CN109377052B - Power load matching method, device, equipment and readable storage medium - Google Patents
Power load matching method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN109377052B CN109377052B CN201811245423.4A CN201811245423A CN109377052B CN 109377052 B CN109377052 B CN 109377052B CN 201811245423 A CN201811245423 A CN 201811245423A CN 109377052 B CN109377052 B CN 109377052B
- Authority
- CN
- China
- Prior art keywords
- power load
- load curve
- power
- matching
- electric
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000004422 calculation algorithm Methods 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 230000006698 induction Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 12
- 238000012549 training Methods 0.000 abstract description 7
- 230000001052 transient effect Effects 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 16
- 238000002474 experimental method Methods 0.000 description 7
- 230000003190 augmentative effect Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 241000209094 Oryza Species 0.000 description 3
- 235000007164 Oryza sativa Nutrition 0.000 description 3
- 230000003416 augmentation Effects 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 235000009566 rice Nutrition 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- KUVIULQEHSCUHY-XYWKZLDCSA-N Beclometasone Chemical compound C1CC2=CC(=O)C=C[C@]2(C)[C@]2(Cl)[C@@H]1[C@@H]1C[C@H](C)[C@@](C(=O)COC(=O)CC)(OC(=O)CC)[C@@]1(C)C[C@@H]2O KUVIULQEHSCUHY-XYWKZLDCSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 229940014063 qvar Drugs 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power load matching method, which is characterized in that a bipartite graph model is constructed according to a first power load curve and a second power load curve of electric equipment; then determining the matching relation between each first power load curve and a second target power load curve through a bipartite graph model; and finally, determining the matching relation between the second target power load curve and each electric device according to the pre-stored matching relation. Because the bipartite graph model is used, a large amount of prior data are not needed to be used as training samples, the clustering number is not needed to be determined in advance, a large amount of transient process data are not needed to be extracted and screened, and meanwhile, due to the superior characteristics of the bipartite graph model, the matching of the first power load curve and the second power load curve can be accurately realized, the matching of the second power load curve and each electric device can be accurately realized, and the matching accuracy of the power loads can be improved. In addition, the invention also discloses a power load matching device, equipment and a readable storage medium, and the effects are as above.
Description
Technical Field
The present invention relates to the field of power system applications, and in particular, to a power load matching method, device, apparatus, and readable storage medium.
Background
The load identification technology is mainly divided into an invasive type and a non-invasive type, the non-invasive type load identification technology can be added with an intelligent detection device at a user electric meter end, so that electric power load data in a room can be acquired, and the service conditions of all electric power equipment in a user house can be deduced by analyzing data such as power consumption, service time, start-stop states and the like.
The starting of each electric device is generally manually started, the starting sequence of the electric device is known, and the corresponding relation between the drawn power load curve and the electric device is clear, but because most electric devices are automatically powered off and closed, the corresponding relation between the power load curve formed after the electric devices are closed and the electric device is unclear, and meanwhile, the corresponding relation between the power load curve when the same electric device is started and the power load curve when the electric device is closed is unclear. Therefore, matching of the power loads is important.
At present, matching of power loads is mainly realized through an artificial neural network, a fuzzy clustering algorithm and the like. However, the artificial neural network needs a large amount of prior data as training samples, and is difficult to expand and extend in the later period, and the newly accessed equipment is difficult to achieve high recognition rate. The method can determine the steady-state data and the characteristic parameters of the voltage and the current of the electric appliance by adopting a fuzzy clustering algorithm, but the fuzzy clustering algorithm has defects, the type identification of the equipment is not accurate enough, the clustering number needs to be determined in advance, a large amount of transient process data needs to be extracted and screened, and the matching process is complex.
Therefore, the problem of how to improve the power load matching accuracy of the power utilization equipment in the power system is an urgent problem to be solved by those skilled in the art.
Disclosure of Invention
The embodiment of the application provides a power load matching method, a device, equipment and a readable storage medium, which are used for solving the problem of how to improve the power load matching accuracy of electric equipment in a power system in the prior art.
In order to solve the above technical problem, the present invention provides a power load matching method, including:
acquiring target data of all electric equipment in a power system when the electric equipment is turned on and turned off to form a first power load curve of each electric equipment when the electric equipment is turned on and a second power load curve of each electric equipment when the electric equipment is turned off;
constructing a bipartite graph model according to each first power load curve and each second power load curve;
determining a second target power load curve matched with each first power load curve according to the bipartite graph model;
determining a matching relation between the second target power load curve and each electric device according to a pre-stored matching relation between the first power load curve and each electric device;
wherein the second power load curve includes the second target power load curve.
Preferably, the acquiring target data of all the electric devices in the power system when the electric devices are turned on and turned off specifically includes:
and acquiring the target data through non-invasive detection equipment.
Preferably, after the acquiring target data of all the electric devices in the power system when the electric devices are turned on and off, the method further includes:
and preprocessing the target data.
Preferably, the determining, according to the bipartite graph model, a second target power load curve matched with each of the first power load curves specifically includes:
and determining the second target power load curve by adopting a Hungarian algorithm in the bipartite graph model.
Preferably, the determining the second target power load curve by using the hungarian algorithm in the bipartite graph model specifically includes:
determining a cost matrix of the Hungarian algorithm;
calculating the matching degree of each first power load curve and each second power load curve according to the cost matrix;
and selecting the second power load curve with the highest matching degree as the second target power load curve.
Preferably, the electric equipment specifically comprises a variable frequency air conditioner, a microwave oven, an induction cooker and an electric kettle.
In order to solve the above technical problem, the present invention further provides a power load matching apparatus corresponding to the power load matching method, including:
the acquisition module is used for acquiring target data of all electric equipment in an electric power system when the electric equipment is started and closed so as to form a first electric load curve of each electric equipment when the electric equipment is started and a second electric load curve of each electric equipment when the electric equipment is closed;
the building module is used for building a bipartite graph model according to each first power load curve and each second power load curve;
the first determining module is used for determining a second target power load curve matched with each first power load curve according to the bipartite graph model;
the second determining module is used for determining the matching relation between the second target power load curve and each electric device according to the pre-stored matching relation between the first power load curve and each electric device;
wherein the second power load curve includes the second target power load curve.
Preferably, the obtaining module is specifically configured to obtain the target data through a non-invasive detection device.
In order to solve the above technical problem, the present invention further provides a power load matching apparatus corresponding to the power load matching method, including:
a memory for storing the computer program;
a processor for executing the calculation program to implement the steps of any one of the above power load matching methods.
In order to solve the above technical problem, the present invention further provides a computer-readable storage medium corresponding to the power load matching method, where the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of any one of the above power load matching methods.
Compared with the prior art, the power load matching method provided by the invention is characterized in that a bipartite graph model is constructed according to a first power load curve and a second power load curve of electric equipment; then determining which second target power load curve in the second power load curves is matched with each first power load curve specifically through the constructed bipartite graph model; and finally, determining the matching relation between the second target power load curve and each electric device according to the pre-stored matching relation between the first power load curve and each electric device. Because the bipartite graph model is used, a large amount of prior data are not needed to be used as training samples, the clustering number is not needed to be determined in advance, a large amount of transient process data are not needed to be extracted and screened, and meanwhile, due to the superior characteristics of the bipartite graph model, the matching between the first power load curve and the second power load curve can be accurately realized, the type matching between the second power load curve and the electric equipment can be accurately realized, and the high matching rate of newly accessed equipment can be achieved. Therefore, the method can improve the matching accuracy of the power load. In addition, the invention also provides a power load matching device, equipment and a readable storage medium, and the effects are as above.
Drawings
Fig. 1 is a flowchart of a power load matching method according to an embodiment of the present invention;
fig. 2(a) is a power curve diagram of an inverter air conditioner according to an embodiment of the present invention at the beginning;
fig. 2(b) is a power curve diagram of the inverter air conditioner according to the embodiment of the present invention when the inverter air conditioner is turned off;
FIG. 2(c) is a power curve diagram of a microwave oven according to an embodiment of the present invention when the microwave oven is turned on;
FIG. 2(d) is a power curve diagram of a microwave oven according to an embodiment of the present invention when the microwave oven is turned off;
fig. 3(a) is a graph illustrating an initial matching relationship between a power X when a power device is turned on and a power Y when the power device is turned off according to an embodiment of the present invention;
fig. 3(b) is a matching relationship diagram of an amplification path of power X when the power consumption device is turned on and power Y when the power consumption device is turned off according to the embodiment of the present invention;
fig. 3(c) is a matching relationship diagram of power X when the electric device is turned on and power Y when the electric device is turned off after inverting one of the augmented paths according to the embodiment of the present invention;
fig. 3(d) is a graph illustrating an optimal matching relationship between a power X when the power consumption device is turned on and a power Y when the power consumption device is turned off according to an embodiment of the present invention;
FIG. 4 is a graph of a power load provided by an embodiment of the present invention;
fig. 5 is a schematic diagram illustrating a power load matching apparatus according to an embodiment of the present invention;
fig. 6 is a schematic diagram illustrating an arrangement of a power load matching device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The core of the invention is to provide a power load matching method, a device, equipment and a readable storage medium, which can solve the problem of how to improve the power load matching accuracy of electric equipment in a power system in the prior art.
In order that those skilled in the art will better understand the concept of the present invention, the following detailed description of the invention is provided in conjunction with the accompanying drawings and the detailed description of the invention.
Fig. 1 is a flowchart of a power load matching method according to an embodiment of the present invention, and as shown in fig. 1, the matching method includes the following steps:
s101: the method comprises the steps of obtaining target data of all electric equipment in the power system when the electric equipment is turned on and turned off to form a first power load curve of each electric equipment when the electric equipment is turned on and a second power load curve of each electric equipment when the electric equipment is turned off.
Specifically, target data of all power utilization equipment in a power system during opening and closing is acquired by adopting detection equipment, wherein the target data in the embodiment of the application mainly refers to data related to power, such as voltage, current and the like; after the corresponding target data is obtained, a first power load curve and a second power load curve, which are time-power curves, are drawn.
In consideration of the accuracy and efficiency of acquiring the target data, as a preferred embodiment, acquiring the target data when all the electric devices in the power system are turned on and off is specifically:
target data is acquired by non-invasive detection equipment.
Specifically, detection equipment is installed at an inlet side of an electric power system to realize collection of relevant target data of all electric equipment, the data collection mode is called non-invasive collection, and after relevant data (load data) are collected, power load feature extraction is required. Load characteristic data of the electric equipment is the key for accurately matching the equipment, identification and start-stop state matching of the type of the electric equipment are the crucial links in a non-invasive monitoring system, and the final identification accuracy of the system is greatly reduced due to matching errors of the type of the equipment. The current characteristics of the n electric devices in the start-stop process can be represented as follows:
wherein InCurrent I for branch IiThe amplitude resolved to the j harmonic. According to the accumulation characteristic of the instantaneous power, the active power of the electric equipment can be obtained as follows:
the reactive power is:
the branch voltage is consistent with the total inlet voltage, so that the total power is the accumulated sum of the power of each electric device in the working state, a superposed total power load curve can be obtained according to the sampling data, and the step jump of the power curve is the start-stop event of the load device.
According to the load data collected by the detection equipment on the inlet side, active power and reactive power change curves of different types of electric equipment during opening and closing can be obtained. Analysis shows that the active power of the resistance heating load (such as an electric cooker, an electric kettle and the like) is basically kept stable in steady-state operation, and large fluctuation cannot occur. The switch is usually in a jumping deformation mode at the opening and closing moment without peak phenomenon. Fig. 2(a) is a power curve diagram of the inverter air conditioner according to the embodiment of the present invention at the beginning, as shown in fig. 2(a), after the inverter air conditioner is turned on, the active power oscillates, then climbs in a climbing manner, and the reactive power gradually decreases and then gradually levels. Fig. 2(b) is a power curve diagram of the inverter air conditioner according to the embodiment of the present invention when the inverter air conditioner is turned off, as shown in fig. 2(b), when the inverter air conditioner is turned off, the active power instantaneously jumps to 0, and the reactive power generates a positive step. Fig. 2(c) is a power curve diagram of the microwave oven according to the embodiment of the present invention, as shown in fig. 2(c), the reactive power of the microwave oven first drops by about 2S after the microwave oven is turned on, then rises instantly, and then maintains a steady trend. Fig. 2(d) is a power curve diagram of the microwave oven according to the embodiment of the present invention when the microwave oven is turned off, as shown in fig. 2(d), when the microwave power is turned off, the active power is instantaneously set to 0, and the reactive power still slightly oscillates.
In practical application, in order to improve the matching accuracy of the power loads, on the basis of the above embodiment, as a preferred implementation, after acquiring target data when all the electric devices in the power system are turned on and off, the method further includes:
and preprocessing the target data. Specifically, after the target data is acquired, the data obviously not meeting the requirements is removed, and the normal target data is reserved, so that the influence on the matching result of the power load in the later period is avoided.
S102: and constructing a bipartite graph model according to each first power load curve and each second power load curve.
S103: and determining a second target power load curve matched with each first power load curve according to the bipartite graph model.
Specifically, after the first power load curves and the second power load curves are formed, a bipartite graph model is first constructed according to the first power load curves and the second power load curves. And then determining a second target power load curve matched with each first power load curve according to the constructed bipartite graph model. Namely, the matching relation between each first power load curve and each second power load curve is realized through a bipartite graph model.
Assume that n electric devices a1 to An are provided in the power system, and each electric device corresponds to An on state and An off state. The detected power change at the time of starting is X, and a starting power jump set X ═ X can be obtained1,x2,x3...xnCorrespondingly, there are n off-state power variations Y, Y ═ Y1,y2,y3...yn}. In order to find an optimal distribution scheme, the on-power and the off-power are matched, and the matching effect is the best, so that a bipartite graph model between the switching states of the equipment can be established, and an edge E is used for connection between the on-power and the off-power. At the moment, the switching matching relation among different electric equipment is converted into the optimal matching problem of solving a bipartite graph G (X, Y; E), and the obtained maximum matching is the optimal result of load matching.
And expressing the detected load opening event and the load closing event in a bipartite graph form, and corresponding the acquired data to the graphs. Fig. 3(a) is a graph illustrating an initial matching relationship between a power X when a power device is turned on and a power Y when the power device is turned off according to an embodiment of the present invention; fig. 3(b) is a matching relationship diagram of an amplification path of power X when the power consumption device is turned on and power Y when the power consumption device is turned off according to the embodiment of the present invention; fig. 3(c) is a matching relationship diagram of power X when the electric device is turned on and power Y when the electric device is turned off after inverting one of the augmented paths according to the embodiment of the present invention; fig. 3(d) is a graph illustrating an optimal matching relationship between the power X when the power consumption device is turned on and the power Y when the power consumption device is turned off according to the embodiment of the present invention. As shown in fig. 3(a), in the initial stage, isolated points (here, X2, X3, Y2 and Y4 are taken as examples) still exist in the data in X and Y, so a cost function is introduced between the data, and matching is performed by finding the optimal path, so that the minimum cost and μ are found. When matching is completed, each vertex of the left vertex set X and the right vertex set Y is connected by an edge, so that data between the two sets are ensured to be in one-to-one correspondence. I.e. each left vertex has and only one right vertex is connected to it with an edge, thus achieving the maximum match of the bipartite graph.
In order to further improve the accuracy of the matching result of the power loads, on the basis of the foregoing embodiment, as a preferred implementation, the determining, according to the bipartite graph model, the second target power load curve matched with each first power load curve specifically includes:
and determining a second target power load curve by adopting a Hungarian algorithm in a bipartite graph model.
As a preferred embodiment, the hungarian algorithm in the bipartite graph model is adopted to determine that the second target power load curve specifically is:
determining a cost matrix of the Hungarian algorithm;
calculating the matching degree of each first power load curve and each second power load curve according to the cost matrix;
and selecting the second power load curve with the highest matching degree as a second target power load curve.
Particularly, the Hungarian algorithm is used for seeking an augmentation path to obtain the optimal matchAnd the purposes of identifying the type of the electric equipment and matching start-stop data are achieved. Arbitrary match M (X) from graph G ═ (X, Y; E)1‐y1And x4‐y3) The beginning of the search for an augmented path is the core idea of the hungarian algorithm. As shown in fig. 3(a), starting from an unmatched vertex y4, the unmatched edge and the matched edge are alternately searched in sequence until an unmatched point x2 ends, and an augmented path shown in fig. 3(b) is formed. At this time, the number of matched edges is increased by one, as shown in fig. 3(c), by inverting the augmented path. This is repeated until no augmented path is found, and fig. 3(d) is obtained, in which fig. 3(d) shows the maximum matching graph of the bipartite graph model. The embodiment of the application finds the unassociated sampling points from the X set, and repeats the process by searching the augmentation path until all the nodes in the set are searched and matched with the elements in the Y, so that the perfect matching result of the power load start-stop event is obtained.
Within a period of time t, data acquisition is carried out at a power entrance, m load opening events and n closing events Y (j) can be detected according to total load data, j belongs to [1, n ], and then a mathematical model of load matching can be expressed as:
s.t.i＝1,2,...,m
j＝1,2,...,n (4)
wherein the cost parameter cijThe smaller the value of the matching degree between different jump powers, i.e. the degree of correlation between the on-load event x (i) and the off-load event y (j), the smaller the difference degree between the two, the higher the possibility of completing the matching. The cost function is defined as:
the cost matrix representing the degree of match can therefore be written as:
according to the cost matrix, perfect matching search and pairing can be performed, and in order to maximize the correlation degree between each load event, the constraint in the formula (4) should be satisfied.
For the power superposition condition caused by the simultaneous opening of the devices, the traditional Hungarian algorithm easily causes matching errors, the calculated value in the cost matrix is larger than a set threshold value alpha, and the embodiment of the application adopts the additive criterion of the characteristic value to improve the algorithm.
In the above formulanjA value representing the j characteristic of the load n, Γj(t) represents the simultaneous opening of the K loads superimposed at time t, the sum of the values of characteristic j. At time t + Δ t, if the j characteristic of the load m satisfies the above expression (7), the load identification and the matching degree can be associated by using the additivity thereof. Unknown superposed loads can be directly inferred according to the characteristic values of the database to obtain the load types running simultaneously, and the system determines that the superposed condition exists. In addition, if more than one set of best match results is involved, let
The normalized variance is expressed by the following formula:
wherein c ismaxAnd cminRepresenting the largest and smallest elements in the cost matrix C.
The original cost matrix is modified again for the original0 element, then add
For non-zero elements c is replacedmaxUsing Hungarian algorithm to solve the new matrix C*And (4) finishing.
S104: and determining the matching relation between the second target power load curve and each electric device according to the pre-stored matching relation between the first power load curve and each electric device.
Wherein the second power load curve comprises a second target power load curve.
After the matching relationship between the first power load curve and the second power load curve is obtained, the matching relationship between the second target power load curve and each electric device can be determined according to the pre-stored matching relationship between the first power load curve and each electric device. That is, the matching relationship between the first power load curve and each electric device is stored in the database in advance, and it is known that, after the matching relationship between the first power load curve and the second power load curve is determined, the embodiment of the present application is equivalent to determining the matching relationship between the second target power load curve and each electric device.
The invention provides a power load matching method, which is characterized in that a bipartite graph model is constructed according to a first power load curve and a second power load curve of electric equipment; then determining which second target power load curve in the second power load curves is matched with each first power load curve specifically through the constructed bipartite graph model; and finally, determining the matching relation between the second target power load curve and each electric device according to the pre-stored matching relation between the first power load curve and each electric device. Because the bipartite graph model is used, a large amount of prior data are not needed to be used as training samples, the clustering number is not needed to be determined in advance, a large amount of transient process data are not needed to be extracted and screened, and meanwhile, due to the superior characteristics of the bipartite graph model, the matching between the first power load curve and the second power load curve can be accurately realized, the type matching between the second power load curve and the electric equipment can be accurately realized, and the high matching rate of newly accessed equipment can be achieved. Therefore, the method can improve the matching accuracy of the power load.
In view of the convenience of the experiment, on the basis of the above embodiment, as a preferred implementation mode, the electric equipment specifically includes a variable frequency air conditioner, a microwave oven, an induction cooker and an electric kettle.
In order to make those skilled in the art better understand the scheme, the following detailed description is made in terms of practical application scenarios, and in consideration of the switching time, power variation and waveform characteristics of household common equipment, 5 types of electric equipment, namely a variable frequency air conditioner, a microwave oven, an electric cooker, an electromagnetic oven and an electric kettle, are selected in the embodiment of the application for experiments. The method comprises the following specific steps:
the method comprises the following steps that firstly, sampling equipment is connected to an inlet of an ammeter in a laboratory, voltage and current data are sampled, and data are collected every 2 s.
And secondly, respectively turning on and off the 5 experimental electric devices at different time intervals, and detecting and marking load events appearing in the data. The opening sequence is known, the closing sequence is unknown, and a steady-state load curve is drawn.
And thirdly, extracting active power jump values of the device to be started and closed after data are preprocessed, and determining the capacity of the X and Y sets.
Step four, calculating the parameter c according to the cost functionijAnd calculating a cost matrix C, and performing pre-matching by using a Hungarian algorithm in a bipartite graph model. In the embodiment of the application, the load characteristics are considered to have equal influence factors on the result factors, so that the weights are set to be the same. Arranged according to the calculated size of the cost element if cminIf the value of the threshold value alpha is larger than the threshold value alpha, the load disturbance condition or the load event superposition is considered to occur, at the moment, the identification effect is judged to be a suboptimal result, and local re-matching is carried out.
The fifth step is toAnd carrying out re-matching on different combinations, determining the weight by using the expansion characteristics, sequencing the calculation results, and outputting the optimal result. Definition of p0Setting a threshold beta for the jump of active power when the device is switched on and off, when | p0If | > β, the load is determined to be turned on or off, and a load event is generated, where β is taken as 100 in the embodiment of the present application. Defining a low power device as 100 < pmax< 1000. Therefore, the detected load change of the type is locked in the low-power device library, and the matching range is reduced. Definition of pmaxThe devices more than 1000 are high-power loads, and comparison is carried out in a high-power device library. Table 1 shows the active and reactive power of the electric devices selected in the experiment, as shown in table 1.
TABLE 1
| Identification | Electric equipment | Active power/W | Reactive power/ |
| 1 | Variable frequency air conditioner | 502.721 | -155.744 |
| 2 | Electric rice cooker | 594.273 | -2.488 |
| 3 | Microwave oven with a heat exchanger | 1207.771 | -188.861 |
| 4 | Electric kettle | 1405.548 | -8.9295 |
| 5 | Electromagnetic oven | 1566.116 | 58.274 |
The above-mentioned device was subjected to a switching-on and switching-off experiment, recording a time point T at each measurement instantiAnd collecting the data at the moment, wherein the time difference between two points is delta T-T2-T12 s. Table 2 is a relation table between the device on time and the power, and table 3 is a relation table between the device off time and the power, and the load event detection is performed on the data, so as to obtain the power variation values p, p when the 5 types of devices are turned on and off, as shown in tables 2 and 31And p2Is a critical value of the jump curve of the equipment, namely the upper peak and the lower peak of the jump curve, delta ponAnd Δ poffIs p1And p2The difference of (a).
TABLE 2
| Time point Ti1 | p1 | p2 | Δpon | (Code) |
| 104 | 79.095 | 568.088 | 488.993 | 1 frequency conversion air conditioner |
| 138 | 579.599 | 1207.021 | 627.422 | 2 electric cooker |
| 243 | 1175.678 | 2445.441 | 1269.763 | 3 microwave oven |
| 327 | 2456.718 | 3980.197 | 1523.479 | 4 electromagnetic oven |
| 423 | 4024.375 | 5477.576 | 1453.201 | 5 electric kettle |
TABLE 3
| Time point Ti2 | p1 | p2 | Δpoff | (Code) |
| 451 | 5507.236 | 4895.364 | 611.872 | A |
| 539 | 4903.549 | 3542.581 | 1360.968 | B |
| 614 | 3541.001 | 2039.736 | 1501.265 | C |
| 622 | 2025.815 | 577.529 | 1448.286 | D |
| 674 | 587.261 | 84.314 | 502.947 | E |
Fig. 4 is a power load curve chart according to the embodiment of the present invention, and the load curve in fig. 4 is plotted according to the above data, as shown in fig. 4, where 1 to 5 in fig. 4 represent powered-on electric devices, and a to E represent powered-off electric devices.
From equation (5), cost parameter c of each vertex between X set and Y set can be obtainedij. Therefore, the cost matrix that can be calculated from the above experimental data is:
and searching an augmentation path by using the Hungarian algorithm, and performing pre-matching on the data. According to multiple tests, the threshold value alpha is properly set to be 0.05-0.1 in the experiment, and the smaller the numerical value is, the more accurate the numerical value is. Multiple experiments prove that the misjudgment probability is easy to increase when alpha is more than 0.1, and the matching result is limited. When alpha is less than 0.05, the number of times of re-matching is increased, unnecessary calculation processes are circulated, and the identification speed is greatly reduced. Therefore, a suitable threshold is selected such that c existsminWhen < alpha, the best match can be obtained.
In this embodiment, alpha is taken to be 0.05 at the time of the first test, when c in the cost matrix is32The elements filter the system without being flagged, causing false positives for the superposition of load events. This is analyzed because the microwave oven belongs to an inductive load, and the operation time in the experiment is long (9.6min), wherein the load characteristics of the microwave oven are influenced by the size of the container and the change of the moisture content of the heating object, and the sampling result of the data is deviated.
Again correcting for alpha to0.1, c in the matrix3jAre all smaller than alpha, so the notation c32Is the target element. The output data is compared with the load feature library to obtain the optimal matching result shown in table 4, the matching result is completely correct, and table 4 is the matching result shown in table 4.
TABLE 4
| Status of state | Variable frequency air conditioner | Electric rice cooker | Microwave oven with a heat exchanger | Electromagnetic oven | Electric kettle |
| Is opened | 1 | 2 | 3 | 4 | 5 |
| Close off | E | A | B | C | D |
According to the matching result, the switching time of the equipment and the collected power data, the system can deduce the operation duration and the energy consumption of the equipment, and table 5 shows the operation duration and the energy consumption of the electric equipment, as shown in table 5. At this point, the process of non-intrusive load matching ends.
TABLE 5
| Categories | Air conditioner | Electric rice cooker | Microwave oven with a heat exchanger | Electromagnetic oven | Electric kettle |
| Opening time Ti1 | 104 | 138 | 243 | 327 | 423 |
| Closing time Ti2 | 674 | 451 | 539 | 614 | 622 |
| Duration of operation/h | 0.32h | 0.17h | 0.16h | 0.16h | 0.11h |
| Energy consumption/kW.h | 0.16 | 0.10 | 0.19 | 0.25 | 0.15 |
The above detailed description is directed to an embodiment of a power load matching method, and based on the power load matching method described in the above embodiment, an embodiment of the present invention further provides a power load matching device corresponding to the method. Since the embodiment of the apparatus portion and the embodiment of the method portion correspond to each other, the embodiment of the apparatus portion is described with reference to the embodiment of the method portion, and is not described again here.
Fig. 5 is a schematic diagram illustrating a power load matching apparatus according to an embodiment of the present invention, and as shown in fig. 5, the matching apparatus includes an obtaining module 501, a constructing module 502, a first determining module 503, and a second determining module 504.
An obtaining module 501, configured to obtain target data of all power consuming devices in an electric power system when the power consuming devices are turned on and off to form a first power load curve when each power consuming device is turned on and a second power load curve when each power consuming device is turned off;
a building module 502, configured to build a bipartite graph model according to each first power load curve and each second power load curve;
a first determining module 503, configured to determine, according to the bipartite graph model, second target power load curves matched with the first power load curves;
a second determining module 504, configured to determine a matching relationship between a second target power load curve and each electrical device according to a pre-stored matching relationship between the first power load curve and each electrical device;
wherein the second power load curve comprises a second target power load curve.
The invention provides a power load matching device, which is characterized in that a bipartite graph model is constructed according to a first power load curve and a second power load curve of electric equipment; then determining which second target power load curve in the second power load curves is matched with each first power load curve specifically through the constructed bipartite graph model; and finally, determining the matching relation between the second target power load curve and each electric device according to the pre-stored matching relation between the first power load curve and each electric device. Because the bipartite graph model is used, a large amount of prior data are not needed to be used as training samples, the clustering number is not needed to be determined in advance, a large amount of transient process data are not needed to be extracted and screened, and meanwhile, due to the superior characteristics of the bipartite graph model, the matching between the first power load curve and the second power load curve can be accurately realized, the type matching between the second power load curve and the electric equipment can be accurately realized, and the high matching rate of newly accessed equipment can be achieved. Therefore, the matching accuracy of the power load can be improved by applying the device.
On the basis of the foregoing embodiment, as a preferred implementation manner, the obtaining module 201 is specifically configured to obtain the target data through a non-invasive detection device.
The above detailed description is given on an embodiment of a power load matching method, and based on the power load matching method described in the above embodiment, an embodiment of the present invention further provides a power load matching device corresponding to the method. Since the embodiment of the device part and the embodiment of the method part correspond to each other, the embodiment of the device part is described with reference to the embodiment of the method part, and is not described again here.
Fig. 6 is a schematic diagram illustrating an apparatus for matching power loads according to an embodiment of the present invention, and as shown in fig. 6, the apparatus for matching power loads includes a memory 601 and a processor 602.
A memory 601 for storing a computer program;
a processor 602 for executing a computing program to implement the steps of the power load matching method provided by any of the above embodiments.
According to the power load matching equipment provided by the invention, the bipartite graph model is utilized, a large amount of prior data are not needed to be used as training samples, the clustering number is not needed to be determined in advance, and a large amount of transient process data are not needed to be extracted and screened. Therefore, the matching accuracy of the power load can be improved by applying the equipment.
The above detailed description is directed to an embodiment of a power load matching method, and based on the power load matching method described in the foregoing embodiment, an embodiment of the present invention further provides a computer-readable storage medium corresponding to the method. Since the embodiment of the computer-readable storage medium portion and the embodiment of the method portion correspond to each other, please refer to the embodiment of the method portion for describing the embodiment of the computer-readable storage medium portion, which is not described herein again.
A computer-readable storage medium having stored thereon a computer program for execution by a processor to perform the steps of the power load matching method provided by any one of the above embodiments.
According to the computer-readable storage medium provided by the invention, the processor can read the program stored in the readable storage medium, so that the power load matching method provided by any one of the embodiments can be realized, because the bipartite graph model is utilized, a large amount of prior data are not needed to be used as training samples, the clustering number is not needed to be determined in advance, and a large amount of transient process data are not needed to be extracted and screened, meanwhile, due to the superior characteristics of the bipartite graph model, the matching between the first power load curve and the second power load curve can be accurately realized, the type matching between the second power load curve and the electric equipment can be accurately realized, and a high matching rate can be achieved for newly accessed equipment. Thus, the matching accuracy of the power load can be improved.
The detailed description of the power load matching method, device, equipment and readable storage medium provided by the invention is provided above. The principles and embodiments of the present invention have been described herein using several examples, the above description of which is only intended to facilitate the understanding of the method and its core concepts of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention, and those skilled in the art should include modifications, equivalent substitutions, improvements and the like of the present invention without creative efforts.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Furthermore, the term "comprises/comprising" and the like, such that a unit, device or system comprising a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such unit, device or system.
Claims (8)
1. A power load matching method, comprising:
acquiring target data of all electric equipment in a power system when the electric equipment is turned on and turned off to form a first power load curve of each electric equipment when the electric equipment is turned on and a second power load curve of each electric equipment when the electric equipment is turned off;
constructing a bipartite graph model according to each first power load curve and each second power load curve;
determining a second target power load curve matched with each first power load curve according to the bipartite graph model;
determining a matching relation between the second target power load curve and each electric device according to a pre-stored matching relation between the first power load curve and each electric device;
wherein the second power load curve comprises the second target power load curve;
the determining, according to the bipartite graph model, a second target power load curve matched with each of the first power load curves specifically includes:
determining the second target power load curve by adopting a Hungarian algorithm in the bipartite graph model;
the determination of the second target power load curve by adopting the Hungarian algorithm in the bipartite graph model specifically comprises the following steps:
determining a cost matrix of the Hungarian algorithm;
calculating the matching degree of each first power load curve and each second power load curve according to the cost matrix;
and selecting the second power load curve with the highest matching degree as the second target power load curve.
2. The power load matching method according to claim 1, wherein the acquiring target data of all power consumption devices in the power system when the power consumption devices are turned on and off specifically comprises:
and acquiring the target data through non-invasive detection equipment.
3. The power load matching method according to claim 1, further comprising, after the obtaining target data of all power consuming devices in the power system when the power consuming devices are turned on and off:
and preprocessing the target data.
4. The power load matching method according to claim 1, wherein the electric devices specifically comprise a variable frequency air conditioner, a microwave oven, an induction cooker and an electric kettle.
5. An electrical load matching apparatus, comprising:
the acquisition module is used for acquiring target data of all electric equipment in an electric power system when the electric equipment is started and closed so as to form a first electric load curve of each electric equipment when the electric equipment is started and a second electric load curve of each electric equipment when the electric equipment is closed;
the building module is used for building a bipartite graph model according to each first power load curve and each second power load curve;
the first determining module is used for determining a second target power load curve matched with each first power load curve according to the bipartite graph model;
the second determining module is used for determining the matching relation between the second target power load curve and each electric device according to the pre-stored matching relation between the first power load curve and each electric device;
wherein the second power load curve comprises the second target power load curve;
the first determining module is further configured to determine the second target power load curve by using a Hungarian algorithm in the bipartite graph model;
the first determining module is further used for determining a cost matrix of the Hungarian algorithm;
calculating the matching degree of each first power load curve and each second power load curve according to the cost matrix;
and selecting the second power load curve with the highest matching degree as the second target power load curve.
6. The power load matching device according to claim 5, wherein the obtaining module is specifically configured to obtain the target data through a non-invasive detection device.
7. An electrical load matching apparatus, comprising:
a memory for storing a computer program;
a processor for executing the computer program to implement the steps of the power load matching method according to any one of claims 1 to 4.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which is executed by a processor to implement the steps of the power load matching method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811245423.4A CN109377052B (en) | 2018-10-24 | 2018-10-24 | Power load matching method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811245423.4A CN109377052B (en) | 2018-10-24 | 2018-10-24 | Power load matching method, device, equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109377052A CN109377052A (en) | 2019-02-22 |
| CN109377052B true CN109377052B (en) | 2022-03-11 |
Family
ID=65401903
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811245423.4A Active CN109377052B (en) | 2018-10-24 | 2018-10-24 | Power load matching method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109377052B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112241822B (en) * | 2019-07-18 | 2022-07-12 | 上海交通大学 | Method and system for distributing micro-service-oriented power resources of data center |
| CN111078803A (en) * | 2019-11-26 | 2020-04-28 | 武汉大学 | Load event multidimensional feature matching method and system based on non-invasive technology |
| CN111275271B (en) * | 2020-03-10 | 2022-09-20 | 清华大学 | Cold-heat-electricity comprehensive energy system power flow optimization method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103026246A (en) * | 2010-06-04 | 2013-04-03 | 胜赛斯美国公司 | Method and system for non-intrusive load monitoring and processing |
| CN103439573A (en) * | 2013-08-14 | 2013-12-11 | 国家电网公司 | Method and system for identifying household loads based on transient characteristic close degree matching |
| CN105067857A (en) * | 2015-08-21 | 2015-11-18 | 南方电网科学研究院有限责任公司 | Electricity consumption information acquisition system and analysis method |
| CN105186693A (en) * | 2015-09-28 | 2015-12-23 | 南方电网科学研究院有限责任公司 | Non-invasive electrical load identification system and method |
| CN106786534A (en) * | 2016-12-28 | 2017-05-31 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load transient process discrimination method and system |
-
2018
- 2018-10-24 CN CN201811245423.4A patent/CN109377052B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103026246A (en) * | 2010-06-04 | 2013-04-03 | 胜赛斯美国公司 | Method and system for non-intrusive load monitoring and processing |
| CN103439573A (en) * | 2013-08-14 | 2013-12-11 | 国家电网公司 | Method and system for identifying household loads based on transient characteristic close degree matching |
| CN105067857A (en) * | 2015-08-21 | 2015-11-18 | 南方电网科学研究院有限责任公司 | Electricity consumption information acquisition system and analysis method |
| CN105186693A (en) * | 2015-09-28 | 2015-12-23 | 南方电网科学研究院有限责任公司 | Non-invasive electrical load identification system and method |
| CN106786534A (en) * | 2016-12-28 | 2017-05-31 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load transient process discrimination method and system |
Non-Patent Citations (2)
| Title |
|---|
| 基于特征相似度的非侵入式用电负荷识别模型研究;赵云等;《电气应用》;20150630(第S1期);第199-203页 * |
| 有负荷约束的指派问题;林浩等;《经济数学》;20130331;第30卷(第1期);第17-21页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109377052A (en) | 2019-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109387712B (en) | Non-invasive load detection and decomposition method based on state matrix decision tree | |
| WO2022067562A1 (en) | Method and device for diagnosing fault arc, and computer-readable storage medium | |
| CN108616120B (en) | Non-invasive power load decomposition method based on RBF neural network | |
| CN106936129B (en) | Power load identification method and system based on multi-feature fusion | |
| CN109377052B (en) | Power load matching method, device, equipment and readable storage medium | |
| CN111564842B (en) | Method for statistical estimation of medium-and-long-term energy consumption in non-invasive electric load monitoring | |
| CN111209976B (en) | Non-invasive load monitoring method and system | |
| CN110504679B (en) | KM matching algorithm-based non-invasive load identification method | |
| CN111563827B (en) | Load decomposition method based on physical characteristics of electrical appliance and electricity utilization behaviors of residents | |
| CN110416995B (en) | Non-invasive load decomposition method and device | |
| CN111722028A (en) | Load identification method based on high-frequency data | |
| Xu et al. | A new non-intrusive load monitoring algorithm based on event matching | |
| CN111078803A (en) | Load event multidimensional feature matching method and system based on non-invasive technology | |
| CN111178393A (en) | Electric appliance power consumption classification metering method and device based on intelligent electric meter | |
| CN111898694B (en) | Non-invasive load identification method and device based on random tree classification | |
| CN113627289A (en) | Deep learning-based power equipment identification method and device | |
| Cannas et al. | NILM techniques applied to a real-time monitoring system of the electricity consumption | |
| CN116467631A (en) | Power fingerprint identification model training method, power fingerprint identification method and device | |
| CN115935267A (en) | Load data identification method and device and storage medium | |
| CN115687999A (en) | Non-invasive load sensing method fusing multi-time scale electric appliance characteristics | |
| Li et al. | A training-free non-intrusive load monitoring approach for high-frequency measurements based on graph signal processing | |
| Buchhop et al. | Residential load identification based on load profile using artificial neural network (ANN) | |
| CN110896218B (en) | Harmonic modeling method and system for establishing collective residential load | |
| CN113902136A (en) | Load identification method based on electric power fingerprint features and integrated learning mechanism | |
| Li et al. | A fusion framework using integrated neural network model for non-intrusive load monitoring |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |