CN115204698A - Real-time analysis method for power supply stability of low-voltage transformer area - Google Patents
Real-time analysis method for power supply stability of low-voltage transformer area Download PDFInfo
- Publication number
- CN115204698A CN115204698A CN202210866497.XA CN202210866497A CN115204698A CN 115204698 A CN115204698 A CN 115204698A CN 202210866497 A CN202210866497 A CN 202210866497A CN 115204698 A CN115204698 A CN 115204698A
- Authority
- CN
- China
- Prior art keywords
- sample data
- node
- neural network
- current
- layer
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 95
- 238000010223 real-time analysis Methods 0.000 title claims abstract description 17
- 238000013528 artificial neural network Methods 0.000 claims abstract description 64
- 238000012549 training Methods 0.000 claims abstract description 52
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 34
- 230000002068 genetic effect Effects 0.000 claims abstract description 28
- 238000010606 normalization Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000004927 fusion Effects 0.000 claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 12
- 230000006870 function Effects 0.000 claims description 48
- 230000008569 process Effects 0.000 claims description 48
- 230000004913 activation Effects 0.000 claims description 24
- 238000009826 distribution Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 20
- 210000000349 chromosome Anatomy 0.000 claims description 15
- 230000035772 mutation Effects 0.000 claims description 15
- 238000012546 transfer Methods 0.000 claims description 8
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 238000011478 gradient descent method Methods 0.000 claims description 4
- 238000012512 characterization method Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 229910052731 fluorine Inorganic materials 0.000 description 1
- 125000001153 fluoro group Chemical group F* 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention belongs to the technical field of electric power information, and particularly relates to a real-time analysis method for power supply stability of a low-voltage transformer area. The method is used for analyzing the current power supply area operation state according to the power monitoring data collected by the fusion terminal. The real-time analysis method comprises the following steps: s1: and acquiring the power information of each power utilization node in the transformer area under different states. S2: and carrying out normalization processing on the acquired data to obtain a sample data set. S3: and clustering the sample data set, and determining a clustering center and the number of categories. S4: and constructing a BP neural network with a three-layer structure. S5: and training the BP neural network, and optimizing the threshold of the BP neural network by combining a classical genetic algorithm. S6: and acquiring real-time electric power information, performing normalization and clustering processing, and identifying by a training BP neural network to obtain a result. The method and the device solve the problems that the data volume of the power information in the transformer area is large, the analysis difficulty is high, the power supply stability of the transformer area is difficult to predict, and the like.
Description
Technical Field
The invention belongs to the technical field of electric power information, and particularly relates to a real-time analysis method for power supply stability of a low-voltage transformer area.
Background
The electric power system is an electric energy production and consumption system which consists of links such as a power plant, a power transmission and transformation line, a power supply and distribution station, power utilization and the like. The function of the device is to convert the primary energy of the nature into electric energy through a power generation device, and then supply the electric energy to each user through power transmission, power transformation and power distribution. In order to realize coordination and control of all links, the power system also comprises an information and control system applied to all links such as power generation, power transmission, power distribution, marketing and the like, so that the production and application processes of electric energy are measured, adjusted, controlled, protected, communicated and scheduled, and a user is ensured to obtain safe and high-quality electric energy.
The development goal of modern power systems is to achieve power system automation. The fields of power system automation include automatic detection, regulation and control of production processes, automatic safety protection of systems and elements, automatic transmission of network information, automatic scheduling of system production, and automatic economic management of enterprises. The main objectives of power system automation are to ensure the quality of power supply (frequency and voltage), to ensure the safety and reliability of system operation, and to improve economic efficiency and management efficiency.
In the links of power distribution and power utilization, equipment such as intelligent electric energy meters and fusion terminals can realize remote collection of electric power information, and remote electric power monitoring and management can be realized based on collected electric power information big data. For example, in the existing power system, the integrated terminal and the intelligent electric energy meter can be used for realizing automatic meter reading in a platform area, and the functions of automatic settlement of power consumption fees and the like are realized by combining with an online payment system.
The large data of the power information can also be applied to monitoring the running state of a power system and the like, however, the power equipment in a single power distribution station area is numerous, and the load state of a power utilization node is complex; how to identify and predict the operating state of the power system through complex power information is still a technical problem to be solved urgently.
Disclosure of Invention
The invention provides a real-time analysis method for power supply stability of a low-voltage distribution room, which aims to solve the problems that the data volume of power information in the distribution room is large, the analysis difficulty is high, the power supply stability of the distribution room is difficult to predict and the like.
The invention is realized by adopting the following technical scheme:
a real-time analysis method for power supply stability of a low-voltage transformer area is used for analyzing the current power supply transformer area operation state according to power monitoring data collected by a fusion terminal. The real-time analysis method comprises the following steps:
s1: and acquiring power information of each power utilization node in the transformer area in different states as sample data of the current node. The sample data includes: supply voltage V of current node 1 Supply current I 1 Power factor of the power converter
The line loss rate Δ P; device voltage V of transformer in transformer area 2 Device current I 2 Real-time load P and equipment temperature T; and other associated data related to the operating state of the grid.
S2: according to the theoretical safety threshold of each item of data in the operation process, a large amount of collected sample data is respectively subjected to normalization processing, and then a sample data set containing all the normalization sample data is obtained.
S3: clustering the sample data set of each node based on a self-adaptive fast search density peak value method, determining the clustering center and the category number, and obtaining the node attribute data set after clustering.
S4: a BP neural network with a three-layer structure is constructed, and comprises an input layer, a hidden layer and an output layer. In the BP neural network, the number n of nodes of an input layer is equal to the number of power utilization nodes in the current transformer area; the number of nodes of the output layer is 1, and the number of nodes of the hidden layer is 2n +1.
S5: and (3) taking a large number of node attribute data sets in different operation states collected in advance as training samples, training the BP neural network constructed in the previous step by using the training samples, and updating the weight of the network model. Meanwhile, the threshold value of the BP neural network is optimized by combining a classical genetic algorithm in the training process. And the trained BP neural network is used as a required platform area operation state identification model.
S6: real-time power information of the transformer area and all power utilization nodes in the transformer area is collected through the fusion terminal, and real-time node attribute data sets are obtained after normalization and clustering processing are sequentially carried out on the real-time power information. And then inputting the real-time node attribute data set into the trained platform area running state recognition model, and outputting the real-time running state of the current platform area by the model.
The real-time running state of the transformer area is divided into normal and abnormal.
In the invention, the supply voltage V 1 Supply current I 1 Voltage V of the device 2 Device current I 2 Respectively corresponding to the voltage and current of each phase A, B and C; the method specifically comprises the following steps: v 1A 、V 1B 、V 1C ，I 1A 、I 1B 、I 1C ，V 2A 、V 2B 、V 2C ，I 2A 、I 2B 、I 2C 。
As a further improvement of the present invention, in step S2, the normalization processing formula of the sample data is as follows:
in the above formula, x represents the measured value of the current sample data;
representA normalized value of current sample data; x is the number of max Representing the theoretical safety threshold upper limit of the current sample data; x is the number of min Representing a theoretical safety threshold lower limit of the current sample data; when some sample data does not have the lower limit of the safety threshold, x min ＝0。
As a further improvement of the present invention, in step S3, the adaptive fast peak density search method clusters the multi-node sample data sets as follows:
s31: acquiring a sample data set of any node, and calculating the Euclidean distance d between any two sample data in the sample data set ij The calculation formula is as follows:
in the above formula, a represents the sample data set, and N represents the number of data points in the sample data set a; x is the number of i And x j Representing two random data points in the sample data set A; dist () represents a euclidean distance computation function.
S32: according to Euclidean distance between the sample data and all other data points and preset truncation distance d 0 The local density rho of each data point in the sample data is calculated i (ii) a The calculation formula is as follows:
wherein,
representing a self-defined classification function for distinguishing whether the Euclidean distance between the data point and the central point is less than the truncation distance, and satisfying the following conditions:
s33: based on the number of samplesCalculating the local density of each data point of the data set, and calculating the distance theta between the sample data and the density center i The calculation process is as follows:
judging whether the local density of the current data point is the maximum value in the sample data set:
(1) If yes, the current data point x is i The maximum distance from other data points in the sample dataset is taken as θ i The calculation formula is as follows: theta i ＝max j (d ij )，j＝N。
(2) Otherwise, the local density in the sample data set is larger than the data point x of the current data point j With the current data point x i Is taken as the minimum distance of i (ii) a The calculation formula is as follows: theta i ＝min(d ij )，x j :ρ j ＞ρ i 。
S34: according to rho of each sample data in the sample data set i And theta i And drawing a decision graph. The abscissa of each sample point in the decision graph is p i Ordinate of theta i (ii) a And determining the clustering center and the category number according to the decision graph.
In the invention, the category number of the node attribute data set is 3; the category of each clustering center is determined by the corresponding power utilization node state. The classification of each node in the node attribute dataset is "underloaded", "stationary" or "overloaded"
As a further improvement of the present invention, in the BP neural network constructed in step S4,
the hyperbolic tangent function Tanh is adopted between the input layer and the hidden layer as an activation function, and the Tanh activation function is as follows:
a nonlinear transformation function Sigmoid is adopted between the hidden layer and the output layer as an activation function, the Sigmoid value range is (0, 1), and the two layers are monotonous and continuous and can be microscopically arranged everywhere, so that the two-classification output can be realized. The expression of Sigmoid activation function is as follows:
as a further improvement of the present invention, in the BP neural network constructed in step S4,
the input layer to hidden layer transfer formula is:
in the above formula, x i For an input value of an ith input layer, i = N, N representing the number of nodes of the input layer; h 1j For the output of the jth node of the hidden layer, j =2N +1; f. of 1 As a function of Tanh activation, ω ij Is the weight value, x, between the ith node of the input layer and the jth node of the hidden layer i Is an input value of an ith node of the input layer, a j Is the threshold of the jth node of the hidden layer.
The transfer formula from the hidden layer to the output layer is as follows;
in the above formula, y is the output value of the output layer, f 2 For Sigmoid activation functions, ω j The weight between the jth node of the hidden layer and the output layer, and b is the output layer threshold.
As a further improvement of the present invention, in step S5, the training process of the BP neural network is as follows:
s51: setting initial training parameters: including the number of iterations; target minimum error, learning rate η.
S52: node attribute data sets in different operation states collected in advance are used as training samples, and the training samples are propagated forward by using a BP neural network.
S53: calculating the sum of squares E of absolute values of relative errors of the predicted output and the expected output of the output layer in each round of forward propagation process, and judging whether a target minimum error is met:
(1) If yes, the training process of the network model is completed.
(2) Otherwise, entering a back propagation process.
S54: and performing a back propagation process by adopting a gradient descent method, and dynamically updating the weight of the output layer and the weight between the input layer and the hidden layer according to a weight updating formula from the hidden layer to the output layer and a weight updating formula between the input layer and the hidden layer.
S55: and continuously inputting the training samples into the BP neural network after the weight value is updated, and repeating the forward propagation of the next round.
S56: and looping the steps S53-S54 until a preset iteration number is reached, or the sum of the squares of the absolute values of the relative errors of the predicted output and the expected output of the network model meets the requirement of the target minimum error.
As a further improvement of the present invention, in step S54, the weight update formula between the input layer and the hidden layer is as follows:
in the above formula, ω i ′ j Representing the updated weight between the ith node of the input layer and the jth node of the hidden layer;
representing an expected output of the current input sample in the network model, y representing an actual output of the current input sample in the network model; e represents the sum of the squares of the relative errors of the desired output and the actual output.
The weight updating formula from the hidden layer to the output layer is as follows:
in the above formula, ω j ' denotes a weight between the jth node of the updated hidden layer and the output layer.
As a further improvement of the present invention, in step S5, the process of optimizing the threshold of the BP neural network by using the classical genetic algorithm is as follows:
s01: and converting the threshold value of the BP neural network into a corresponding chromosome individual by adopting a real number coding mode, and further randomly generating an initial population containing a plurality of chromosome individuals.
S02: setting an iteration termination condition of a classical genetic algorithm as training phase synchronization of a BP neural network, and performing iterative optimization on an initial population by using the classical genetic algorithm, wherein each iteration comprises the following contents;
s021: and calculating the fitness of each chromosome in the initial population by using a preset fitness function.
S022: and selecting the initial population by adopting a selection operator of a classical genetic algorithm.
S023: and performing cross operation on the initial population by adopting a cross operator of a classical genetic algorithm.
S024: and (4) carrying out mutation operation on the initial population by adopting a mutation operator of a classical genetic algorithm.
S03: and in each round of population iteration process, outputting the threshold value of the chromosome characterization with the maximum fitness to the BP neural network as the threshold value of the BP neural network in the next training round.
As a further improvement of the invention, in the classical genetic algorithm adopted by the invention, the selection operator adopts an elite reservation operator. The crossover operator calculates the similarity between any two individuals of the current population through a self-defined similarity function, and then performs double-point crossover on the two individuals with the lowest similarity. And the mutation operator performs single-point mutation on the chromosomes with the highest fitness and the lowest fitness according to a preset mutation probability.
The technical scheme provided by the invention has the following beneficial effects:
the invention designs a novel identification method of power supply stability of a transformer area, which is characterized in that firstly, acquired power data of different nodes of the transformer area are normalized into standard data and then into a sample data set, then the sample data set of each node is clustered through a self-adaptive fast density peak value searching method, finally, the clustered multi-node attribute data set is input into a model based on a BP (back propagation) neural network, the model identifies the power supply stability state of the transformer area according to a predicted sample, and an identification result is output.
The constructed BP neural network is trained by combining the collected sample data set, and the classical genetic algorithm is applied to the updating of the network model threshold in the training process, so that the iteration period of the training stage of the network model is effectively shortened, and the identification precision of the model is improved.
Based on the identification method provided by the invention, massive transformer area power information can be analyzed and processed, and an analysis result can be quickly obtained. The identification method provided by the invention not only has higher identification accuracy, but also improves the real-time performance of the algorithm. And the network model provided by the invention can be automatically learned according to the recognition result in the application process, so that the recognition accuracy of the method can be continuously improved.
Drawings
Fig. 1 is a flowchart illustrating steps of a method for analyzing power supply stability of a low-voltage distribution area in real time according to embodiment 1 of the present invention.
Fig. 2 is a flowchart of a signal step of clustering a multi-node sample data set by the adaptive fast peak density searching method in embodiment 1 of the present invention.
Fig. 3 is a flowchart of the procedure of the training phase of the BP neural network constructed in embodiment 1 of the present invention.
Fig. 4 is a flowchart of a procedure for optimizing the BP neural network threshold value by using a classical genetic algorithm in embodiment 1 of the present invention.
Fig. 5 is a system architecture diagram of a platform power supply stability monitoring system based on a convergence terminal according to embodiment 2 of the present invention.
Fig. 6 is a topological diagram of a power supply stability monitoring system of a platform based on a convergence terminal.
Fig. 7 is a network architecture diagram of a BP neural network model constructed in embodiment 2 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Example 1
The embodiment provides a real-time analysis method for power supply stability of a low-voltage transformer area, which is used for analyzing the current power supply transformer area operation state according to power monitoring data collected by a fusion terminal. As shown in fig. 1, the real-time analysis method specifically includes the following steps:
s1: and acquiring power information of each power utilization node in the transformer area in different states as sample data of the current node. The sample data includes: supply voltage V of current node 1 Supply current I 1 Power factor of the power converter
The line loss rate Δ P. Device voltage V of transformer in transformer area 2 Device current I 2 Real-time load P and equipment temperature T. And other associated data related to the operating state of the grid.
In addition to the abnormality caused by equipment failure or other accidents in the existing power grid, the most frequent causes influencing the stable operation of the power grid are imbalance of supply and demand and impact on the power grid caused by power demand fluctuation of a user side. Therefore, the real-time analysis of the power supply stability of the embodiment mainly analyzes the power supply and demand balance relationship through the power information of the power supply side and the user side in the power grid, and analyzes and predicts the possible abnormal state.
Specifically, the supply voltage V collected in the present embodiment 1 Supply current I 1 Voltage V of the device 2 Device current I 2 Respectively corresponding to the voltage and current of each phase A, B and C; the method comprises the following steps: v 1A 、V 1B 、V 1C ，I 1A 、I 1B 、I 1C ，V 2A 、V 2B 、V 2C ，I 2A 、I 2B 、I 2C 。
The power factor refers to the ratio of active power to on-line power of the alternating current circuit; is a coefficient for measuring the efficiency of the electrical equipment. The power factor is low, which indicates that the reactive power of the circuit for alternating magnetic field conversion is large, thereby reducing the utilization rate of equipment and increasing the power supply loss of a line. The power factor is related to the load properties of the grid circuit; is also an important technical index for evaluating the power system.
The line loss rate is the percentage of the electrical energy lost in the grid (line loss load) to the supply of electrical energy to the power network (supply load). The line loss rate may assess the economics of the operation of the power system. The line loss rate is related to the load power factor of the power grid, the voltage supplied to the load by the power system changes along with the change of the active power and the reactive power transmitted by the line, and when the active power transmitted by the line and the voltage at the starting end are unchanged, the more the reactive power transmitted, the greater the voltage loss of the line, and the higher the line loss rate. Therefore, when the power factor is improved, the reactive power which is absorbed by the load to the system is reduced, the voltage loss of the line is correspondingly reduced, and the line loss rate is reduced.
The equipment temperature is an index for evaluating the tolerance of the transformer equipment, heat dissipation is required in the running process of the transformer, and when the real-time load of the transformer is increased, the equipment temperature is correspondingly increased. If the environment temperature and other conditions cause the transformer to be unable to effectively dissipate heat, the equipment temperature of the transformer may rise rapidly, which may cause the transformer to be unable to operate according to the rated load, thereby affecting the normal power supply in the transformer area. Therefore, the present embodiment also needs to take the device temperature of the transformer into account when analyzing the grid operating state.
S2: and respectively carrying out normalization processing on a large amount of collected sample data according to the theoretical safety threshold of each item of data in the operation process, and further obtaining a sample data set containing all the normalized sample data.
The normalization processing formula of the sample data is as follows:
in the above formula, x represents the measured value of the current sample data;
a normalized value representing current sample data; x is the number of max Representing the theoretical safety threshold upper limit of the current sample data; x is the number of min Representing a theoretical safety threshold lower limit of the current sample data; when some sample data does not have the lower limit of the safety threshold, x min ＝0。
In this embodiment, the dimensions and the dimension units of each item of data used are different from each other, and it is relatively unfavorable to perform data analysis in the later period, and the embodiment eliminates the dimension influence between different index items through normalization processing. In the embodiment, after normalization processing, data of different dimensions are mapped to a (-1, 1) interval, so that data indexes have comparability. After the raw data is subjected to data standardization processing, all indexes are in the same order of magnitude, and the method is suitable for comprehensive comparison and evaluation.
S3: clustering the sample data set of each node based on a self-adaptive fast search density peak value method, determining the clustering center and the category number, and obtaining the node attribute data set after clustering.
As shown in fig. 2, the process of clustering the multi-node sample data set by the adaptive fast search density peak method is as follows:
s31: acquiring a sample data set of any node, and calculating the Euclidean distance d between any two sample data in the sample data set ij The calculation formula is as follows:
in the above formula, a represents the sample data set, and N represents the number of data points in the sample data set a; x is a radical of a fluorine atom i And x j Representing two random data points in the sample data set A; dist () represents a euclidean distance computation function.
S32: according to Euclidean distance between the sample data and all other data points and preset sectionDistance d of interruption 0 The local density rho of each data point in the sample data is calculated i . The calculation formula is as follows:
wherein,
representing a self-defined classification function for distinguishing whether the Euclidean distance between the data point and the central point is less than the truncation distance, and satisfying the following conditions:
s33: based on the local density of each data point of the sample data set, calculating the distance theta between the sample data and the density center i . The calculation process is as follows:
judging whether the local density of the current data point is the maximum value in the sample data set:
(1) If yes, the current data point x is i The maximum distance from other data points in the sample dataset is taken as θ i The calculation formula is as follows: theta i ＝max j (d ij )，j＝N。
(2) Otherwise, the local density in the sample data set is larger than the data point x of the current data point j With the current data point x i Is taken as the minimum distance of i (ii) a The calculation formula is as follows: theta i ＝min(d ij )，x j :ρ j ＞ρ i 。
S34: according to rho of each sample data in the sample data set i And theta i And drawing a decision graph. The abscissa of each sample point in the decision graph is p i Ordinate of theta i (ii) a And determining the clustering center and the category number according to the decision graph.
Specifically, the category of each cluster center is determined by the corresponding power utilization node state. In this embodiment, the number of categories of the node attribute data set is 3; the classification of each node in the node attribute dataset is "underloaded", "smooth" or "overloaded".
The adaptive fast density peak searching method provided by the embodiment determines the clustering center by analyzing the densities of different data points, and the basis for realizing clustering is that the density of the clustering center is greater than that of the neighboring points around the clustering center. The method can automatically acquire the number of categories according to the collected data set, does not need to determine an initial clustering center, but quickly finds the density peak of the data set with any shape by utilizing the characteristic that the local density of the category center is always higher than that of the nearest neighbor point, effectively distributes non-central sample points, and determines the clustering center by utilizing a decision diagram. The self-adaptive fast density peak searching method provided by the embodiment is suitable for multi-class clustering, and the clustering processing efficiency is obviously improved.
S4: a BP neural network with a three-layer structure is constructed, and comprises an input layer, a hidden layer and an output layer. In the BP neural network, the number n of nodes of an input layer is equal to the number of power consumption nodes in the current distribution area; the number of output layer nodes is 1 and the number of hidden layer nodes is 2n +1.
In the constructed BP neural network, the BP neural network is obtained,
and a hyperbolic tangent function Tanh is adopted between the input layer and the hidden layer as an activation function, wherein the Tanh activation function is as follows:
a nonlinear transformation function Sigmoid is adopted between the hidden layer and the output layer as an activation function, the Sigmoid value range is (0, 1), and the two-class output can be realized because the Sigmoid value range is monotonous and continuous and can be tiny everywhere. The expression of Sigmoid activation function is as follows:
the input layer to hidden layer transfer formula is:
in the above formula, x i For an input value of an ith input layer, i = N, N representing the number of nodes of the input layer; h 1j For the output of the jth node of the hidden layer, j =2N +1; f. of 1 As a function of Tanh activation, ω ij Is the weight value, x, between the ith node of the input layer and the jth node of the hidden layer i Is an input value of the ith node of the input layer, a j Is the threshold of the jth node of the hidden layer.
The transfer formula from the hidden layer to the output layer is as follows;
in the above formula, y is the output value of the output layer, f 2 For Sigmoid activation functions, ω j The weight between the jth node of the hidden layer and the output layer, and b is the threshold of the output layer.
S5: and (3) taking a large number of node attribute data sets in different operation states collected in advance as training samples, training the BP neural network constructed in the previous step by using the training samples, and updating the weight of the network model. Meanwhile, the threshold value of the BP neural network is optimized by combining a classical genetic algorithm in the training process. And the trained BP neural network is used as a required platform area operation state identification model.
In this embodiment, as shown in fig. 3, the training process of the BP neural network is as follows:
s51: setting initial training parameters: including the number of iterations; target minimum error, learning rate η.
S52: node attribute data sets in different operation states collected in advance are used as training samples, and the training samples are propagated forward by using a BP neural network.
S53: calculating the sum of squares E of absolute values of relative errors of the predicted output and the expected output of the output layer in each round of forward propagation process, and judging whether a target minimum error is met:
(1) If yes, the training process of the network model is completed.
(2) Otherwise, entering a back propagation process.
S54: and performing a back propagation process by adopting a gradient descent method, and dynamically updating the weight of the output layer and the weight between the input layer and the hidden layer according to a weight updating formula from the hidden layer to the output layer and a weight updating formula between the input layer and the hidden layer.
Specifically, the weight update formula between the input layer and the hidden layer is as follows:
in the above formula, ω i ′ j Representing the updated weight between the ith node of the input layer and the jth node of the hidden layer;
representing the expected output of the current input sample in the network model, and y representing the actual output of the current input sample in the network model; e represents the sum of the squares of the relative errors of the desired output and the actual output.
The weight updating formula from the hidden layer to the output layer is as follows:
in the above formula, ω j ' denotes a weight between the jth node of the updated hidden layer and the output layer.
S55: and continuously inputting the training samples into the BP neural network after the weight value is updated, and repeating the forward propagation of the next round.
S56: and looping the steps S53-S54 until a preset iteration number is reached, or the sum of the squares of the absolute values of the relative errors of the predicted output and the expected output of the network model meets the requirement of the target minimum error.
S6: real-time power information of the transformer area and all power utilization nodes in the transformer area is collected through the fusion terminal, and real-time node attribute data sets are obtained after normalization and clustering processing are sequentially carried out on the real-time power information. And then inputting the real-time node attribute data set into the trained platform area running state recognition model, and outputting the real-time running state of the current platform area by the model. The real-time running state of the transformer area is divided into normal and abnormal.
In particular, in the present embodiment, as shown in fig. 4, the process of optimizing the threshold of the BP neural network by using the classical genetic algorithm is as follows:
s01: and converting the threshold value of the BP neural network into a corresponding chromosome individual by adopting a real number coding mode, and further randomly generating an initial population containing a plurality of chromosome individuals.
S02: setting the iteration termination condition of the classical genetic algorithm as the training phase synchronization of the BP neural network, and performing iterative optimization on the initial population by using the classical genetic algorithm, wherein each iteration comprises the following contents:
s021: and calculating the fitness of each chromosome in the initial population by using a preset fitness function.
S022: and selecting the initial population by adopting a selection operator of a classical genetic algorithm.
S023: and carrying out cross operation on the initial population by adopting a cross operator of a classical genetic algorithm.
S024: and (3) carrying out mutation operation on the initial population by adopting a mutation operator of a classical genetic algorithm.
S03: and in each round of population iteration process, outputting the threshold value of the chromosome characterization with the maximum fitness to the BP neural network as the threshold value of the BP neural network in the next training round.
In the classical genetic algorithm employed in this embodiment, the selection operator employs an elite retention operator. The crossover operator calculates the similarity between any two individuals of the current population through a self-defined similarity function, and then performs double-point crossover on the two individuals with the lowest similarity. And the mutation operator performs single-point mutation on the chromosomes with the highest fitness and the lowest fitness according to a preset mutation probability.
In the final stage of the technical scheme, the present embodiment adopts a BP neural network to complete a task of predicting a power supply stability state of a power grid according to node attribute data sets of different nodes. And the BP neural network adopts a successive approximation mode, and carries out error analysis on the obtained result and the expected result in the continuous algorithm training process, so as to modify the weight and the threshold value and obtain a model which can be output and is consistent with the expected result in one step. Particularly, in order to improve the training effect of the network model, the embodiment also introduces the genetic algorithm into the threshold updating process of the network model, so as to significantly improve the convergence rate of the BP neural network model. The trained network model has higher response speed, so that the power supply state of the transformer area can be dynamically evaluated according to the data acquired in real time.
Example 2
On the basis of embodiment 1, this embodiment further provides a power supply stability monitoring system for a distribution room based on a convergence terminal, where the monitoring is used to collect power information of a transformer and each power consumption node of the distribution room, and further, by using the collected power information, the operation state of the distribution room is analyzed online by using the real-time analysis method for power supply stability of a low-voltage distribution room as in embodiment 1, so as to predict power supply stability of the distribution room.
As shown in fig. 5, the monitoring system provided in this embodiment includes a data acquisition device and a master station server. The data acquisition equipment is installed at the field of the power distribution station, and the master station server is arranged at the cloud end. The data acquisition equipment is in communication connection with the master station server.
Wherein, data acquisition equipment includes: intelligent ammeter, concentrator and fusion terminal. The intelligent electric energy meter is installed at the power utilization node of each power consumer and used for collecting power information of a user side. The concentrator is used for obtaining the collected data of the intelligent electric energy meters at all the power utilization nodes. The concentrator is in communication connection with the convergence terminal, and the concentrator sends the acquired data from the different power consumption nodes to the convergence terminal in a unified manner. The fusion terminal is also electrically connected with a transformer of a transformer area of the low-voltage power grid, so that power information of the power grid side is obtained. The fusion terminal is in communication connection with the master station server, and sends the synchronously acquired user side power information and the power information of the power grid side to the master station server.
As shown in fig. 6, a data normalization module, a clustering model based on the adaptive fast search density peak algorithm, and a station operation state identification model based on the BP neural network are operated in the master station server. The data normalization module is used for performing normalization processing on the collected power information so as to obtain a sample data set containing the normalized data of all the nodes. The clustering model is used for clustering the sample data sets of all the nodes, determining the number of categories and the clustering center, and obtaining a node attribute data set containing state information of all the nodes. The transformer area operation state identification model is used for predicting the current power supply stability state of the transformer area according to the node attribute data set; the clustering centers of the clustering models are three and respectively correspond to the underload state, the steady state or the overload state of the nodes. The prediction result of the platform area operation state recognition model is divided into a normal state and an abnormal state.
The concentrator is in communication connection with the intelligent electric meter through an RS485 serial bus interface. The fusion terminal is in communication connection with the concentrator and the transformer area voltage device in an Ethernet or power carrier communication mode. The fusion terminal is in communication connection with the master station server through 4G and 5G mobile communication or Ethernet communication modes.
In this embodiment, the electric power information of the user side collected by the convergence terminal includes: supply voltage V 1 Supply current I 1 Power factor of the power converter
The line loss rate Δ P. The grid-side power information includes: device voltage V of transformer in transformer area 2 Device current I 2 Real-time load P and equipment temperature T.
The normalization module is used for mapping the data of different dimensions to the (-1, 1) interval by adopting a normalization formula, and the normalization formula is as follows:
wherein, x represents the measured value of the current sample data;
a normalized value representing the current sample data; x is the number of max Representing the theoretical safety threshold upper limit of the current sample data; x is the number of min Representing the theoretical lower safety threshold for the current sample data. When some sample data does not have the lower limit of the safety threshold, x min ＝0。
In the monitoring system, a clustering model adopts a clustering model of an adaptive fast search density peak algorithm to cluster a sample data set, and the clustering process of the model is as follows:
firstly, a sample data set of any node is obtained, and the Euclidean distance d between any two sample data in the sample data set is calculated ij The calculation formula is as follows:
in the above formula, a represents a sample data set, and N represents the number of data points in the sample data set a; x is the number of i And x j Representing two random data points in the sample data set A; dist () represents a euclidean distance computation function.
Secondly, according to Euclidean distance between the sample data and all other data points and preset truncation distance d 0 The local density rho of each data point in the sample data is calculated i (ii) a The calculation formula is as follows:
wherein,
representing a self-defined classification function for distinguishing whether the Euclidean distance between the data point and the central point is less than the truncation distance, and satisfying the following conditions:
then, based on the local density of each data point of the sample data set, the distance theta between the sample data and the density center is calculated i The calculation process is as follows: judging whether the local density of the current data point is the maximum value in the sample data set: if yes, the current data point x is i The maximum distance from other data points in the sample dataset is taken as θ i The calculation formula is as follows: theta i ＝max j (d ij ) J = N. Otherwise, the local density in the sample data set is larger than the data point x of the current data point j And the current data point x i Is taken as the minimum distance of i (ii) a The calculation formula is as follows: theta i ＝min(d ij )，x j :ρ j ＞ρ i 。
Finally, according to rho of each sample data in the sample data set i And theta i And drawing a decision graph. The abscissa of each sample point in the decision graph is p i Ordinate of theta i (ii) a And determining the clustering center and the category number according to the decision graph.
The identification model of the operating state of the distribution room constructed in the embodiment is a BP neural network with a three-layer structure. As shown in fig. 7, the BP neural network includes an input layer, a hidden layer, and an output layer. The number of nodes of the input layer is equal to the number of power consumption nodes in the current distribution area, and the number of nodes of the output layer is 1; implicit tier node count =2 input tier node count + 1.
In the BP neural network, a hyperbolic tangent function Tanh is adopted between an input layer and a hidden layer as an activation function, and the Tanh activation function is as follows:
a nonlinear transformation function Sigmoid is adopted between the hidden layer and the output layer as an activation function; the expression of Sigmoid activation function is as follows:
in the BP neural network constructed in this embodiment, the transfer formula from the input layer to the hidden layer is:
in the above formula, x i For the input value of the ith input layer, i = N, and N represents the number of nodes of the input layer. H 1j J =2N +1 for the output of the jth node of the hidden layer. f. of 1 As a function of Tanh activation, ω ij Is the weight value, x, between the ith node of the input layer and the jth node of the hidden layer i Is an input value of the ith node of the input layer, a j Is the threshold of the jth node of the hidden layer.
The transfer formula from the hidden layer to the output layer is:
in the above formula, y is the output value of the output layer, f 2 For Sigmoid activation functions, ω j The weight between the jth node of the hidden layer and the output layer, and b is the threshold of the output layer.
In the identification model of the operating state of the platform area provided in this embodiment, the training process of the BP neural network is as follows:
s1: setting initial training parameters: including the number of iterations; target minimum error, learning rate η.
S2: node attribute data sets in different operation states collected in advance are used as training samples, and the training samples are propagated forward by using a BP neural network.
S3: calculating the sum of squares of absolute values of relative errors of the predicted output and the expected output of the output layer in each round of forward propagation process, and judging whether a target minimum error is met:
(1) If yes, the training process of the network model is completed.
(2) Otherwise, entering a back propagation process.
S4: and performing a back propagation process by adopting a gradient descent method, and dynamically updating the weight of the output layer and the weight between the input layer and the hidden layer according to a weight updating formula from the hidden layer to the output layer and a weight updating formula between the input layer and the hidden layer.
Wherein, the weight updating formula between the input layer and the hidden layer is as follows:
in the above formula, ω i ′ j Representing the updated weight between the ith node of the input layer and the jth node of the hidden layer,
represents the expected output of the current input sample in the network model, y represents the actual output of the current input sample in the network model, and E represents the sum of the squares of the relative errors of the expected output and the actual output.
The weight updating formula from the hidden layer to the output layer is as follows:
in the above formula, ω j ' denotes a weight between the jth node of the updated hidden layer and the output layer.
S5: and continuously inputting the training samples into the BP neural network after the weight value is updated, and repeating the forward propagation of the next round.
S6: and (5) circulating the steps S3-S4 until a preset iteration number is reached, or the sum of squares of absolute values of relative errors of the predicted output and the expected output of the network model meets the requirement of the target minimum error.
In the embodiment, the iteration times and the error which are smaller than the preset value are simultaneously used as the conditions for ending the iteration, and when any one of the two conditions is reached, the recursive process of the training of the planting algorithm is performed.
In this embodiment, in order to improve the training effect and the convergence rate of the algorithm model, a genetic algorithm is further used for threshold optimization in the training process of the BP neural network, and the optimization process is described in detail in the foregoing embodiments as follows, and is not described in detail in this embodiment.
Example 3
The present implementation provides a real-time analysis apparatus for power supply stability of a low-voltage distribution area, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the method for analyzing the power supply stability of the low-voltage distribution room in real time as in embodiment 1 are implemented, and then the prediction result of the power supply stability of the distribution room is analyzed according to the collected power information in the distribution room.
The computer device may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server or a cabinet server (including an independent server or a server cluster composed of a plurality of servers) capable of executing programs, and the like. The computer device of the embodiment at least includes but is not limited to: a memory, a processor communicatively coupled to each other via a system bus.
In this embodiment, the memory (i.e., the readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the computer device. Of course, the memory may also include both internal and external storage units of the computer device. In this embodiment, the memory is generally used for storing an operating system, various types of application software, and the like installed in the computer device. In addition, the memory may also be used to temporarily store various types of data that have been output or are to be output.
The processor may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor is typically used to control the overall operation of the computer device. In this embodiment, the processor is configured to execute the program code stored in the memory or process data.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A real-time analysis method for power supply stability of a low-voltage transformer area is used for analyzing the current power supply transformer area operation state according to power monitoring data collected by a fusion terminal; the real-time analysis method is characterized by comprising the following steps:
s1: acquiring power information of each power utilization node in the transformer area under different states as sample data of the current node; the sample data includes: supply voltage V of current node 1 Supply current I 1 Power factor of the power converter
The line loss rate Δ P; device voltage V of transformer in transformer area 2 Device current I 2 Real-time load P and equipment temperature T; and other associated data related to the operating state of the power grid;
s2: respectively carrying out normalization processing on a large number of collected sample data according to a theoretical safety threshold value of each item of data in the operation process, and further obtaining a sample data set containing all the normalized sample data;
s3: clustering the sample data set of each node based on a self-adaptive fast search density peak value method, determining a clustering center and a category number, and obtaining a node attribute data set after clustering is completed;
s4: constructing a BP neural network with a three-layer structure; the BP neural network comprises an input layer, a hidden layer and an output layer; the number n of nodes of the input layer is equal to the number of power consumption nodes in the current distribution area, the number of nodes of the output layer is 1, and the number of nodes of the hidden layer is 2n +1;
s5: using a large number of node attribute data sets in different operation states collected in advance as training samples, training the BP neural network constructed in the last step by using the training samples, and updating the weight of a network model; optimizing the threshold of the BP neural network by combining a classical genetic algorithm in the training process; the trained BP neural network is used as a required platform area operation state identification model;
s6: acquiring real-time power information of a transformer area and all power utilization nodes in the transformer area through a fusion terminal, sequentially carrying out normalization and clustering processing on the real-time power information to obtain a real-time node attribute data set, inputting the real-time node attribute data set into a trained identification model of the running state of the transformer area, and outputting the real-time running state of the current transformer area through the model; the real-time running state of the transformer area is divided into normal and abnormal.
2. The method for analyzing the power supply stability of the low-voltage transformer area in real time as claimed in claim 1, wherein: the supply voltage V 1 Supply current I 1 Voltage V of the device 2 Device current I 2 Respectively corresponding to the voltage and current of each phase A, B and C; the method comprises the following steps: v 1A 、V 1B 、V 1C ，I 1A 、I 1B 、I 1C ，V 2A 、V 2B 、V 2C ，I 2A 、I 2B 、I 2C 。
3. The method for analyzing the power supply stability of the low-voltage transformer area in real time as claimed in claim 2, wherein: in step S2, the normalization processing formula of the sample data is as follows:
in the above formula, x represents the measured value of the current sample data;
a normalized value representing the current sample data; x is the number of max Representing the theoretical safety threshold upper limit of the current sample data; x is the number of min Representing the lower limit of a theoretical safety threshold of the current sample data; wherein, when some sample data has no lower limit of safety threshold, then x min ＝0。
4. The method for analyzing the power supply stability of the low-voltage transformer area in real time as claimed in claim 1, wherein: in step S3, the adaptive fast density peak searching method performs clustering on the multi-node sample data sets as follows:
s31: acquiring a sample data set of any node, and calculating the Euclidean distance d between any two sample data in the sample data set ij The calculation formula is as follows:
in the above formula, a represents the sample data set, and N represents the number of data points in the sample data set a; x is the number of i And x j Representing two random data points in the sample data set A; dist () represents a euclidean distance computation function;
s32: according to Euclidean distance between the sample data and all other data points and preset truncation distance d 0 The local density rho of each data point in the sample data is calculated i (ii) a The calculation formula is as follows:
wherein,
representing a self-defined classification function for distinguishing whether the Euclidean distance between the data point and the central point is less than the truncation distance, and satisfying the following conditions:
s33: calculating the distance theta between the sample data and the density center based on the local density of each data point of the sample data set i The calculation process is as follows: judging whether the local density of the current data point is the maximum value in the sample data set or not; if yes, the current data point x is i The maximum distance from other data points in the sample dataset is taken as θ i The calculation formula is as follows: theta i ＝max j (d ij ) J = N; otherwise, the local density in the sample data set is larger than the data point x of the current data point j With the current data point x i Is taken as the minimum distance of theta i (ii) a The calculation formula is as follows:
θ i ＝min(d ij )，x j :ρ j ＞ρ i ；
s34: according to rho of each sample data in the sample data set i And theta i Drawing a decision graph, wherein the abscissa of each sample point in the decision graph is rho i Ordinate of theta i (ii) a Determining the clustering center and the category number according to the decision graph; the number of categories is 3; the category of each clustering center is determined by the state of the corresponding power utilization node; the classification of each node in the node attribute dataset is either "underrun", "smooth" or "overloaded".
5. The method for analyzing the power supply stability of the low-voltage transformer area in real time as claimed in claim 1, wherein: in the BP neural network constructed in step S4,
the hyperbolic tangent function Tanh is adopted between the input layer and the hidden layer as an activation function, and the Tanh activation function is as follows:
a nonlinear transformation function Sigmoid is adopted between the hidden layer and the output layer as an activation function; the expression of Sigmoid activation function is as follows:
6. the method for analyzing the power supply stability of the low-voltage transformer area in real time as claimed in claim 5, wherein: in the BP neural network constructed in step S4,
the transfer formula from the input layer to the hidden layer is as follows:
in the above formula, x i For an input value of an ith input layer, i = N, N representing the number of nodes of the input layer; h 1j For the output of the jth node of the hidden layer, j =2N +1; f. of 1 As a function of Tanh activation, ω ij Is the weight value, x, between the ith node of the input layer and the jth node of the hidden layer i Is an input value of the ith node of the input layer, a j A threshold value of the jth node of the hidden layer;
the transfer formula from the hidden layer to the output layer is as follows;
in the above formula, y is the output value of the output layer, f 2 For Sigmoid activation functions, ω j The weight between the jth node of the hidden layer and the output layer, and b is the threshold of the output layer.
7. The method for analyzing the power supply stability of the low-voltage transformer area in real time as claimed in claim 6, wherein: in step S5, the training process of the BP neural network is as follows:
s51: setting initial training parameters: including the number of iterations; target minimum error, learning rate η;
s52: adopting node attribute data sets in different operation states collected in advance as training samples, and carrying out forward propagation on the training samples by using a BP neural network;
s53: calculating the sum of squares of absolute values of relative errors of the predicted output and the expected output of the output layer in each round of forward propagation process, and judging whether the target minimum error is met; if so, finishing the training process of the network model, otherwise, entering a back propagation process;
s54: adopting a gradient descent method to perform a back propagation process, and dynamically updating the output layer weight and the weight between the input layer and the hidden layer according to a weight updating formula from the hidden layer to the output layer and a weight updating formula between the input layer and the hidden layer;
s55: continuously inputting the training samples into the BP neural network after weight updating, and repeating the forward propagation of the next round;
s56: and looping the steps S53-S54 until a preset iteration number is reached, or the sum of the squares of the absolute values of the relative errors of the predicted output and the expected output of the network model meets the requirement of the target minimum error.
8. The method for real-time analysis of low-voltage transformer area power supply stability of claim 7, wherein: in step S54, the formula for updating the weight between the input layer and the hidden layer is as follows:
of the above formula, ω' ij Representing the updated weight between the ith node of the input layer and the jth node of the hidden layer;
representing the expected output of the current input sample in the network model, and y representing the actual output of the current input sample in the network model; e represents the sum of the squares of the relative errors of the desired output and the actual output;
the weight updating formula from the hidden layer to the output layer is as follows:
in the above formula, ω' j And representing the weight between the jth node of the updated hidden layer and the output layer.
9. The method for real-time analysis of low-voltage transformer area power supply stability of claim 8, wherein: in a step S5, the first step is executed,
the process of optimizing the threshold of the BP neural network by adopting the classical genetic algorithm is as follows:
s01: converting the threshold value of the BP neural network into corresponding chromosome individuals by adopting a real number coding mode, and further randomly generating an initial population containing a plurality of chromosome individuals;
s02: setting an iteration termination condition of a classical genetic algorithm as training phase synchronization of a BP neural network, and performing iterative optimization on an initial population by using the classical genetic algorithm, wherein each iteration comprises the following contents;
s021: calculating the fitness of each chromosome in the initial population by using a preset fitness function;
s022: selecting the initial population by adopting a selection operator of a classical genetic algorithm;
s023: performing cross operation on the initial population by adopting a cross operator of a classical genetic algorithm;
s024: carrying out mutation operation on the initial population by adopting a mutation operator of a classical genetic algorithm;
s03: and in each round of population iteration process, outputting the threshold value of the chromosome characterization with the maximum fitness to the BP neural network as the threshold value of the BP neural network in the next training round.
10. The method for analyzing the power supply stability of the low-voltage transformer area in real time as set forth in claim 9, wherein: the selection operator adopts an elite reservation operator; the crossover operator calculates the similarity between any two individuals of the current population through a self-defined similarity function, and then performs double-point crossover on the two individuals with the lowest similarity; and the mutation operator performs single-point mutation on the chromosomes with the highest fitness and the lowest fitness according to a preset mutation probability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210866497.XA CN115204698A (en) | 2022-07-22 | 2022-07-22 | Real-time analysis method for power supply stability of low-voltage transformer area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210866497.XA CN115204698A (en) | 2022-07-22 | 2022-07-22 | Real-time analysis method for power supply stability of low-voltage transformer area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115204698A true CN115204698A (en) | 2022-10-18 |
Family
ID=83583470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210866497.XA Pending CN115204698A (en) | 2022-07-22 | 2022-07-22 | Real-time analysis method for power supply stability of low-voltage transformer area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115204698A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116316611A (en) * | 2023-04-25 | 2023-06-23 | 佰聆数据股份有限公司 | Power supply method and system based on low-voltage transformer area |
| CN117634850A (en) * | 2024-01-12 | 2024-03-01 | 广州能信数字科技有限公司 | Power dispatching command interaction method and system based on block chain |
-
2022
- 2022-07-22 CN CN202210866497.XA patent/CN115204698A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116316611A (en) * | 2023-04-25 | 2023-06-23 | 佰聆数据股份有限公司 | Power supply method and system based on low-voltage transformer area |
| CN116316611B (en) * | 2023-04-25 | 2023-08-18 | 佰聆数据股份有限公司 | Power supply method and system based on low-voltage transformer area |
| CN117634850A (en) * | 2024-01-12 | 2024-03-01 | 广州能信数字科技有限公司 | Power dispatching command interaction method and system based on block chain |
| CN117634850B (en) * | 2024-01-12 | 2024-06-18 | 广州能信数字科技有限公司 | Power dispatching command interaction method and system based on block chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108734355B (en) | Short-term power load parallel prediction method and system applied to power quality comprehensive management scene | |
| CN112734128B (en) | 7-day power load peak prediction method based on optimized RBF | |
| CN107516170A (en) | A kind of difference self-healing control method based on probability of equipment failure and power networks risk | |
| CN106251001A (en) | A kind of based on the photovoltaic power Forecasting Methodology improving fuzzy clustering algorithm | |
| CN110188919A (en) | A kind of load forecasting method based on shot and long term memory network | |
| CN111028100A (en) | Refined short-term load prediction method, device and medium considering meteorological factors | |
| CN115204698A (en) | Real-time analysis method for power supply stability of low-voltage transformer area | |
| CN112241606A (en) | Cooperative decision-making method for operation and maintenance of ship intelligent equipment based on CPS decision-making module | |
| CN116523148B (en) | Distribution network distribution transformer overload early warning method, device and equipment | |
| CN115169719A (en) | Platform area state prediction model based on fuzzy clustering and BP neural network | |
| CN116148753A (en) | Intelligent electric energy meter operation error monitoring system | |
| CN115879602A (en) | Ultra-short-term photovoltaic output prediction method based on transient weather | |
| CN115619028A (en) | Clustering algorithm fusion-based power load accurate prediction method | |
| CN116169670A (en) | Short-term non-resident load prediction method and system based on improved neural network | |
| CN117674119A (en) | Power grid operation risk assessment method, device, computer equipment and storage medium | |
| CN116307111A (en) | Reactive load prediction method based on K-means clustering and random forest algorithm | |
| CN115118015A (en) | Platform district power supply stability monitoring system based on fuse terminal | |
| CN111027841A (en) | Low-voltage transformer area line loss calculation method based on gradient lifting decision tree | |
| Zhang | Short‐Term Power Load Forecasting Based on SAPSO‐CNN‐LSTM Model considering Autocorrelated Errors | |
| CN117913808A (en) | Distributed photovoltaic power generation prediction method and device | |
| CN117454180A (en) | Photovoltaic power generation power prediction model construction method and device | |
| CN115081551A (en) | RVM line loss model building method and system based on K-Means clustering and optimization | |
| CN115313522A (en) | Spare capacity configuration method and system considering new energy output prediction deviation | |
| Sicheng et al. | Abnormal line loss data detection and correction method | |
| CN115759395A (en) | Training of photovoltaic detection model, detection method of photovoltaic power generation and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |