CN116244964B - Distribution network strong wind disaster power outage forecasting method based on numerical simulation and SVD model - Google Patents

Abstract

The invention relates to a power failure prediction method for a power distribution network heavy wind disaster based on numerical simulation and SVD model, which comprises the following steps: matching body parameters, meteorological parameters, running state parameters and outage probability and duration data after the occurrence of a power failure fault under the condition of a strong wind disaster, and establishing a power distribution network historical meteorological parameter sample library A and a power distribution network strong wind fault sample library B; based on the sample library, an SVD method is adopted to construct an SVD model of influence of a strong wind disaster on power failure faults of the power distribution network; adopting a regional numerical mode, and carrying out numerical simulation by combining an initial boundary field provided by global weather forecast data to obtain a weather parameter forecast value of a target region; and forecasting the power failure probability and the power failure time under the strong wind disaster of the power distribution network based on the SVD model and the meteorological parameter forecasting value. The invention realizes the refined large wind disaster forecast based on numerical simulation and statistical method, and is suitable for disaster prevention and reduction of various complicated distribution networks.

Description

Distribution network strong wind disaster power outage forecasting method based on numerical simulation and SVD model

Technical field

The invention belongs to the technical field of power grid disaster prevention, and specifically relates to a method for forecasting power outage in distribution network due to strong wind disaster based on numerical simulation and SVD model.

Background technique

The power grid is an important basic industry closely related to the national economy and people's livelihood. However, due to its own structure and operating characteristics, the smooth operation of its related hardware facilities will be significantly affected by surrounding meteorological factors. In the context of global warming, disastrous meteorological and climate events occur frequently, and natural disasters such as strong winds, heavy rains, and lightning have severely challenged the normal operating environment of hardware facilities such as distribution networks. Among them, strong wind disasters have a higher probability of occurrence, with a wider range of influence and greater harm. They can directly cause power equipment disconnections, toppled towers, wind deflection flashovers and other faults, and can also cause branches, cloth strips, balloons and other debris to occur. Tangle in wires and cause indirect damage to power transmission lines. If relevant warnings can be issued in a timely manner and preparations can be made in advance to gain sufficient time for emergency repairs and power supply work in areas affected by strong winds, it is crucial to ensure the safe and reliable power supply of regional power grids. Therefore, it is urgent to propose a method for forecasting wind disaster and power outage in distribution network.

In the field of meteorology, with the continuous development of numerical weather prediction models, the accuracy of forecasting various meteorological elements at the weather scale has been greatly improved, and accordingly kilometer-level wind forecast products have also been formed. However, due to the complex and diverse topography of the distribution network, and the widespread micro-topography and micro-meteorological characteristics, if we want to carry out strong wind warning for each distribution network in the region, the horizontal resolution of the current numerical forecast products is still difficult to meet the requirements. At the same time, each distribution network also lacks effective strong wind monitoring methods, making it difficult to construct an effective statistical forecast model based on a single distribution network. Therefore, there is an urgent need to study refined weather forecasting and disaster early warning technology for distribution networks. If we can combine coarse-resolution meteorological elements with historical fault data of distribution networks in the region based on numerical prediction products and distribution network fault data sets, and establish a spatio-temporal connection between the two, it will be of great help to achieve refined wind forecasting of distribution networks. Disaster forecasting and early warning are of great significance.

Contents of the invention

In view of the shortcomings of existing methods, the present invention is a distribution network wind disaster power outage forecasting method based on numerical simulation and SVD model, which realizes refined wind disaster forecasting based on numerical simulation and statistical methods, and is suitable for power distribution in various complex situations. Network disaster prevention and mitigation.

In order to achieve the above objects, the present invention adopts the following technical solutions:

A method for forecasting wind disaster and power outage in distribution network based on numerical simulation and SVD model, including the following steps:

Collect historical meteorological parameter data sets, obtain the ontology parameters and operating status parameters of the distribution network, and establish a distribution network operating status data set;

Match the ontology parameters, meteorological parameters, operating status parameters, power outage probability and duration data after the fault occurs when the power outage fault occurs under strong wind disasters, and establish a distribution network historical meteorological parameter sample library A and a distribution network high wind fault sample library B;

Based on the historical meteorological parameter sample library A and the distribution network wind fault sample library B, the SVD method is used to construct an SVD model of the impact of strong wind disasters on distribution network power outage faults;

Using a regional numerical model, combined with the initial boundary field provided by global weather forecast data, numerical simulations are performed to obtain forecast values of meteorological parameters in the target area;

Based on the constructed SVD model of the impact of strong wind disasters on distribution network power outage faults and the meteorological parameter forecast values in the target area, the probability and duration of blackouts under strong wind disasters in the distribution network are predicted.

Preferably, the ontology parameters include tower information and line information of the distribution network.

Preferably, the tower information includes tower type, number, longitude, latitude, altitude, manufacturer, installation location, geological environment information, horizontal span, vertical span, tensile tower rotation and insulator string model of the tower, The number of strings and the number of insulator pieces.

Preferably, the line information includes line serial number, voltage level, line number, line name, start and end locations, line specifications, line type, number of loops, transmission length, design wind speed, design ice thickness, number of splits and split gaps.

Preferably, the meteorological parameters include wind speed and wind direction.

Preferably, the construction steps of the SVD model of the impact of the strong wind disaster on the power outage fault of the distribution network are as follows:

S1. Input distribution network historical meteorological parameter sample library A and distribution network wind fault sample library B:

A＝(A ₁₁ ,A ₁₂ ,…,A ₂₁ ,…,A _ij ,…,A _NM ),

B＝(B ₁₁ ,B ₁₂ ,…,B ₂₁ ,…,B _ik ,…,B _NS ),

Among them, A _ij is the meteorological parameter of the j-th grid point at the i-th time sample, and B _ik is the fault sample input parameter of the k-th distribution network at the i-th time sample, that is, the distribution network when the wind disaster fault sample occurs. Power grid ontology parameters, operating status parameters, power outage probability and power outage duration;

S2. Perform singular value decomposition on the covariance matrix of the distribution network historical meteorological parameter sample library A and the distribution network wind fault sample library B to obtain the time coefficient X of the main mode of the distribution network historical meteorological parameter sample library A:

X＝(X ₁ ,…,X _i ,…,X _N ),

Among them, X _N represents the coefficient corresponding to the Nth time sample of the main mode of the meteorological parameter;

Further obtain the correlation coefficient C of the main spatial modes of X and B, which is the influence weight on each distribution network:

C=(C ₁ ,…,C _i ,…,C _S ),

Among them, C _S represents the correlation coefficient corresponding to the S-th distribution network;

S3. Use C to build a prediction model:

Among them, x _i is the meteorological parameter of the i-th time sample, is the average value of meteorological parameters, and y _i is the predicted value of power outage probability or power outage duration under strong wind disaster in the distribution network.

Preferably, the method also includes combining the power outage probability and power outage duration under strong wind disasters in the distribution network, dividing the wind disaster into several levels, and conducting wind disaster early warning.

A distribution network wind disaster power outage forecasting system based on numerical simulation and SVD model, including: a memory, a processor and a computer program stored in the memory and capable of running on the processor. The processor executes the The computer program is used to implement any of the above-mentioned methods for forecasting wind disaster and power outage in distribution network based on numerical simulation and SVD model.

A computer-readable storage medium that stores computer-executable instructions, and the computer-executable instructions are used to cause the computer to execute any one of the above-mentioned numerical simulation and SVD model-based distribution network gale Disaster power outage forecasting method.

Positive beneficial effects of the present invention:

1. The present invention discloses a distribution network wind disaster power outage forecasting method based on numerical simulation and SVD model. It uses relatively easy-to-obtain historical meteorological parameter data sets and distribution network operating status data sets to establish meteorological elements through the SVD method. Statistical relationship model with each distribution network in space and time, that is, constructing an SVD model of the impact of strong wind disasters on distribution network power outages, and allocating the impact of coarse-resolution meteorological elements to each distribution network in the target area according to weight, fully Use the meteorological information of the surrounding environment during power outages in the distribution network; then use the regional numerical model to cooperate with the initial boundary field provided by global weather forecast data to integrate to obtain kilometer-level meteorological parameter forecast values; finally, combine the meteorological parameter forecast values in the target area with Combining the SVD model, micro-meteorological forecast products for a single distribution network can be obtained, thereby achieving refined predictions of the blackout probability and duration of strong wind disasters for each distribution network in the target area. It can also be based on the blackout probability under strong wind disasters. Classify the level of wind disaster according to the duration of power outage, and realize the early warning of wind disaster in distribution network based on the forecast results. The invention realizes refined strong wind disaster forecasting based on numerical simulation and statistical methods, and is suitable for disaster prevention and reduction of distribution networks with various complex situations.

Description of the drawings

Figure 1 is a flow chart of the distribution network wind disaster power outage forecasting method based on numerical simulation and SVD model.

Detailed ways

The present invention will be further described below in conjunction with some specific embodiments.

Example 1

A method for forecasting wind disaster and power outage in distribution network based on numerical simulation and SVD model, see Figure 1, including the following steps:

Collect historical meteorological parameter data sets, obtain the ontology parameters and operating status parameters of the distribution network, and establish a distribution network operating status data set;

Match the ontology parameters, meteorological parameters, operating status parameters, power outage probability and duration data after the fault occurs when the power outage fault occurs under strong wind disasters, and establish a distribution network historical meteorological parameter sample library A (including meteorological parameters) and distribution network strong wind Fault sample library B (including ontology parameters, operating status parameters, power outage probability and duration data after the fault occurs);

Based on the historical meteorological parameter sample library A and the distribution network wind fault sample library B, the SVD method is used to analyze the impact of strong winds on various distribution networks in the target area, and an SVD model of the impact of strong wind disasters on distribution network power outage faults is constructed;

Using a regional numerical model, combined with the initial boundary field provided by global weather forecast data, numerical simulation is performed to obtain the forecast values of meteorological parameters in the target area, that is, a gridded wind forecast product is obtained;

Based on the constructed SVD model of the impact of strong wind disasters on distribution network power outage faults and gridded strong wind forecast products, the probability and duration of power outages under strong wind disasters in the distribution network are forecast;

Combined with the probability and duration of power outage under strong wind disaster in the distribution network, the wind disaster is divided into several levels to carry out wind disaster early warning.

Further, the ontology parameters include tower information and line information of the distribution network.

Further, the tower information includes tower type, number, longitude, latitude, altitude, manufacturer, installation location, geological environment information, horizontal span, vertical span, tensile tower rotation, and insulator string model and string number of the tower. The number of insulator pieces is angular.

Further, the line information includes line serial number, voltage level, line number, line name, start and end locations, line specifications, line type, number of loops, transmission length, design wind speed, design ice thickness, number of splits and split gaps.

Further, meteorological parameters include wind speed and wind direction.

Furthermore, the steps to construct the SVD model of the impact of strong wind disasters on distribution network power outage faults are as follows:

S1. Input distribution network historical meteorological parameter sample library A and distribution network wind fault sample library B:

A＝(A ₁₁ ,A ₁₂ ,…,A ₂₁ ,…,A _ij ,…,A _NM ),

B＝(B ₁₁ ,B ₁₂ ,…,B ₂₁ ,…,B _ik ,…,B _NS ),

Among them, A _ij is the meteorological parameter of the j-th grid point at the i-th time sample, and B _ik is the fault sample input parameter of the k-th distribution network at the i-th time sample, that is, the distribution network when the wind disaster fault sample occurs. Power grid ontology parameters, operating status parameters, power outage probability and power outage duration;

S2. Perform singular value decomposition on the covariance matrix of the distribution network historical meteorological parameter sample library A and the distribution network wind fault sample library B to obtain the time coefficient X of the main mode of the distribution network historical meteorological parameter sample library A:

X＝(X ₁ ,…,X _i ,…,X _N ),

Among them, X _N represents the coefficient corresponding to the Nth time sample of the main mode of the meteorological parameter;

Further obtain the correlation coefficient C of the main spatial modes of X and B, which is the influence weight on each distribution network:

C=(C ₁ ,…,C _i ,…,C _S ),

Among them, C _S represents the correlation coefficient corresponding to the S-th distribution network;

S3. Use C to build a prediction model:

Among them, x _i is the meteorological parameter of the i-th time sample, is the average value of meteorological parameters, and y _i is the predicted value of power outage probability or power outage duration in the case of strong wind disaster in the distribution network.

A distribution network wind disaster power outage forecasting system based on numerical simulation and SVD model, including: a memory, a processor and a computer program stored in the memory and capable of running on the processor. The processor executes the The computer program is used to implement any of the above-mentioned methods for forecasting wind disaster and power outage in distribution network based on numerical simulation and SVD model.

The processor and memory may be connected via a bus or other means.

As a non-transitory computer-readable storage medium, memory can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory may include high-speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory located remotely from the processor, and the remote memory may be connected to the processor via a network. Examples of the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof.

It should be noted that the distribution network wind disaster and power outage forecasting system based on numerical simulation and SVD model in this embodiment may include a business processing module, an edge database, a server version information register, and a data synchronization module. The processor executes The computer program implements the above-mentioned distribution network wind disaster and power outage forecasting method based on numerical simulation and SVD model.

The device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separate, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

A computer-readable storage medium that stores computer-executable instructions, and the computer-executable instructions are used to cause the computer to execute any one of the above-mentioned numerical simulation and SVD model-based distribution network gale Disaster power outage forecasting method.

Those of ordinary skill in the art can understand that all or some steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit . Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As is known to those of ordinary skill in the art, the term computer storage media includes volatile and nonvolatile media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. removable, removable and non-removable media. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disk (DVD) or other optical disk storage, magnetic cassettes, tapes, disk storage or other magnetic storage devices, or may Any other medium used to store the desired information and that can be accessed by a computer. Additionally, it is known to those of ordinary skill in the art that communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media .

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Those of ordinary skill in the art may make other modifications or equivalent substitutions to the technical solutions of the present invention, as long as they do not deviate from the spirit and scope of the technical solutions of the present invention. The scope should be covered by the claims of the present invention.

Claims (8)

1. A method for forecasting wind disaster and power outage in distribution network based on numerical simulation and SVD model, which is characterized by including the following steps: Collect historical meteorological parameter data sets, obtain the ontology parameters and operating status parameters of the distribution network, and establish a distribution network operating status data set; Match the ontology parameters, meteorological parameters, operating status parameters, power outage probability and duration data after the fault occurs when the power outage fault occurs under strong wind disasters, and establish a distribution network historical meteorological parameter sample library A and a distribution network high wind fault sample library B; Based on the historical meteorological parameter sample library A and the distribution network wind fault sample library B, the SVD method is used to construct an SVD model of the impact of strong wind disasters on distribution network power outage faults; Using a regional numerical model, combined with the initial boundary field provided by global weather forecast data, numerical simulations are performed to obtain forecast values of meteorological parameters in the target area; Based on the constructed SVD model of the impact of strong wind disasters on distribution network power outage faults and the meteorological parameter forecast values in the target area, the probability and duration of power outages under strong wind disasters in the distribution network are forecast; The construction steps of the SVD model of the impact of the strong wind disaster on the power outage fault of the distribution network are as follows: S1. Input distribution network historical meteorological parameter sample library A and distribution network wind fault sample library B: A＝(A ₁₁ ,A ₁₂ ,…,A ₂₁ ,…,A _ij ,…,A _NM ), B＝(B ₁₁ ,B ₁₂ ,…,B ₂₁ ,…,B _ik ,…,B _NS ), Among them, A _ij is the meteorological parameter of the j-th grid point at the i-th time sample, and B _ik is the fault sample input parameter of the k-th distribution network at the i-th time sample, that is, the distribution network when the wind disaster fault sample occurs. Power grid ontology parameters, operating status parameters, power outage probability and power outage duration; S2. Perform singular value decomposition on the covariance matrix of the distribution network historical meteorological parameter sample library A and the distribution network wind fault sample library B to obtain the time coefficient X of the main mode of the distribution network historical meteorological parameter sample library A: X＝(X ₁ ,…,X _i ,…,X _N ), Among them, X _N represents the coefficient corresponding to the Nth time sample of the main mode of the meteorological parameter; Further obtain the correlation coefficient C of the main spatial modes of X and B, which is the influence weight on each distribution network: C=(C ₁ ,…,C _i ,…,C _S ), Among them, C _S represents the correlation coefficient corresponding to the S-th distribution network; S3. Use C to build a prediction model: Among them, x _i is the meteorological parameter of the i-th time sample, is the average value of meteorological parameters, and y _i is the predicted value of power outage probability or power outage duration under strong wind disaster in the distribution network. 2. The distribution network wind disaster power outage prediction method based on numerical simulation and SVD model according to claim 1, characterized in that the ontology parameters include tower information and line information of the distribution network. 3. The distribution network wind disaster power outage forecasting method based on numerical simulation and SVD model according to claim 2, characterized in that the tower information includes tower type, number, longitude, latitude, altitude, manufacturer, Installation location, geological environment information, horizontal span, vertical span, tension tower rotation, and insulator string model, string number, and insulator sheet number angle of the tower. 4. The distribution network wind disaster power outage forecasting method based on numerical simulation and SVD model according to claim 2, characterized in that the line information includes line serial number, voltage level, line number, line name, starting and ending locations, Line specifications, line type, number of loops, transmission length, design wind speed, design ice thickness, number of splits and split gaps. 5. The distribution network wind disaster power outage forecasting method based on numerical simulation and SVD model according to claim 1, characterized in that the meteorological parameters include wind speed and wind direction. 6. The distribution network wind disaster power outage prediction method based on numerical simulation and SVD model according to any one of claims 1 to 5, characterized in that it also includes combining the power outage probability and power outage duration under strong wind disaster in the distribution network, Divide wind disasters into several levels and carry out wind disaster early warning. 7. A distribution network wind disaster and power outage forecasting system based on numerical simulation and SVD model, which is characterized in that it includes: a memory, a processor, and a computer program stored in the memory and capable of running on the processor, When the processor executes the computer program, the method for forecasting wind disaster and power outage in the distribution network based on numerical simulation and SVD model described in any one of claims 1 to 6 is implemented. 8. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause the computer to execute the method according to any one of claims 1-6. Distribution network wind disaster and power outage forecasting methods using numerical simulation and SVD model.