CN112003308A - Platform area load balance control method based on genetic algorithm - Google Patents

Platform area load balance control method based on genetic algorithm Download PDF

Info

Publication number
CN112003308A
CN112003308A CN202010854641.9A CN202010854641A CN112003308A CN 112003308 A CN112003308 A CN 112003308A CN 202010854641 A CN202010854641 A CN 202010854641A CN 112003308 A CN112003308 A CN 112003308A
Authority
CN
China
Prior art keywords
phase
phase current
genetic algorithm
unbalance
current
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.)
Withdrawn
Application number
CN202010854641.9A
Other languages
Chinese (zh)
Inventor
李峰
陈健
席文兵
汪洋
王东阳
石旭初
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.)
HuaiAn Power Supply Co of State Grid Jiangsu Electric Power Co Ltd
Original Assignee
HuaiAn Power Supply Co of State Grid Jiangsu 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 HuaiAn Power Supply Co of State Grid Jiangsu Electric Power Co Ltd filed Critical HuaiAn Power Supply Co of State Grid Jiangsu Electric Power Co Ltd
Priority to CN202010854641.9A priority Critical patent/CN112003308A/en
Publication of CN112003308A publication Critical patent/CN112003308A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/26—Arrangements for eliminating or reducing asymmetry in polyphase networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • 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
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/50—Arrangements for eliminating or reducing asymmetry in polyphase networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Genetics & Genomics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Physiology (AREA)
  • Power Engineering (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention relates to the technical field of power distribution network control, and discloses a platform load balance control method based on a genetic algorithm, wherein three-phase current data at the head end of a platform area are periodically read, abnormal data are screened out, the unbalance degree and the load rate of the three-phase current are calculated, and if the unbalance degree of the three-phase current is greater than a threshold value and the load rate is greater than the threshold value for n times continuously, a control strategy is formed based on the genetic algorithm, and the method mainly comprises the steps of generating an initial population; evaluating individuals; selecting; crossing; mutation; policy checking, etc. Compared with the prior art, the method adopts the genetic algorithm with stronger searching capability and low dependency on the objective function to carry out nonlinear multi-objective optimization, and achieves better three-phase imbalance treatment effect by the action times as few as possible.

Description

Platform area load balance control method based on genetic algorithm
Technical Field
The invention relates to the technical field of power distribution network control, in particular to a platform region load balance control method based on a genetic algorithm.
Background
The power distribution system is a hub for the connection of a power grid and user power utilization equipment and is an important link of the power grid system, and the comprehensive optimization planning of the working process of the power distribution network is the key point for maintaining the stability of the power grid system, reducing the waste of power grid management resources and improving the power utilization quality of users. The traditional mathematical optimization method and the artificial intelligence algorithm which is continuously developed in recent years are generally adopted to carry out control optimization aiming at multiple problems of the power distribution network, but the current power distribution network control technical field lacks research on distribution area load balance control, and is difficult to accurately grasp the trend of regional power distribution network load change, so that a comprehensive optimization planning scheme of the power distribution network which can effectively implement control on the load change trend and load characteristics in a user low-voltage distribution area power grid is urgently needed to solve the problems of high line loss rate, low voltage qualification rate, low investment fund and the like of the power distribution network.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems in the prior art, the platform load balance control method based on the genetic algorithm is characterized in that three-phase current data at the head end of the platform are periodically read, abnormal data are screened out, the three-phase current unbalance degree and the load rate are calculated, and if the three-phase current unbalance degree is larger than a threshold value and the load rate is larger than the threshold value for n times continuously, a control strategy is formed based on the genetic algorithm.
The technical scheme is as follows: the invention provides a platform region load balance control method based on a genetic algorithm, which comprises the following steps:
step 1) generating an initial population: the population scale is determined according to the number of installed phase change switches, a plurality of switches are distributed to A, B, C three phases according to the inverse relation of three-phase current at the head end of a transformer area, and the larger the current is, the fewer the number of switches in the phase is; and (3) an encoding mode: the condition of a plurality of switch phases is represented by a 3-row matrix, each column represents switch information called genes, and the state of each switch can only be switched among A, B, C three phases;
step 2) individual evaluation: forming a fitness function according to the three-phase current unbalance and all switching action times, and evaluating individuals according to the fitness function;
step 3), selection: selecting by adopting a rotation method, determining the probability of the individuals to be reserved to enter the next generation of genetic operation by adopting the ratio of the practical function value of the ith individual in the population to the sum of the fitness function values of all the individuals in the population, wherein the probability of the individuals to enter the next generation of genetic operation is in direct proportion to the individual fitness function;
step 4), crossing: adopting the point crossing of parents and gems, randomly selecting 1 breakpoint on a chromosome, and mutually exchanging the right sections of the breakpoints so as to form new offspring; in order to not destroy the dependence and mutual exclusion relationship between the genes, the whole vector gene is replaced during the cross operation, and the characteristics of the vector gene are not destroyed;
step 5) mutation: controlling whether the chromosome is mutated or not according to the mutation rate, and randomly selecting genes needing to be mutated when the chromosome needs to be mutated, wherein each gene can be mutated among the genes represented by 3 groups of switch information and represents that the switch phase is switched among A phase, B phase and C phase;
step 6) strategy verification: and after the genetic algorithm gives a control strategy, calculating the unbalance degree of the three-phase current after control, and if the unbalance degree of the three-phase current is larger than the unbalance degree of the three-phase current before control, cancelling the control command.
Further, before the step 1), periodically reading three-phase current data at the head end of the platform area, screening out abnormal data, calculating the unbalance degree and the load rate of the three-phase current, wherein the unbalance degree of the three-phase current is greater than a threshold ibal _ limit and the load rate is greater than a threshold load _ rate _ limit for n times:
and recording three-phase currents corresponding to n times of continuous out-of-limit of the three-phase current unbalance and the load rate as Ia1, Ia2, …, Ian, Ib1, …, Ibn, Ic1, … and Icn respectively.
The data closer to the present moment have higher weights, the three-phase weighted average current is calculated:
Figure BDA0002645975160000021
Figure BDA0002645975160000022
Figure BDA0002645975160000023
note the book
Figure BDA0002645975160000024
Wherein the content of the first and second substances,
Figure BDA0002645975160000025
further, the number of the phase change switches is 9, and the initialization population is as follows:
Figure BDA0002645975160000026
wherein, the load current of each switch is recorded as: i issw＝[i1 i2 i3 i4 i5 i6 i7 i8 i9]The total switch current of each phase is Isw_sum＝Ksw·Isw T。
Further, the fitness function in step 2) is composed of two parts, which are the three-phase current imbalance and the number of switching actions:
Fun＝Cmax-k1·ibal-k2·act_times
where Fun is the fitness function, CmaxIs a large constant, ensures that the fitness function is not negative, k1Is the weight of the unbalance degree of the three-phase current, ibal is the unbalance degree of the three-phase current, k2The action times weight, and act _ times is the action times.
Furthermore, the number of the phase change switches in the step 5) is 10-20, and the variation rate is 0.001-0.1.
Has the advantages that:
the invention adopts the genetic algorithm with stronger searching capability and low target function dependency to carry out nonlinear multi-target optimization, and achieves better three-phase imbalance treatment effect by the action times as few as possible.
Drawings
FIG. 1 is a schematic flow chart of a platform load balance control method based on a genetic algorithm according to the present invention;
fig. 2 is a device structure diagram of the platform load balance control method based on genetic algorithm of the invention.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings, and it should be understood that the embodiments described herein are merely illustrative of the technical solutions of the present invention, and are not intended to limit the present invention.
Referring to the attached figure 1, the platform load balance control method based on the genetic algorithm, provided by the invention, comprises the steps of periodically reading three-phase current data at the head end of a platform, screening abnormal data, calculating the unbalance degree and the load rate of the three-phase current, and forming a control strategy based on the genetic algorithm if the unbalance degree of the three-phase current is greater than a threshold ibal _ limit and the load rate is greater than a threshold load _ rate _ limit for n times:
recording three-phase currents corresponding to n times of continuous out-of-limit three-phase current unbalance and load rate as Ia1, Ia2, …, Ian, Ib1, …, Ibn, Ic1, … and Icn respectively;
the data closer to the present moment have higher weights, the three-phase weighted average current is calculated:
Figure BDA0002645975160000031
Figure BDA0002645975160000032
Figure BDA0002645975160000033
note the book
Figure BDA0002645975160000034
Wherein the content of the first and second substances,
Figure BDA0002645975160000035
the method specifically comprises the following steps:
step 1: generating an initial population;
the population scale is determined according to the number of installed phase change switches:
popsize＝k·N_sw
wherein, popsize is the population size, N _ sw is the number of switches, k is a coefficient, and the default is 10.
The N _ sw switches are distributed to A, B, C three phases according to the inverse proportion relation of three-phase current at the head end of a transformer area, and the larger the current is, the fewer the number of the switches in the phase is.
And (3) an encoding mode: the N _ sw switch phase situation is represented by a 3-row N _ sw column matrix, each column represents a switch information (called gene), [ 100 ]]TIndicating that the switch is in phase A, [ 010 ]]TShowing the switch in phase B, [ 001 ]]TIndicating that the switch is in phase C. The state of each switch can only be switched between A, B, C phases. Taking 9 switches as an example, the initialization population can be represented as:
Figure BDA0002645975160000041
the load current of each switch is noted as: i issw＝[i1 i2 i3 i4 i5 i6 i7 i8 i9]The total switch current of each phase is Isw_sum＝Ksw·Isw T。
Step 2: evaluating individuals;
evaluating individuals according to a fitness function, wherein the fitness function consists of two parts, namely three-phase current unbalance and all switching action times:
Fun＝Cmax-k1·ibal-k2·act_times
where Fun is the fitness function, CmaxIs a large constant, ensures that the fitness function is not negative, k1Is the weight of the unbalance degree of the three-phase current, ibal is the unbalance degree of the three-phase current, k2The action times weight, and act _ times is the action times.
Each control scheme controls a rear switch state matrix K'swTotal switching current of each phase is l'sw_sum＝K'sw·Isw TThen the total current variation of the switch is Δ Isw_sum＝I'sw_sum-I'sw_sumControlling the three-phase current of the head end of the background area to be I'T＝IT+ΔIsw_sumThe unbalance of three-phase current is
Figure BDA0002645975160000042
And step 3: selection (replication);
in the selection operation, the higher the value of the utility function of an individual is, the more the chance to proceed to the next generation operation. And (4) selecting operation by adopting a rotation method, wherein the probability of the individual entering the next generation of genetic operation is in direct proportion to the individual fitness function. Let Σ fiIs equal to the sum of fitness function values of all individuals of the population, fiThen equal to the value of the utility function of the ith individual in the population, then fi/∑fiThe probability that an individual is retained for the next generation of genetic manipulation is determined.
And 4, step 4: crossing;
adopting the point crossing of parents and parents, randomly selecting 1 breakpoint on the chromosome, and mutually exchanging the right segments of the breakpoints so as to form 2 new offspring. In order to not destroy the dependence and mutual exclusion relationship between genes, the whole vector gene is replaced during the cross operation, and the characteristics of the vector gene are not destroyed.
And 5: mutation;
controlling whether the chromosome is mutated or not according to the mutation rate; when mutation is required, a gene to be mutated is randomly selected. Each gene may be in [ 100 ]]T、[0 1 0]T、[0 0 1]TThe variation between the phases indicates that the switch phase is switched among the A phase, the B phase and the C phase. When the chromosome is longer, the variation rate can be properly smaller, the number of the commutation switches is generally between 10 and 20, and the variation rate can be 0.001 to 0.1.
Step 6: checking a strategy;
and after the genetic algorithm gives a control strategy, calculating the unbalance degree ibal 'of the three-phase current after control, and if the unbalance degree ibal' of the three-phase current is larger than the unbalance degree ibal of the three-phase current before control, cancelling the control command.
As shown in fig. 2, the hardware part of the platform load balance control system based on the genetic algorithm includes a master controller and a plurality of commutation switches, the master controller and each commutation switch are respectively connected to the three-phase line A, B, C and the zero line N of the three-phase unbalanced circuit, the control strategy is suitable for the "master control + execution switch" mode, and one master controller controls all the commutation switches of the platform area.
The above embodiments are merely illustrative of the technical concepts and features of the present invention, and the purpose of the embodiments is to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the protection scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.

Claims (5)

1. A platform region load balance control method based on genetic algorithm is characterized by comprising the following steps:
step 1) generating an initial population: the population scale is determined according to the number of installed phase change switches, a plurality of switches are distributed to A, B, C three phases according to the inverse relation of three-phase current at the head end of a transformer area, and the larger the current is, the fewer the number of switches in the phase is; and (3) an encoding mode: the condition of a plurality of switch phases is represented by a 3-row matrix, each column represents switch information called genes, and the state of each switch can only be switched among A, B, C three phases;
step 2) individual evaluation: forming a fitness function according to the three-phase current unbalance and all switching action times, and evaluating individuals according to the fitness function;
step 3), selection: selecting by adopting a rotation method, determining the probability of the individuals to be reserved to enter the next generation of genetic operation by adopting the ratio of the practical function value of the ith individual in the population to the sum of the fitness function values of all the individuals in the population, wherein the probability of the individuals to enter the next generation of genetic operation is in direct proportion to the individual fitness function;
step 4), crossing: adopting the point crossing of parents and gems, randomly selecting 1 breakpoint on a chromosome, and mutually exchanging the right sections of the breakpoints so as to form new offspring; in order to not destroy the dependence and mutual exclusion relationship between the genes, the whole vector gene is replaced during the cross operation, and the characteristics of the vector gene are not destroyed;
step 5) mutation: controlling whether the chromosome is mutated or not according to the mutation rate, and randomly selecting genes needing to be mutated when the chromosome needs to be mutated, wherein each gene can be mutated among the genes represented by 3 groups of switch information and represents that the switch phase is switched among A phase, B phase and C phase;
step 6) strategy verification: and after the genetic algorithm gives a control strategy, calculating the unbalance degree of the three-phase current after control, and if the unbalance degree of the three-phase current is larger than the unbalance degree of the three-phase current before control, cancelling the control command.
2. The platform load balance control method based on the genetic algorithm as claimed in claim 1, wherein before step 1), periodically reading three-phase current data at the head end of the platform, screening out abnormal data, calculating three-phase current unbalance degrees and load rates, wherein the unbalance degrees of the three-phase current are greater than a threshold value and the load rates are greater than a threshold value for n consecutive times:
and recording three-phase currents corresponding to n times of continuous out-of-limit of the three-phase current unbalance and the load rate as Ia1, Ia2, …, Ian, Ib1, …, Ibn, Ic1, … and Icn respectively.
Calculating the three-phase weighted average current:
Figure FDA0002645975150000021
Figure FDA0002645975150000022
Figure FDA0002645975150000023
note the book
Figure FDA0002645975150000024
Wherein the content of the first and second substances,
Figure FDA0002645975150000025
3. the distribution room load balance control method based on the genetic algorithm, according to claim 1, wherein the number of the phase change switches is 9, and the initialization population is:
Figure FDA0002645975150000026
wherein, the load current of each switch is recorded as: i issw＝[i1 i2 i3 i4 i5 i6 i7 i8 i9]The total switch current of each phase is Isw_sum＝Ksw·Isw T。
4. The distribution room load balance control method based on the genetic algorithm as claimed in claim 1, wherein the fitness function in step 2) is composed of two parts, which are three-phase current unbalance and all switching action times:
Fun＝Cmax-k1·ibal-k2·act_times
where Fun is the fitness function, CmaxIs a large constant, ensures that the fitness function is not negative, k1Is the weight of the unbalance degree of the three-phase current, ibal is the unbalance degree of the three-phase current, k2Act _ tim as weight of action timeses is the number of actions.
5. The method for controlling distribution room load balance based on genetic algorithm as claimed in claim 1, wherein the number of commutation switches in step 5) is between 10 and 20, and the variation rate is 0.001 to 0.1.
CN202010854641.9A 2020-08-24 2020-08-24 Platform area load balance control method based on genetic algorithm Withdrawn CN112003308A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010854641.9A CN112003308A (en) 2020-08-24 2020-08-24 Platform area load balance control method based on genetic algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010854641.9A CN112003308A (en) 2020-08-24 2020-08-24 Platform area load balance control method based on genetic algorithm

Publications (1)

Publication Number Publication Date
CN112003308A true CN112003308A (en) 2020-11-27

Family

ID=73473118

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010854641.9A Withdrawn CN112003308A (en) 2020-08-24 2020-08-24 Platform area load balance control method based on genetic algorithm

Country Status (1)

Country Link
CN (1) CN112003308A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113552528A (en) * 2021-06-29 2021-10-26 国网上海市电力公司 Transformer substation bus unbalance rate abnormity analysis method based on improved genetic algorithm
CN113890116A (en) * 2021-09-30 2022-01-04 国网北京市电力公司 Multi-distribution-station-area interconnection mutual-aid power control method, device and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113552528A (en) * 2021-06-29 2021-10-26 国网上海市电力公司 Transformer substation bus unbalance rate abnormity analysis method based on improved genetic algorithm
CN113890116A (en) * 2021-09-30 2022-01-04 国网北京市电力公司 Multi-distribution-station-area interconnection mutual-aid power control method, device and storage medium
CN113890116B (en) * 2021-09-30 2024-05-07 国网北京市电力公司 Multi-distribution-area interconnection mutual power control method, device and storage medium

Similar Documents

Publication Publication Date Title
Niknam An efficient hybrid evolutionary algorithm based on PSO and ACO for distribution feeder reconfiguration
EP2507751B1 (en) Restoration switching analysis with modified genetic algorithm
Zhu Optimal reconfiguration of electrical distribution network using the refined genetic algorithm
CN112003308A (en) Platform area load balance control method based on genetic algorithm
EP2507750B1 (en) Restoration switching analysis with genetic algorithm
Song et al. Advanced engineered-conditioning genetic approach to power economic dispatch
CN111200290B (en) Intelligent control method of phase change switch for three-phase unbalance treatment of transformer area
CN110854891B (en) Power distribution network pre-disaster resource allocation method and system
King et al. A fuzzy logic controlled genetic algorithm for optimal electrical distribution network reconfiguration
CN108879670A (en) A kind of high voltage distribution network partition zone optimizing method
Hong et al. Genetic algorithm based network reconfiguration for loss minimization in distribution systems
CN114417719A (en) Power distribution network gridding method and device based on graph attention network
Juang et al. Power system load frequency control with fuzzy gain scheduling designed by new genetic algorithms
Ganesan et al. Regular paper distribution system reconfiguration for loss reduction using genetic algorithm
Kumari et al. A fast computational genetic algorithm for economic load dispatch
Eghbal et al. Application of metaheuristic methods to reactive power planning: a comparative study for GA, PSO and EPSO
CN114758023A (en) Stomach electrical impedance tomography method of self-adaptive genetic algorithm
Choi et al. An application of genetic algorithms to the network reconfiguration in distribution for loss minimization and load balancing problem. II
Tian et al. A two-stage planning strategy for reliability enhancement and loss reduction in distribution systems
CN111105025A (en) Urban high-voltage distribution network blocking management method based on data-driven heuristic optimization
CN112381377A (en) Power grid connection mode evaluation method, device, equipment and storage medium
Wang et al. Research on Distribution Network Fault Location based on Improved Genetic Algorithm
CN115833116B (en) Power distribution network reconstruction optimization method based on multi-objective optimization
Momoh et al. Investigation of artificial neural networks for voltage stability assessment
CN116799826A (en) Distributed photovoltaic energy storage system optimal configuration method and related device

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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20201127