CN117081076A - Radial basis function neural network power flow calculation method and system - Google Patents
Radial basis function neural network power flow calculation method and system Download PDFInfo
- Publication number
- CN117081076A CN117081076A CN202310837416.8A CN202310837416A CN117081076A CN 117081076 A CN117081076 A CN 117081076A CN 202310837416 A CN202310837416 A CN 202310837416A CN 117081076 A CN117081076 A CN 117081076A
- Authority
- CN
- China
- Prior art keywords
- radial basis
- basis function
- neural network
- flow calculation
- node
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 62
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 39
- 239000002245 particle Substances 0.000 claims abstract description 76
- 238000003062 neural network model Methods 0.000 claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000010606 normalization Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims description 77
- 210000002569 neuron Anatomy 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 7
- 230000006978 adaptation Effects 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 239000004065 semiconductor Substances 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/04—Circuit arrangements for ac mains or ac distribution networks for connecting networks of the same frequency but supplied from different sources
- H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses a radial basis function neural network load flow calculation method and a radial basis function neural network load flow calculation system, wherein the radial basis function neural network load flow calculation method comprises the following steps: collecting historical operation data of the power system and carrying out normalization processing; constructing a radial basis neural network model based on the normalized data; training the radial basis function neural network model by adopting a particle swarm algorithm; and carrying out load flow calculation test on the power system by using the trained radial basis function neural network model. The radial basis function network of the application has relatively high calculation speed and high precision, and simultaneously establishes nonlinear mapping of load flow calculation input and output through the radial basis function network; the particle swarm algorithm is combined with the radial basis function neural network, the particle swarm algorithm has global searching capability, and the particle swarm algorithm is utilized to find the optimal weight and the threshold of the radial basis function neural network, so that the model precision is improved; the number of iterations of the radial basis function network may be reduced.
Description
Technical Field
The application relates to the technical field of power flow calculation of power systems, in particular to a radial basis function neural network power flow calculation method and system.
Background
With the rapid development of power systems, renewable energy sources are rapidly growing, distributed power generation, flexible loads, power electronics and the like are connected into the power systems in a large scale, and power fluctuation of the power systems becomes more complex. The traditional model-driven power flow calculation method is difficult to be suitable for the rapid development of a power system, and particularly for the power system with unknown topological relation and network parameters, the model-driven power flow calculation is not suitable any more. A large amount of measuring equipment is connected into the power system, the voltage, the current, the phase angle, the active power and the reactive power are obtained to become the capacity, and the power flow calculation method based on data driving has better application prospect.
In the existing data-driven power flow calculation method, the input and the output are generally in a linear mapping relation. Although the linear power flow method has high calculation speed, the nonlinear characteristics of the power system cannot be accurately simulated, and the accurate power flow calculation and system analysis may not be accurate enough. In order to solve the problems, the dynamic characteristics and rules of the power system are learned by analyzing the historical electrical data of the system and a data-driven method is adopted to establish a nonlinear mapping relation so as to predict the future power flow condition, so that the application provides a radial basis neural network power flow calculation method based on particle swarm optimization parameter optimization.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
The present application has been made in view of the above-described problems occurring in the prior art.
Therefore, the application aims to provide a radial basis function neural network power flow calculation method and system, which solve the problem that the traditional model-driven power flow calculation method is difficult to be applied to a power system with unknown topological relation and network parameters.
In order to solve the technical problems, the application provides the following technical scheme:
in a first aspect, an embodiment of the present application provides a radial basis function neural network load flow calculation method, including:
collecting historical operation data of the power system and carrying out normalization processing;
constructing a radial basis neural network model based on the normalized data;
training the radial basis function neural network model by adopting a particle swarm algorithm;
and carrying out load flow calculation test on the power system by using the trained radial basis function neural network model.
The radial basis function neural network load flow calculation method provided by the application comprises the following steps: the historical operating data of the power system is collected to include all voltage, phase angle, active power and reactive power data measured by the measurement devices installed at the PQ node, PV node and balance node.
The radial basis function neural network load flow calculation method provided by the application comprises the following steps: the radial basis function neural network model includes,
the input layer comprises active power and reactive power of the PQ node, active power and voltage amplitude of the PV node, and voltage amplitude and voltage phase angle of the balance node;
a hidden layer comprising the following number of neurons:
wherein p is the number of neurons of the hidden layer, m is the number of neurons of the input layer, n is the number of neurons of the output layer, and a is a random number of 1-10;
the output layer includes the voltage amplitude and voltage phase angle of the PQ node, the reactive power and voltage phase angle of the PV node.
The radial basis function neural network load flow calculation method provided by the application comprises the following steps: also included is a method of manufacturing a semiconductor device,
the radial basis function adopted by the radial basis function neural network model is a Gaussian kernel function, and the specific formula is as follows:
wherein x is 1 And x 2 For input samples, ||x1-x2|| is the Euclidean distance between samples, and σ is the bandwidth parameter of the Gaussian kernel function.
The radial basis function neural network load flow calculation method provided by the application comprises the following steps: training the radial basis function neural network model using a particle swarm algorithm includes,
initializing a particle swarm, setting the particle swarm population scale as M, the iteration number as K, the inertia weight as w, the learning factors as c1 and c2, and initializing the particle swarm at a speed of v and a position of x;
the initial fitness of each particle was calculated as follows:
where i=1, 2,3 … N, denotes the dimension of the output, y i For the output value of the model,is an actual value;
taking the initial adaptive value as the current individual optimal value of each particle, and taking the position corresponding to each adaptive value as the position of the individual optimal value of each particle;
and taking the best initial adaptation value as a global optimal value of the current population, and taking the position corresponding to the best adaptation value as the position of the global optimal value of the current population.
The radial basis function neural network load flow calculation method provided by the application comprises the following steps: also included is a method of manufacturing a semiconductor device,
updating the position and the speed of the particles, and updating according to the current position, the speed and the population information of the particles;
the updated particle population is adjusted by the following adjustment rules:
wherein v is max ,v min Respectively a maximum value and a minimum value of the speed;
calculating the fitness of the updated particles;
comparing whether the fitness value of each particle is better than the optimal value of the historical individual;
if so, taking the current particle fitness value as an individual optimal value of the particles, and taking the corresponding position as the position of the individual optimal value of each particle;
otherwise, the individual optimal value of the history particles is not replaced, and the individual optimal value of the history particles is still used as the reference;
comparing whether the global optimum of the current population is better than the global optimum of the historical population;
if so, replacing the current population global optimal value with the historical population global optimal value, wherein the corresponding position is used as the position of the population global optimal value;
otherwise, the global optimal value of the historical population is not replaced, and the global optimal value of the historical population is still used as the reference;
repeating the step of updating the particle position and speed to compare the fitness value of each particle and the global optimal value of the current population until the set maximum iteration number is met;
outputting a global optimal value of the particle swarm and a corresponding position;
and obtaining the weight and the threshold of the optimal radial basis function neural network according to the optimal output result, and establishing a radial basis function neural network model of the optimal parameters.
The radial basis function neural network load flow calculation method provided by the application comprises the following steps: the power flow calculation test of the power system by using the trained radial basis function neural network model comprises,
collecting active power and reactive power of a PQ node of a system at the current moment, active power and voltage amplitude of a PV node, and balancing voltage amplitude and voltage phase angle of the node;
carrying out normalization processing on the collected active power and reactive power data of the PQ node, the active power and voltage amplitude data of the PV node, and the voltage amplitude and voltage phase angle data of the balance node;
and inputting the normalized data into a trained base neural network model to obtain voltage amplitude and voltage phase angle data of the PQ node and reactive power and voltage phase angle data of the PV node.
In a second aspect, an embodiment of the present application provides a radial basis function neural network load flow calculation system, including,
the acquisition module acquires historical operation data of the power system and performs normalization processing;
the model building module is used for building a radial basis neural network model based on the normalized data;
the training module is used for training the radial basis function neural network model by adopting a particle swarm algorithm;
and the output module is used for carrying out load flow calculation test on the power system by using the trained radial basis function neural network model.
In a third aspect, embodiments of the present application provide a computing device comprising:
a memory and a processor;
the memory is configured to store computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to implement a radial basis function neural network power flow calculation method in accordance with any of the embodiments of the present application.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the radial basis function network power flow calculation method.
The application has the beneficial effects that: the radial basis function network of the application has relatively high calculation speed and high precision, and simultaneously establishes nonlinear mapping of load flow calculation input and output through the radial basis function network; the particle swarm algorithm is combined with the radial basis function neural network, the particle swarm algorithm has global searching capability, and the particle swarm algorithm is utilized to find the optimal weight and the threshold of the radial basis function neural network, so that the model precision is improved; the number of iterations of the radial basis function network may be reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
fig. 1 is a flow chart of a radial basis function neural network load flow calculation method of the present application.
Fig. 2 is a diagram of a radial basis function neural network model according to the radial basis function neural network load flow calculation method of the present application.
FIG. 3 is a graph of the voltage amplitude test results of the radial basis function neural network load flow calculation method of the present application.
Fig. 4 is a graph of voltage phase angle test results of the radial basis function neural network power flow calculation method of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the application will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, but the present application may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present application is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the application. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Further, in describing the embodiments of the present application in detail, the cross-sectional view of the device structure is not partially enlarged to a general scale for convenience of description, and the schematic is only an example, which should not limit the scope of protection of the present application. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Example 1
Referring to fig. 1 to fig. 2, for an embodiment of the present application, a radial basis function neural network load flow calculation method is provided, including:
s1: and collecting historical operation data of the power system and carrying out normalization processing. It should be noted that:
the historical operating data of the power system is collected to include all voltage, phase angle, active power and reactive power data measured by the measurement devices installed at the PQ node, PV node and balance node.
The normalization process may include the steps of,
wherein x' is normalized data, x is original data, x max ,x min Respectively, the maximum and minimum values in the original data.
S2: and constructing a radial basis neural network model based on the normalized data. It should be noted that:
the input layer comprises active power and reactive power of the PQ node, active power and voltage amplitude of the PV node, and voltage amplitude and voltage phase angle of the balance node;
a hidden layer comprising the following number of neurons:
wherein p is the number of neurons of the hidden layer, m is the number of neurons of the input layer, n is the number of neurons of the output layer, and a is a random number of 1-10;
the output layer includes the voltage amplitude and voltage phase angle of the PQ node, the reactive power and voltage phase angle of the PV node.
The radial basis function adopted by the radial basis function neural network model is a Gaussian kernel function, and the specific formula is as follows:
wherein x is 1 And x 2 For input samples, ||x1-x2|| is the Euclidean distance between samples, and σ is the bandwidth parameter of the Gaussian kernel function.
S3: and training the radial basis function neural network model by adopting a particle swarm algorithm. It should be noted that:
initializing a particle swarm, setting a particle swarm population scale M, iteration times K, an inertia weight w, learning factors c1 and c2, and initializing a speed v and a position x of the particle swarm;
the initial fitness of each particle was calculated as follows:
where i=1, 2,3 … N, denotes the dimension of the output, y i For the output value of the model,is an actual value;
taking the initial adaptive value as the current individual optimal value of each particle, and taking the position corresponding to each adaptive value as the position of the individual optimal value of each particle;
taking the best initial adaptation value as a global optimal value of the current population, and taking the position corresponding to the best adaptation value as the position of the global optimal value of the current population;
updating the position and the speed of the particles, and updating according to the current position, the speed and the population information of the particles; the update formula of the speed is as follows:
wherein r is 1 ,r 2 Respectively [0,1 ]]A range of random numbers is used,for the individual optimum value, < >>Is the optimal value of the population;
the update formula of the position is as follows:
wherein alpha is a constraint factor;
the updated particle population is adjusted by the following adjustment rules:
wherein v is max ,v min Respectively a maximum value and a minimum value of the speed;
calculating the fitness of the updated particles;
comparing whether the fitness value of each particle is better than the historical individual optimal value,
if so, taking the current particle fitness value as an individual optimal value of the particles, and taking the corresponding position as the position of the individual optimal value of each particle;
otherwise, the individual optimal value of the history particles is not replaced, and the individual optimal value of the history particles is still used as the reference;
comparing whether the global optimum of the current population is better than the global optimum of the historical population;
if so, replacing the current population global optimal value with the historical population global optimal value, wherein the corresponding position is used as the position of the population global optimal value;
otherwise, the global optimal value of the historical population is not replaced, and the global optimal value of the historical population is still used as the reference;
repeating the step of updating the particle position and speed to compare the fitness value of each particle and the global optimal value of the current population until the set maximum iteration number is met;
outputting a global optimal value of the particle swarm and a corresponding position;
and obtaining the weight and the threshold of the optimal radial basis function neural network according to the optimal output result, and establishing a radial basis function neural network model of the optimal parameters.
Repeating the step of updating the particle position and speed to compare the fitness value of each particle and the global optimal value of the current population until the set maximum iteration number is met;
outputting a global optimal value of the particle swarm and a corresponding position;
and obtaining the weight and the threshold of the optimal radial basis function neural network according to the optimal output result, and establishing a radial basis function neural network model of the optimal parameters.
S4: and carrying out load flow calculation test on the power system by using the trained radial basis function neural network model. It should be noted that:
collecting active power and reactive power of a PQ node of a system at the current moment, active power and voltage amplitude of a PV node, and balancing voltage amplitude and voltage phase angle of the node;
carrying out normalization processing on the collected active power and reactive power data of the PQ node, the active power and voltage amplitude data of the PV node, and the voltage amplitude and voltage phase angle data of the balance node;
and inputting the normalized data into a trained base neural network model to obtain voltage amplitude and voltage phase angle data of the PQ node and reactive power and voltage phase angle data of the PV node.
The embodiment also provides a radial basis function neural network load flow calculation system, which comprises:
the acquisition module acquires historical operation data of the power system and performs normalization processing;
the model building module is used for building a radial basis neural network model based on the normalized data;
the training module is used for training the radial basis function neural network model by adopting a particle swarm algorithm;
and the output module is used for carrying out load flow calculation test on the power system by using the trained radial basis function neural network model.
The embodiment also provides a computing device, which is suitable for the situation of a radial basis function network power flow computing method, and includes:
a memory and a processor; the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement a radial basis function neural network load flow calculation method as set forth in the foregoing embodiment.
The computer device may be a terminal comprising a processor, a memory, a communication interface, a display screen and input means connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
The present embodiment also provides a storage medium having stored thereon a computer program which, when executed by a processor, implements a radial basis function neural network load flow calculation method as proposed in the above embodiment.
The storage medium according to the present embodiment belongs to the same inventive concept as the data storage method according to the above embodiment, and technical details not described in detail in the present embodiment can be seen in the above embodiment, and the present embodiment has the same advantageous effects as the above embodiment.
Example 2
As shown in fig. 3, another embodiment of the present application, which is different from the first embodiment, provides a verification test of a radial basis function network load flow calculation method and system, and a verification description is made on the technical effects adopted in the method.
In order to verify the power flow calculation effect of the application, an IEEE9 node system is adopted for testing, a No. 1 node is a balance node, no. 2-3 nodes are PV nodes, 4-9 nodes are PQ nodes, the characteristics of different power utilization behaviors of the actual running state of a power grid and each node are considered, power disturbance which is distributed randomly and uniformly and is +/-30% of the load clothes of each node on the original level is assumed, matpower7.0 is utilized for carrying out power flow calculation to obtain the voltage, phase angle, active power and reactive power values of all nodes, the active power and the voltage amplitude of the PQ nodes, the voltage amplitude and the voltage phase angle of the balance node are used as the input of a model, and the voltage amplitude and the voltage phase angle data of the PQ nodes and the reactive power and the voltage phase angle data of the PV nodes are used as the output of the model. And normalizing the input data set and the output data set, and inputting the normalized data set and the output data set into a training model.
The regression accuracy of the load flow calculation is analyzed by using a decision coefficient, and the decision coefficient formula is as follows:
wherein i is=1, 2,3 … n, n representing the dimension of the output, y i For the output value of the model,is the actual value +.>Is the average of the actual values. The voltage amplitude test result diagram is shown in fig. 3, the voltage phase angle test result diagram is shown in fig. 4, the regression accuracy is shown in table 1, and the method provided by the application has extremely high accuracy.
Table 1: regression accuracy meter
System and method for controlling a system | Voltage amplitude regression accuracy | Voltage phase angle regression accuracy |
IEEE9 node system | 99.99% | 99.99% |
It should be noted that the above embodiments are only for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present application may be modified or substituted without departing from the spirit and scope of the technical solution of the present application, which is intended to be covered in the scope of the claims of the present application.
Claims (10)
1. A radial basis function neural network tide calculation method is characterized in that: comprising the steps of (a) a step of,
collecting historical operation data of the power system and carrying out normalization processing;
constructing a radial basis neural network model based on the normalized data;
training the radial basis function neural network model by adopting a particle swarm algorithm;
and carrying out load flow calculation test on the power system by using the trained radial basis function neural network model.
2. The radial basis function network power flow calculation method of claim 1, wherein: the historical operating data of the power system is collected to include all voltage, phase angle, active power and reactive power data measured by the measurement devices installed at the PQ node, PV node and balance node.
3. The radial basis function network power flow calculation method of claim 1, wherein: the radial basis function neural network model includes,
the input layer comprises active power and reactive power of the PQ node, active power and voltage amplitude of the PV node, and voltage amplitude and voltage phase angle of the balance node;
a hidden layer comprising the following number of neurons:
wherein p is the number of neurons of the hidden layer, m is the number of neurons of the input layer, n is the number of neurons of the output layer, and a is a random number of 1-10;
the output layer includes the voltage amplitude and voltage phase angle of the PQ node, the reactive power and voltage phase angle of the PV node.
4. A radial basis function neural network power flow calculation method as claimed in any one of claims 1 to 3, wherein: also included is a method of manufacturing a semiconductor device,
the radial basis function adopted by the radial basis function neural network model is a Gaussian kernel function, and the specific formula is as follows:
wherein x is 1 And x 2 For input samples, ||x1-x2|| is the Euclidean distance between samples, and σ is the bandwidth parameter of the Gaussian kernel function.
5. The radial basis function neural network power flow calculation method according to any one of claims 1 to 4, characterized in that: training the radial basis function neural network model using a particle swarm algorithm includes,
initializing a particle swarm, setting the particle swarm population scale as M, the iteration number as K, the inertia weight as w, the learning factors as c1 and c2, and initializing the particle swarm at a speed of v and a position of x;
the initial fitness of each particle was calculated as follows:
where i=1, 2,3 … N, denotes the dimension of the output, y i For the output value of the model,is an actual value;
taking the initial adaptive value as the current individual optimal value of each particle, and taking the position corresponding to each adaptive value as the position of the individual optimal value of each particle;
and taking the best initial adaptation value as a global optimal value of the current population, and taking the position corresponding to the best adaptation value as the position of the global optimal value of the current population.
6. The radial basis function network power flow calculation method of claim 5, wherein: also included is a method of manufacturing a semiconductor device,
updating the position and the speed of the particles, and updating according to the current position, the speed and the population information of the particles;
the updated particle population is adjusted by the following adjustment rules:
wherein v is max ,v min Respectively a maximum value and a minimum value of the speed;
calculating the fitness of the updated particles;
comparing whether the fitness value of each particle is better than the optimal value of the historical individual;
if so, taking the current particle fitness value as an individual optimal value of the particles, and taking the corresponding position as the position of the individual optimal value of each particle;
otherwise, the individual optimal value of the history particles is not replaced, and the individual optimal value of the history particles is still used as the reference;
comparing whether the global optimum of the current population is better than the global optimum of the historical population;
if so, replacing the current population global optimal value with the historical population global optimal value, wherein the corresponding position is used as the position of the population global optimal value;
otherwise, the global optimal value of the historical population is not replaced, and the global optimal value of the historical population is still used as the reference;
repeating the step of updating the particle position and speed to compare the fitness value of each particle and the global optimal value of the current population until the set maximum iteration number is met;
outputting a global optimal value of the particle swarm and a corresponding position;
and obtaining the weight and the threshold of the optimal radial basis function neural network according to the optimal output result, and establishing a radial basis function neural network model of the optimal parameters.
7. The radial basis function network power flow calculation method of claim 6, wherein: the power flow calculation test of the power system by using the trained radial basis function neural network model comprises,
collecting active power and reactive power of a PQ node of a system at the current moment, active power and voltage amplitude of a PV node, and balancing voltage amplitude and voltage phase angle of the node;
carrying out normalization processing on the collected active power and reactive power data of the PQ node, the active power and voltage amplitude data of the PV node, and the voltage amplitude and voltage phase angle data of the balance node;
and inputting the normalized data into a trained base neural network model to obtain voltage amplitude and voltage phase angle data of the PQ node and reactive power and voltage phase angle data of the PV node.
8. A radial basis function neural network power flow calculation system is characterized by comprising,
the acquisition module acquires historical operation data of the power system and performs normalization processing;
the model building module is used for building a radial basis neural network model based on the normalized data;
the training module is used for training the radial basis function neural network model by adopting a particle swarm algorithm;
and the output module is used for carrying out load flow calculation test on the power system by using the trained radial basis function neural network model.
9. A computing device, comprising:
a memory and a processor;
the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, which when executed by the processor, implement the steps of a radial basis function neural network power flow calculation method according to any one of claims 1 to 7.
10. A computer readable storage medium storing computer executable instructions which when executed by a processor implement the steps of a radial basis function neural network load flow calculation method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310837416.8A CN117081076A (en) | 2023-07-10 | 2023-07-10 | Radial basis function neural network power flow calculation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310837416.8A CN117081076A (en) | 2023-07-10 | 2023-07-10 | Radial basis function neural network power flow calculation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117081076A true CN117081076A (en) | 2023-11-17 |
Family
ID=88703187
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310837416.8A Pending CN117081076A (en) | 2023-07-10 | 2023-07-10 | Radial basis function neural network power flow calculation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117081076A (en) |
-
2023
- 2023-07-10 CN CN202310837416.8A patent/CN117081076A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Bu et al. | A data-driven game-theoretic approach for behind-the-meter PV generation disaggregation | |
Lei et al. | Data-driven optimal power flow: A physics-informed machine learning approach | |
Bu et al. | WECC composite load model parameter identification using evolutionary deep reinforcement learning | |
CN111860982A (en) | Wind power plant short-term wind power prediction method based on VMD-FCM-GRU | |
Tong et al. | Detection and classification of transmission line transient faults based on graph convolutional neural network | |
Ye et al. | Combined approach for short-term wind power forecasting based on wave division and Seq2Seq model using deep learning | |
CN109359665B (en) | Household appliance load identification method and device based on support vector machine | |
CN111900731B (en) | PMU-based power system state estimation performance evaluation method | |
CN113659565B (en) | Online prediction method for frequency situation of new energy power system | |
CN113935512A (en) | Wind power prediction method and device, computer equipment and storage medium | |
CN114021483A (en) | Ultra-short-term wind power prediction method based on time domain characteristics and XGboost | |
CN110458341A (en) | A kind of ultra-short term wind-powered electricity generation prediction technique and system considering meteorological features | |
CN117330963A (en) | Energy storage power station fault detection method, system and equipment | |
CN113609750A (en) | Current calculation method based on magnetic field sensing signal machine learning | |
CN117081076A (en) | Radial basis function neural network power flow calculation method and system | |
CN116522594A (en) | Time self-adaptive transient stability prediction method and device based on convolutional neural network | |
CN110276478A (en) | Short-term wind power forecast method based on segmentation ant group algorithm optimization SVM | |
CN112581311B (en) | Method and system for predicting long-term output fluctuation characteristics of aggregated multiple wind power plants | |
CN115796327A (en) | Wind power interval prediction method based on VMD (vertical vector decomposition) and IWOA-F-GRU (empirical mode decomposition) -based models | |
CN115688535A (en) | Power data combined interpolation method and system based on waveform similarity analysis | |
CN112685900B (en) | Power load simulation method for representing impact load power characteristics | |
CN115081742A (en) | Ultra-short-term power prediction method for distributed wind power plant and related equipment | |
CN115275975A (en) | Method and device for determining electric power data matching degree of optical storage charging station | |
CN113344435B (en) | Platform power supply state evaluation device, electronic equipment and storage medium | |
Feng et al. | A received signal strength based indoor localization algorithm using ELM technique and ridge regression |
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 |