CN113922373A - Electrical load identification method based on multi-feature index fusion - Google Patents

Electrical load identification method based on multi-feature index fusion Download PDF

Info

Publication number
CN113922373A
CN113922373A CN202111203183.3A CN202111203183A CN113922373A CN 113922373 A CN113922373 A CN 113922373A CN 202111203183 A CN202111203183 A CN 202111203183A CN 113922373 A CN113922373 A CN 113922373A
Authority
CN
China
Prior art keywords
load
feature index
objective function
power
load identification
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
CN202111203183.3A
Other languages
Chinese (zh)
Inventor
孙珂
解正兵
王琪琪
李佳朔
周涵
唐勤
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.)
Feixi Power Supply Co of State Grid Anhui Electric Power Co Ltd
Original Assignee
Feixi Power Supply Co of State Grid Anhui 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 Feixi Power Supply Co of State Grid Anhui Electric Power Co Ltd filed Critical Feixi Power Supply Co of State Grid Anhui Electric Power Co Ltd
Priority to CN202111203183.3A priority Critical patent/CN113922373A/en
Publication of CN113922373A publication Critical patent/CN113922373A/en
Pending 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
    • 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
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • 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
    • H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
    • H02J2310/70—Load identification

Abstract

The invention discloses a multi-feature index fusion-based power load identification method, which comprises the following steps of: step 1, acquiring single load characteristic quantity, and constructing a single load objective function and a multi-load objective function; step 2, extracting the characteristic quantity of the total power consumption data of the load operation to be identified, and constructing an actual measurement objective function; and 3, carrying out load identification on the actually measured target function by adopting a genetic algorithm. According to the invention, a plurality of parameter indexes such as the current effective value and the active power are used as the load identification characteristic quantity, so that the identification accuracy is improved; the invention adopts the target function of multi-characteristic index fusion as the load identification condition, thereby reducing the load identification calculation amount.

Description

Electrical load identification method based on multi-feature index fusion
Technical Field
The invention relates to the technical field of load identification, in particular to an electrical load identification method based on multi-feature index fusion.
Background
In recent years, along with the gradual development of intelligent power utilization and power demand side management technologies and the gradual enhancement of energy saving awareness, the realization of power utilization intellectualization of intelligent sockets and intelligent electrical appliances appears in succession. However, the traditional detection method mostly adopts an intrusive mode to monitor the running state of the household appliance and provide related data for an energy management system. The high cost investment and poor expansibility of the system cause the application range of the system to be limited, and meanwhile, the system is inconvenient for long-term maintenance. Non-intrusive load monitoring (Non-intrusive load monitoring NILM) is a process that estimates the energy consumed by a single device based only on power meter readings throughout the house. For example, the amount of electricity used by various types of appliances (such as air conditioners, refrigerators, incandescent lamps, fluorescent lamps, and televisions) can be determined by only one electricity meter for the entire house. After the electricity utilization condition of the classified electric appliances is known, various energy-saving measures can be realized.
Meanwhile, load identification is a key of non-invasive load monitoring, in common load identification, active power, reactive power, harmonic waves, current and the like are mainly used as load identification characteristic quantities, and when different loads have the same power or the same current, certain influence is caused on the accuracy of load identification.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an electric load identification method based on multi-feature index fusion, which takes a plurality of feature indexes as load identification feature quantities and utilizes a genetic algorithm to carry out load identification so as to improve the load identification accuracy.
In a first aspect, the invention provides a method for identifying an electrical load based on multi-feature index fusion, which comprises the following steps:
step 1, acquiring single load characteristic quantity, and constructing a single load objective function and a multi-load objective function;
further, the single load characteristic quantity comprises an effective current value IrmsActive power P and power factor
Figure BDA0003305791170000011
Wherein the effective value of the current
Figure BDA0003305791170000012
Active power
Figure BDA0003305791170000013
Apparent power
Figure BDA0003305791170000014
Power factor
Figure BDA0003305791170000015
k is the harmonic order.
Further, the single-load objective function is Yn(x)＝αy1(x)+βy2(x)+γy3(x) (ii) a Wherein x is a load working state, x belongs to {0,1}, and when x is equal to 1, the load is represented as the working state; when x is 0, it indicates that the load is not operating, and y is1(x),y2(x),y3(x) Are respectively IrmsP and
Figure BDA0003305791170000021
and the alpha, beta and gamma are weight coefficients.
The multi-load objective function is Y (x) Y1(x)+Y2(x)+Y3(x)+…+Yn(x)。
Step 2, extracting the characteristic quantity of the total power consumption data of the load operation to be identified, and constructing an actual measurement objective function;
further, the total power utilization data characteristic quantity comprises measured current, measured active power and measured apparent power.
Further, the measured objective function is: y '(x) ═ α I' + β P '+ γ cos Φ'.
Wherein, I ', P ', cos phi ' are respectively normalized values constructed based on the measured current, the measured active power and the measured apparent power, and alpha, beta and gamma are weight coefficients.
And 3, carrying out load identification on the actually measured target function by adopting a genetic algorithm.
Further, the genetic algorithm comprises the steps of:
step 3.1, determining a coding scheme, defining a fitness function, and selecting genetic algorithm parameters;
further, the coding scheme employs binary coding, i.e., "0" and "1". Each chromosome corresponds to a load combination set, the load combination set comprises n loads, the length L of the chromosome is n, namely the chromosome is a 0 and 1 character string with the length of n; when a certain gene in the chromosome is "1", it indicates that the load corresponding to the gene is in an operating state, and when a certain gene in the chromosome is "0", it indicates that the load corresponding to the gene is in an off state.
Further, the fitness function is: h ═ min (Y (x) -Y' (x)); when H is present<H0Judging to reach the optimal solution, finishing iteration and outputting the optimal solution, wherein H0To an adaptation value.
Step 3.2, randomly generating an initial population;
wherein the initial population is a group of 0 and 1 character strings with the length of n.
Step 3.3, calculating a fitness function of the initial population according to the load access state of the initial population;
step 3.4, judging whether the calculation result reaches the optimal solution;
step 3.5, outputting the optimal solution if the optimal solution is reached, otherwise, performing iterative operation to generate a new population, and repeating the step 3.3-3.5;
further, the iterative operations include selection, crossover, and mutation; the selection in the iterative operation adopts a roulette selection method; the uniform crossing strategy is adopted for crossing, namely, the genes on the chromosome are exchanged with the same crossing probability, so that a new individual is formed; the mutation adopts basic bit mutation, namely mutation operation is carried out on a certain bit or values on certain bits randomly specified by mutation probability in a chromosome, namely that '1' is changed into '0' and '0' is changed into '1'.
And 3.6, forming the output optimal solution into a matrix with m rows and n columns, and judging the load type of the access system under the current actual measurement condition.
Wherein, each row of the matrix with m rows and n columns is a solution which meets the requirement of fitness, namely a string with the length of n being 0 and 1, and m solutions are shared, thereby carrying out load identification.
In a second aspect, the present invention provides an electrical load identification apparatus based on multi-feature index fusion, including: a processor, a memory for storing processor-executable instructions.
Wherein the processor is configured to execute the electrical load identification method based on multi-feature index fusion of the first aspect.
In a third aspect, the present invention protects a non-volatile computer-readable storage medium, on which computer program instructions are stored, which when executed by a processor implement the above-mentioned electrical load identification method based on multi-feature index fusion of the first aspect.
The invention has the beneficial effects that: 1. the method can be used for processing large-scale complex data and is suitable for solving the multi-objective optimization problem; 2. according to the invention, a plurality of parameter indexes such as the current effective value and the active power are used as the load identification characteristic quantity, so that the identification accuracy is improved; 3. the invention adopts the target function of multi-characteristic index fusion as the load identification condition, thereby reducing the load identification calculation amount.
Drawings
FIG. 1 is a flow chart of a method for identifying electrical loads based on multi-feature index fusion;
FIG. 2 is a flowchart of the genetic algorithm in example 1.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments. The embodiments of the present invention have been presented for purposes of illustration and description, and are not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiment was chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.
Example 1
The present embodiment specifically explains the technical solution (as shown in fig. 1) of the present invention by taking a household power system as an example. Selecting 5 power loads: an electric kettle, an induction cooker, an energy-saving lamp, an electric fan and a printer are respectively marked as loads 1-5. 5 kinds of loads are respectively connected into the power system.
A power load identification method based on multi-feature index fusion comprises the following steps:
step 1, acquiring single load characteristic quantity of a household power utilization system, and constructing a single load objective function and a multi-load objective function;
in particular, the single load characteristic quantity comprises an effective value of current IrmsActive power P and power factor
Figure BDA0003305791170000041
The identification accuracy is improved by comprehensively considering a plurality of parameter indexes of the current effective value, the active power and the power factor as the load identification characteristic quantity.
Wherein, the current effective value:
Figure BDA0003305791170000042
active power is the integrated average of the instantaneous power consumed by the load:
Figure BDA0003305791170000043
apparent power:
Figure BDA0003305791170000044
the power factor is the ratio of the active power to the apparent power of the circuit:
Figure BDA0003305791170000045
k is the harmonic order.
More specifically, a single-load objective function is constructed which is a combination of a current effective value, active power and a power factor, the current effective value, the active power and the power factor respectively occupying different weights. Meanwhile, because the current effective value, the active power and the power factor dimension are not consistent, the data are normalized in order to simplify the calculation.Thus, the single load objective function is represented as: y isn(x)＝αy1(x)+βy2(x)+γy3(x) (ii) a Wherein x is a load working state, x belongs to {0,1}, and when x is equal to 1, the load is represented as the working state; when x is 0, it indicates that the load is not operating, and y is1(x),y2(x),y3(x) Are respectively IrmsP and
Figure BDA0003305791170000046
and the alpha, beta and gamma are weight coefficients. By adopting the target function of multi-feature index fusion as the load identification condition, the load identification calculated amount is reduced.
In the present embodiment, α is set to 0.3, β is set to 0.2, and γ is set to 0.1. The effective value of current, active power and power factor of the electric kettle are respectively 7.85, 1711 and 0.999, and the single load objective function of the electric kettle is obtained as
Y1＝0.3*7.85+0.2*1711+0.1*0.9＝344.65
The effective value of the current, the active power and the power factor of the induction cooker are respectively 5.82, 1135.2 and 0.874, and the single load objective function of the induction cooker is obtained as
Y2＝0.3*5.82+0.2*1135.2+0.1*0.874＝228.87
The effective value, the active power and the power factor of the energy-saving lamp current are respectively 0.41, 40.7 and 0.998, and the single load objective function of the energy-saving lamp is obtained as
Y3＝0.3*0.41+0.2*40.7+0.1*0.998＝8.36
The effective value of the current, the active power and the power factor of the electric fan are respectively 0.145, 28.4 and 0.889, and the single load objective function of the electric fan is obtained as
Y4＝0.3*0.145+0.2*28.4+0.1*0.889＝5.81
The effective value, active power and power factor of printer current are respectively 2.8, 823.1 and 0.892, and the single load objective function of printer is obtained as
Y5＝0.3*2.8+0.2*823.1+0.1*0.892＝165.55
Included in said multi-load objective functionThe single load objective function is formed by combining the effective value of current, active power and power factor, and is expressed as Y (x) Y1(x)+Y2(x)+Y3(x)+Y4(x)+Y5(x)。
In this embodiment, if all the loads are running simultaneously, the multi-load objective function is
Y＝1*344.65+1*227.26+1*8.36+1*5.81+1*165.55＝753.24
Step 2, extracting the total power consumption data characteristic quantity of the household power consumption, and constructing an actual measurement objective function;
specifically, the total power consumption data characteristic quantity comprises measured current, measured active power and measured apparent power.
Further, the measured objective function is: y '(x) ═ α I' + β P '+ γ cos Φ'.
Wherein, I ', P ', cos phi ' are respectively normalized values constructed based on the measured current, the measured active power and the measured apparent power, and alpha, beta and gamma are weight coefficients.
And 3, as shown in fig. 2, carrying out load identification on the actually measured target function by adopting a genetic algorithm. The genetic algorithm has good global search capability, can quickly search out the whole solution in the solution space, and cannot get into a quick descending trap of a local optimal solution; and by utilizing the intrinsic parallelism of the method, distributed computation can be conveniently carried out, and the solving speed is accelerated.
Further, the genetic algorithm comprises the steps of:
step 3.1, determining a coding scheme, defining a fitness function, and selecting genetic algorithm parameters;
in particular, the coding scheme employs binary coding, i.e., "0" and "1". Each chromosome corresponds to a load combination set, the load combination set comprises 5 loads, the length L of the chromosome is 5, namely the chromosome is a 0 and 1 character string with the length of 5; when a certain gene in the chromosome is "1", it indicates that the electric appliance corresponding to the gene is in an operating state, and when a certain gene in the chromosome is "0", it indicates that the electric appliance corresponding to the gene is in an off state.
Specifically, the fitness function is: h ═ min (Y (x) -Y' (x)); when H is present<H0Judging to reach the optimal solution, finishing iteration and outputting the optimal solution, wherein H0To an adaptation value.
Step 3.2, randomly generating an initial population: 00101, when the loads of the energy-saving lamp and the printer are in running states, the loads of the electric kettle, the induction cooker and the electric fan are disconnected;
step 3.3, calculating a fitness function of the initial population according to the load access state of the initial population;
step 3.4, judging whether the calculation result reaches the optimal solution;
step 3.5, outputting the optimal solution if the optimal solution is reached, otherwise, performing iterative operation to generate a new population, and repeating the step 3.3-3.5;
in particular, the iterative operations include selection, crossover and mutation; the selection in the iterative operation adopts a roulette selection method; the uniform crossing strategy is adopted for crossing, namely, the genes on the chromosome are exchanged with the same crossing probability, so that a new individual is formed; the mutation adopts basic bit mutation, namely mutation operation is carried out on a certain bit or values on certain bits randomly specified by mutation probability in a chromosome, namely that '1' is changed into '0' and '0' is changed into '1'.
And 3.6, forming the output optimal solution into a matrix with 3 rows and 5 columns, and judging the load type of the access system under the current actual measurement condition.
Specifically, in this embodiment, it is assumed that the measured objective function is 585, and the adaptive value is set to H0After iterative operation, the genetic algorithm judges that the optimal solution is reached, and outputs the optimal solution as
Figure BDA0003305791170000061
Calculating the operation probability of each load as follows: 100%, 33%, 0%. Then the probability that insulating pot, electromagnetism stove, electricity-saving lamp, electric fan, printer appear in this actual measurement system is respectively: 100%, 33%, 0%.
In this embodiment, it is assumed that the measured objective function is still 585, and the adaptive value is set to H0After iterative operation, the genetic algorithm judges that the optimal solution is reached, and outputs the optimal solution as
Figure BDA0003305791170000062
Calculating the operation probability of each load as follows: 100%, 0%, 50%, 0%. Then the probability that insulating pot, electromagnetism stove, electricity-saving lamp, electric fan, printer appear in this actual measurement system is respectively: 100%, 0%, 50%, 0%.
The method uses the measured data to obtain the current value of the single load, and calculates the objective function of the single load and the objective function of the multiple loads by using the calculated current effective value, active power and power factor as the load identification characteristic quantity. When the load to be identified is accessed, on the basis of comprehensively considering the current effective value, the active power and the power factor, the genetic algorithm is adopted to optimize the actual measurement target function, so that an optimal solution meeting the fitness function is obtained, and the load access condition is judged according to the output optimal solution string.
Example 2
Corresponding to the electrical load identification method based on the multi-feature index fusion in the embodiment 1, the embodiment of the invention provides an electrical load identification device based on the multi-feature index fusion, which comprises the following steps: a processor, a memory for storing processor-executable instructions.
Wherein the processor is configured to execute the electrical load identification method based on multi-feature index fusion of the first aspect.
Example 3
The present embodiment provides a non-transitory computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method of embodiment 1 described above.
It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by one of ordinary skill in the art and related arts based on the embodiments of the present invention without any creative effort, shall fall within the protection scope of the present invention.

Claims (10)

1. A power load identification method based on multi-feature index fusion comprises the following steps:
step 1, acquiring single load characteristic quantity, and constructing a single load objective function and a multi-load objective function;
step 2, extracting the characteristic quantity of the total power consumption data of the load operation to be identified, and constructing an actual measurement objective function;
and 3, carrying out load identification on the actually measured target function by adopting a genetic algorithm.
2. The electrical load identification method based on multi-feature index fusion as claimed in claim 1, wherein the single load feature quantity comprises a current effective value IrmsActive power P and power factor
Figure FDA0003305791160000011
Wherein the effective value of the current
Figure FDA0003305791160000012
Active power
Figure FDA0003305791160000013
Apparent power
Figure FDA0003305791160000014
Power factor
Figure FDA0003305791160000015
k is the harmonic order.
3. The electrical load identification method based on multi-feature index fusion as claimed in claim 2, wherein the single load objective function is Yn(x)＝αy1(x)+βy2(x)+γy3(x) (ii) a The multi-load objective function is Y (x) Y1(x)+Y2(x)+Y3(x)+…+Yn(x)；
Wherein x is a load working state, x belongs to {0,1}, and when x is equal to 1, the load is represented as the working state; when x is 0, it indicates that the load is not operating, and y is1(x),y2(x),y3(x) Are respectively IrmsP and
Figure FDA0003305791160000016
and the alpha, beta and gamma are weight coefficients.
4. The method according to claim 1, wherein the total electricity consumption data characteristic quantities comprise measured current, measured active power and measured apparent power.
5. The electrical load identification method based on multi-feature index fusion according to claim 4, wherein the measured objective function is: y '(x) ═ β I' + β P '+ γ cos Φ';
wherein, I ', P ', cos phi ' are respectively normalized values constructed based on the measured current, the measured active power and the measured apparent power, and alpha, beta and gamma are weight coefficients.
6. The method for identifying the electric load based on the multi-feature index fusion according to claim 1, wherein the genetic algorithm comprises the following steps:
step 3.1, determining a coding scheme, defining a fitness function, and selecting genetic algorithm parameters;
step 3.2, randomly generating an initial population;
wherein the initial population is a group of 0 and 1 character strings with the length of n;
step 3.3, calculating a fitness function of the initial population according to the load access state of the initial population;
step 3.4, judging whether the calculation result reaches the optimal solution;
step 3.5, outputting the optimal solution if the optimal solution is reached, otherwise, performing iterative operation to generate a new population, and repeating the step 3.3-3.5;
step 3.6, forming the output optimal solution into a matrix with m rows and n columns, and judging the load type of the access system under the current actual measurement condition;
and each row of the matrix with m rows and n columns is a solution which meets the requirement of fitness, namely m solutions are shared, so that the load identification is carried out.
7. The electrical load identification method based on multi-feature index fusion according to claim 6, characterized in that in the step 3.1, the coding scheme adopts binary coding; each chromosome corresponds to a load combination set, the load combination set comprises n loads, the length L of the chromosome is n, namely the chromosome is a 0 and 1 character string with the length of n; when a certain gene in the chromosome is '1', the load corresponding to the gene is in an operating state, and when a certain gene in the chromosome is '0', the load corresponding to the gene is in an off state;
the fitness function is: h ═ min (Y (x) -Y' (x)); when H is present<H0Judging to reach the optimal solution, finishing iteration and outputting the optimal solution, wherein H0To an adaptation value.
8. The electrical load identification method based on multi-feature index fusion according to claim 6 or 7, wherein the iterative operation comprises selection, intersection and variation; the selection in the iterative operation adopts a roulette selection method; the uniform crossing strategy is adopted for crossing; the mutation adopts basic bit mutation, namely mutation operation is carried out on a certain bit or values on certain bits randomly designated by mutation probability in a chromosome.
9. The utility model provides a device is discerned to power consumption load based on multi-feature index fuses which characterized in that includes: a processor, a memory for storing processor-executable instructions;
wherein the processor is configured to execute the electrical load identification method based on multi-feature index fusion according to any one of claims 1 to 8.
10. A non-transitory computer readable storage medium having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method for identifying electrical loads based on multi-feature index fusion according to any one of claims 1 to 8.
CN202111203183.3A 2021-10-15 2021-10-15 Electrical load identification method based on multi-feature index fusion Pending CN113922373A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111203183.3A CN113922373A (en) 2021-10-15 2021-10-15 Electrical load identification method based on multi-feature index fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111203183.3A CN113922373A (en) 2021-10-15 2021-10-15 Electrical load identification method based on multi-feature index fusion

Publications (1)

Publication Number Publication Date
CN113922373A true CN113922373A (en) 2022-01-11

Family

ID=79240872

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111203183.3A Pending CN113922373A (en) 2021-10-15 2021-10-15 Electrical load identification method based on multi-feature index fusion

Country Status (1)

Country Link
CN (1) CN113922373A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140336831A1 (en) * 2013-05-08 2014-11-13 Samsung Electronics Co., Ltd. Non-intrusive load monitoring apparatus and method
CN108564205A (en) * 2018-03-27 2018-09-21 昆明理工大学 A kind of load model and parameter identification optimization method based on measured data
CN108616120A (en) * 2018-04-28 2018-10-02 西安理工大学 A kind of non-intrusive electrical load decomposition method based on RBF neural
CN110942263A (en) * 2019-12-16 2020-03-31 国网江苏省电力有限公司苏州供电分公司 Aggregation monitoring method and device for response capability of low-voltage power load demand side
CN111948446A (en) * 2020-07-20 2020-11-17 江阴长仪集团有限公司 Self-adaptive load identification method and intelligent electric energy meter
CN112381665A (en) * 2020-09-28 2021-02-19 华南理工大学 Multi-feature weighted household electrical load identification method based on chicken swarm algorithm
CN112736904A (en) * 2020-12-25 2021-04-30 天津大学 Power load model online analysis method based on small disturbance data
WO2021171303A1 (en) * 2020-02-26 2021-09-02 Council Of Scientific And Industrial Research A system and method for energy management of identical appliances using non-intrusive load monitoring technique

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140336831A1 (en) * 2013-05-08 2014-11-13 Samsung Electronics Co., Ltd. Non-intrusive load monitoring apparatus and method
CN108564205A (en) * 2018-03-27 2018-09-21 昆明理工大学 A kind of load model and parameter identification optimization method based on measured data
CN108616120A (en) * 2018-04-28 2018-10-02 西安理工大学 A kind of non-intrusive electrical load decomposition method based on RBF neural
CN110942263A (en) * 2019-12-16 2020-03-31 国网江苏省电力有限公司苏州供电分公司 Aggregation monitoring method and device for response capability of low-voltage power load demand side
WO2021171303A1 (en) * 2020-02-26 2021-09-02 Council Of Scientific And Industrial Research A system and method for energy management of identical appliances using non-intrusive load monitoring technique
CN111948446A (en) * 2020-07-20 2020-11-17 江阴长仪集团有限公司 Self-adaptive load identification method and intelligent electric energy meter
CN112381665A (en) * 2020-09-28 2021-02-19 华南理工大学 Multi-feature weighted household electrical load identification method based on chicken swarm algorithm
CN112736904A (en) * 2020-12-25 2021-04-30 天津大学 Power load model online analysis method based on small disturbance data

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
孙珂: "基于导纳特征和遗传算法的负荷识别", 《安徽大学学报（自然科学版）》, vol. 45, no. 4, pages 64 - 70 *
祁兵: "基于遗传优化的非侵入式居民负荷辨识算法", 《电测与仪表》, vol. 54, no. 17, pages 11 - 17 *

Similar Documents

Publication Publication Date Title
CN109165788B (en) Optimization method of combined cooling heating and power system
CN106484512B (en) The dispatching method of computing unit
Shuai et al. Are China's solar PV products competitive in the context of the Belt and Road Initiative?
CN106651628B (en) Regional cooling, heating and power comprehensive energy optimal allocation method and device based on graph theory
CN111932070A (en) Household power consumer electricity utilization efficiency analysis device
Saha et al. A model of residential energy use in New Zealand
Musa et al. Optimal sizing and location of multiple distributed generation for power loss minimization using genetic algorithm
CN113988471A (en) Multi-objective optimization method for micro-grid operation
CN113922373A (en) Electrical load identification method based on multi-feature index fusion
CN114662809A (en) Method and system for evaluating electric energy quality of power supply in comprehensive energy park
Iqbal et al. Optimal load scheduling using genetic algorithm to improve the load profile
Chang et al. PMV-based genetic algorithms for indoor temperature control system
CN111859242A (en) Household power energy efficiency optimization method and system
US9002483B1 (en) Diploid control of water heaters
CN112379159B (en) Non-invasive household load decomposition method based on electric appliance operation mode
CN112113316B (en) Method for extracting air conditioner load
CN113947255A (en) Electric water heater short-term load prediction method and system based on Monte Carlo method
CN114066264A (en) Comprehensive energy system operation optimization method and system considering comprehensive demand response
Palacios-Garcia et al. Smart community load matching using stochastic demand modeling and historical production data
CN113610556A (en) Method, device and terminal for power load prediction
CN108110755B (en) Household electricity combination method based on power prediction
CN111948446A (en) Self-adaptive load identification method and intelligent electric energy meter
CN111709670A (en) Building energy regulation and control strategy evaluation method and device for geothermal energy
CN111146781A (en) Low-voltage distribution room program-controlled load simulation system
Van Harmelen et al. Multi-level expert-modelling for the evaluation of hot water load management opportunities in South Africa

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