF

Info

Publication number
CN111027830A
CN111027830A CN201911183768.6A CN201911183768A CN111027830A CN 111027830 A CN111027830 A CN 111027830A CN 201911183768 A CN201911183768 A CN 201911183768A CN 111027830 A CN111027830 A CN 111027830A
Authority
CN
China
Prior art keywords
machine learning
current
value
voltage
prediction
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.)
Granted
Application number
CN201911183768.6A
Other languages
Chinese (zh)
Other versions
CN111027830B (en
Inventor
谈军
赵爱华
朱军伟
唐亮
梁晓伟
周宇
吕朋朋
隋仕伟
何义赟
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to CN201911183768.6A priority Critical patent/CN111027830B/en
Publication of CN111027830A publication Critical patent/CN111027830A/en
Application granted granted Critical
Publication of CN111027830B publication Critical patent/CN111027830B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • 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
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Software Systems (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention belongs to a prediction method, and particularly relates to a power supply reliability index grading prediction method based on machine learning. A power supply reliability index grading prediction method based on machine learning is characterized in that voltage and current prediction at the next moment is carried out by using machine learning prediction and a preset formula respectively, the difference value of the two prediction values is smaller than a set threshold value, a machine prediction result is output, and otherwise, a preset formula prediction value is output. The invention has the following remarkable effects: (1) through machine learning and prediction, automation and intellectualization of power grid prediction are realized, and efficiency and accuracy are obviously improved; (2) establishing a reliability index suitable for machine learning, and providing an operation step for machine learning of power grid prediction; (3) the method can be carried out aiming at any power supply facility, and has high flexibility and wide applicability.

Description

Power supply reliability index grading prediction method based on machine learning
Technical Field
The invention belongs to a prediction method, and particularly relates to a power supply reliability index grading prediction method based on machine learning.
Background
Along with the rapid development of national economy and energy industry, the demand of power users on electric energy is more and more large, and for power supply enterprises, the prediction of the power consumption of the users is particularly important, so that the prediction of the power consumption can help the power company to better know and service the users, and make a corresponding plan for the development of a power grid, specifically can carry out the dispatching of distribution electric quantity, and also can help the making of government-related policies, such as the construction planning layout of a power system. With the lapse of time and the continuous development of economy, the degree of dependence on electric power in China is expected to be higher and higher.
The power utilization behaviors of users have differences, even if the users in the same industry have the differences, the differences become more and more obvious as time goes on, and most of the existing power utilization predictions are subjected to mode recognition through industry characteristics and cannot well mine the information of the users. The power utilization characteristics of the users are not only related to relevant factors of the industry, but also related to other social and economic factors, the power utilization characteristics of the users in different areas are similar to the power utilization characteristics of different industries in change trend, the power utilization characteristics of the users are diversified, and the method for predicting the relevant power quantity forms a challenge. With the development of science and technology, especially the continuous progress of intelligent technology, various intelligent power grid technologies emerge endlessly, and the construction aspect of the power grid is also greatly improved, but no method for predicting the power supply reliability based on machine learning exists in the prior art.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a power supply reliability index grading prediction method based on machine learning.
The invention is realized by the following steps: a power supply reliability index grading prediction method based on machine learning is characterized in that voltage and current prediction at the next moment is carried out by using machine learning prediction and a preset formula respectively, the difference value of the two prediction values is smaller than a set threshold value, a machine prediction result is output, and otherwise, a preset formula prediction value is output.
The method for power supply reliability index hierarchical prediction based on machine learning is described above, wherein the machine learning uses a graph theory reasoning algorithm or a laplacian support vector machine method.
The method for predicting the power supply reliability index grades based on the machine learning comprises the following steps:
step one, sampling;
the parameters to be sampled include: voltage V, current I, frequency F, environment temperature T, environment humidity K, and sampling interval S;
in the present application, the sampling results obtained by different subsamplings are denoted by i, i.e. Vi、Ii、Fi、Ti、Fi、Ti、KiThe result of the same sampling is shown,
step two, machine learning training;
based on the data sampled in the step one, the machine is learned and trained by adopting a graph theory reasoning algorithm or a Laplace support vector machine method,
the trained machine continuously outputs the predicted next time voltage and current,
step three, calculating a reference;
the calculation is not carried out during the first sampling, the calculation is carried out by using the following formula from the second sampling, and M is set as the total sampling times to the current moment; the voltage and current at the next moment are calculated using the following equations,
Figure BDA0002291929260000031
Figure BDA0002291929260000032
Figure BDA0002291929260000033
Figure BDA0002291929260000034
the voltage and current at the next moment calculated in this step are reference values,
step four, judging the prediction accuracy;
and (4) solving a difference value by using the voltage predicted by the machine in the step two and the voltage calculated in the step three, wherein if the difference value is less than or equal to a threshold value, the predicted voltage value after machine learning is judged to meet the requirement, and the voltage value at the next moment predicted in the step two is output, otherwise, the predicted voltage value after machine learning is judged to not meet the requirement, and the voltage value at the next moment calculated in the step three is output.
And (4) solving a difference value by using the current predicted by the machine in the step two and the current calculated in the step three, wherein if the difference value is less than or equal to a threshold value, the predicted current value after machine learning is judged to meet the requirement, and the current value at the next moment predicted in the step two is output, otherwise, the predicted current value after machine learning is judged to not meet the requirement, and the current value at the next moment calculated in the step three is output.
The power supply reliability index grading prediction method based on machine learning is characterized in that the value range of S is 10 microseconds-20 milliseconds.
The power supply reliability index grading prediction method based on machine learning is characterized in that the threshold value of the voltage is
Figure BDA0002291929260000035
1% of the total.
The power supply reliability index grading prediction method based on machine learning is characterized in that the threshold value of the current is
Figure BDA0002291929260000041
1% of the total.
The invention has the following remarkable effects: (1) through machine learning and prediction, automation and intellectualization of power grid prediction are realized, and efficiency and accuracy are obviously improved; (2) establishing a reliability index suitable for machine learning, and providing an operation step for machine learning of power grid prediction; (3) the method can be carried out aiming at any power supply facility, and has high flexibility and wide applicability.
Detailed Description
A power supply reliability index grading prediction method based on machine learning comprises the following steps:
step one, sampling;
sampling in a reliable environment, the parameters to be sampled include: voltage V, current I, frequency F, environment temperature T, environment humidity K, and sampling interval S;
the reliable environment refers to a stable environment in which the system to be tested is located in both the sampling phase and the prediction phase.
The voltage V, the current I, the frequency F, the environment temperature T and the environment humidity K are obtained by corresponding testing devices, and the dimensions are international unit dimensions, such as a voltage meter for voltage and an ammeter for current.
The sampling interval refers to a time interval between adjacent samples, and the values of different power systems S are different, and the range of the sampling interval is 10 microseconds to 20 milliseconds.
In the present application, the sampling results obtained by different subsamplings are denoted by i, i.e. Vi、Ii、Fi、Ti、Fi、Ti、KiRepresenting the same sampling result.
Step two, machine learning training;
and (3) learning and training the machine by adopting a graph theory reasoning algorithm or a Laplace support vector machine method based on the data sampled in the step one.
The trained machine continuously outputs the predicted next time voltages and currents.
Step three, calculating a reference;
the calculation is not carried out during the first sampling, the calculation is carried out by using the following formula from the second sampling, and M is set as the total sampling times to the current moment; the voltage and current at the next moment are calculated using the following equations,
Figure BDA0002291929260000051
Figure BDA0002291929260000052
Figure BDA0002291929260000053
Figure BDA0002291929260000054
the voltage and current at the next time calculated in this step are reference values.
Step four, judging the prediction accuracy;
calculating the difference between the voltage predicted by the second machine and the voltage calculated by the third machine, wherein the difference is less than or equal to
Figure BDA0002291929260000055
And 1%, judging that the predicted voltage value after machine learning meets the requirement, and outputting the voltage value at the next moment predicted in the step two, otherwise, judging that the predicted voltage value after machine learning does not meet the requirement, and outputting the voltage value at the next moment obtained by calculation in the step three.
Calculating the difference between the predicted current in the second step and the current calculated in the third step, wherein the difference is less than or equal to
Figure BDA0002291929260000056
And 1% of the current value, judging that the predicted current value after machine learning meets the requirement, and outputting the current value at the next moment predicted in the step two, otherwise, judging that the predicted current value after machine learning does not meet the requirement, and outputting the current value at the next moment calculated in the step three.

Claims (6)

1. A power supply reliability index grading prediction method based on machine learning is characterized in that: and (3) predicting the voltage and the current at the next moment by using a machine learning prediction formula and a preset formula respectively, outputting a machine prediction result when the difference value of the two predicted values is smaller than a set threshold value, and otherwise, outputting a preset formula prediction value.
2. The machine learning-based power supply reliability index grading prediction method according to claim 1, characterized in that: machine learning uses either graph theory inference algorithms or laplacian support vector machine methods.
3. The machine learning-based power supply reliability index grading prediction method according to claim 2, characterized in that: the method comprises the following steps:
step one, sampling;
the parameters to be sampled include: voltage V, current I, frequency F, environment temperature T, environment humidity K, and sampling interval S;
in the present application, the sampling results obtained by different subsamplings are denoted by i, i.e. Vi、Ii、Fi、Ti、Fi、Ti、KiThe result of the same sampling is shown,
step two, machine learning training;
based on the data sampled in the step one, the machine is learned and trained by adopting a graph theory reasoning algorithm or a Laplace support vector machine method,
the trained machine continuously outputs the predicted next time voltage and current,
step three, calculating a reference;
the calculation is not carried out during the first sampling, the calculation is carried out by using the following formula from the second sampling, and M is set as the total sampling times to the current moment; the voltage and current at the next moment are calculated using the following equations,
Figure FDA0002291929250000021
Figure FDA0002291929250000022
Figure FDA0002291929250000023
Figure FDA0002291929250000024
the voltage and current at the next moment calculated in this step are reference values,
step four, judging the prediction accuracy;
calculating the difference value between the voltage predicted by the machine in the step two and the voltage calculated in the step three, if the difference value is less than or equal to the threshold value, judging that the predicted voltage value after machine learning meets the requirement, outputting the voltage value at the next moment predicted in the step two, otherwise, judging that the predicted voltage value after machine learning does not meet the requirement, outputting the voltage value at the next moment calculated in the step three,
and (4) solving a difference value by using the current predicted by the machine in the step two and the current calculated in the step three, wherein if the difference value is less than or equal to a threshold value, the predicted current value after machine learning is judged to meet the requirement, and the current value at the next moment predicted in the step two is output, otherwise, the predicted current value after machine learning is judged to not meet the requirement, and the current value at the next moment calculated in the step three is output.
4. The machine learning-based power supply reliability index grading prediction method according to claim 3, characterized in that: the value range of S is 10 microseconds to 20 milliseconds.
5. The machine learning-based power supply reliability index grading prediction method according to claim 4, characterized in that: the threshold value of the voltage is
Figure FDA0002291929250000025
1% of the total.
6. The machine learning-based power supply reliability index grading prediction method according to claim 4, characterized in that: the threshold value of the current is
Figure FDA0002291929250000031
1% of the total.
CN201911183768.6A 2019-11-27 2019-11-27 Power supply reliability index grading prediction method based on machine learning Active CN111027830B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911183768.6A CN111027830B (en) 2019-11-27 2019-11-27 Power supply reliability index grading prediction method based on machine learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911183768.6A CN111027830B (en) 2019-11-27 2019-11-27 Power supply reliability index grading prediction method based on machine learning

Publications (2)

Publication Number Publication Date
CN111027830A true CN111027830A (en) 2020-04-17
CN111027830B CN111027830B (en) 2023-04-18

Family

ID=70207214

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911183768.6A Active CN111027830B (en) 2019-11-27 2019-11-27 Power supply reliability index grading prediction method based on machine learning

Country Status (1)

Country Link
CN (1) CN111027830B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103617573A (en) * 2013-12-13 2014-03-05 国家电网公司 Short-term tendency forecasting method for power quality index
CN105730270A (en) * 2016-02-03 2016-07-06 惠州市蓝微新源技术有限公司 Method and system for performing safety prediction according to change of state variables of battery and external environment
CN108521173A (en) * 2018-05-09 2018-09-11 北京国网普瑞特高压输电技术有限公司 A kind of super extra-high voltage series compensation device status monitoring integrated platform based on IEC61850
KR20180123951A (en) * 2017-05-10 2018-11-20 주식회사 알스피릿 Device and method for diagnosing/predicting status of solar cell or solar cell array on real time based on machine learing
CN108964023A (en) * 2018-06-29 2018-12-07 国网上海市电力公司 A kind of busbar voltage situation short term prediction method and system for power grid
CN110165259A (en) * 2019-05-16 2019-08-23 苏州纳尔森能源科技有限公司 Monitoring method and device, the system of the operating status of battery

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103617573A (en) * 2013-12-13 2014-03-05 国家电网公司 Short-term tendency forecasting method for power quality index
CN105730270A (en) * 2016-02-03 2016-07-06 惠州市蓝微新源技术有限公司 Method and system for performing safety prediction according to change of state variables of battery and external environment
KR20180123951A (en) * 2017-05-10 2018-11-20 주식회사 알스피릿 Device and method for diagnosing/predicting status of solar cell or solar cell array on real time based on machine learing
CN108521173A (en) * 2018-05-09 2018-09-11 北京国网普瑞特高压输电技术有限公司 A kind of super extra-high voltage series compensation device status monitoring integrated platform based on IEC61850
CN108964023A (en) * 2018-06-29 2018-12-07 国网上海市电力公司 A kind of busbar voltage situation short term prediction method and system for power grid
CN110165259A (en) * 2019-05-16 2019-08-23 苏州纳尔森能源科技有限公司 Monitoring method and device, the system of the operating status of battery

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
JAKUB JURASZ等: "The impact of complementarity on power supply reliability of small scale hybrid energy systems", 《ENERGY》 *
张洋 等: "基于LSTM神经网络的短期高压负荷电流预测方法", 《计算机科学》 *

Also Published As

Publication number Publication date
CN111027830B (en) 2023-04-18

Similar Documents

Publication Publication Date Title
Zheng et al. A novel equivalent model of active distribution networks based on LSTM
Franco et al. Optimal conductor size selection and reconductoring in radial distribution systems using a mixed-integer LP approach
CN103413188B (en) A kind of monthly industrial power predicating method based on industry Business Process System
CN112149873B (en) Low-voltage station line loss reasonable interval prediction method based on deep learning
Sun et al. Charging load forecasting of electric vehicle charging station based on support vector regression
Fathy et al. Static transmission expansion planning for realistic networks in Egypt
CN105740975A (en) Data association relationship-based equipment defect assessment and prediction method
KR102029031B1 (en) Apparatus and method for estimating power loss of distribution line
CN109428327B (en) Power grid key branch and leading stable mode identification method and system based on response
Shin et al. Spatiotemporal load-analysis model for electric power distribution facilities using consumer meter-reading data
CN110837915A (en) Low-voltage load point prediction and probability prediction method for power system based on hybrid integrated deep learning
Guder et al. Data mining framework for power quality event characterization of iron and steel plants
CN101206727B (en) Data processing apparatus, data processing method
CN111539840A (en) Electricity stealing detection method and system fusing clustering and density estimation
CN112508254B (en) Method for determining investment prediction data of transformer substation engineering project
CN109784362A (en) A kind of DGA shortage of data value interpolating method based on iteration KNN and interpolation priority
CN111027830B (en) Power supply reliability index grading prediction method based on machine learning
CN109376990B (en) Method and system for determining critical removal time of power system based on Simese network model
Wang et al. Cloud computing and extreme learning machine for a distributed energy consumption forecasting in equipment-manufacturing enterprises
CN108123436B (en) Voltage out-of-limit prediction model based on principal component analysis and multiple regression algorithm
Hailu et al. Application of Data-Driven Tuned Fuzzy Inference System for Static Equivalencing of Power Systems with High Penetration of Renewable Energy
CN108009686B (en) Photovoltaic power generation power prediction method, device and system
Frimpong et al. A model for predicting unregulated energy usage
Moradzadeh et al. Image processing-based data integrity attack detection in dynamic line rating forecasting applications
Venayagamoorthy Computational approaches for bad data handling in power system synchrophasor networks

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 730050 No.89, Qilihe North Street, Qilihe district, Lanzhou City, Gansu Province

Applicant after: Zhao Yongsheng

Address before: 230022 State Grid Anhui Electric Power Co., Ltd., No. 9 Huangshan Road, Hefei, Anhui

Applicant before: Zhao Yongsheng

GR01 Patent grant
GR01 Patent grant