Power distribution network operation monitoring method and system based on middle station

Abstract

The invention provides a power distribution network operation monitoring method and system based on a middle station. The method comprises the following steps: acquiring operation data of a power distribution network from a plurality of subsystems related to the power distribution network by adopting the middle station, and performing data processing; inputting the operation data after data processing into a pre-established power distribution network partition model, solving by adopting a particle swarm algorithm, and dividing the power distribution network into a plurality of partitions; based on a middle station, monitoring each partition of the power distribution network; wherein the power distribution network partition model is established based on minimization of line loss and maximization of new energy consumption; according to the invention, the operation data of the power distribution network is obtained from the plurality of subsystems through the middle station, which is beneficial to subsequent defect analysis of the whole power distribution network fault and can also ensure data monitoring and calling among different departments; and the power distribution network is partitioned through the power distribution network partitioning model, so that the data of the power distribution network partitioning can be favorably and finely obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network monitoring, and in particular to a distribution network operation monitoring method and system based on a middle station. Background Art

[0002] The data center is a sustainable mechanism for "making the enterprise's data useful", a strategic choice and organizational form. It is based on the enterprise's unique business model and organizational structure, supported by tangible products and implementation methodologies, to build a mechanism that continuously turns data into assets and serves the business. It is a comprehensive data capability platform that integrates data collection, connectivity, unified governance, modeling analysis, and service applications, providing a capability foundation for the digital transformation of enterprises. The data center is a new stage of high-level application of enterprise data supported by new technologies such as artificial intelligence.

[0003] The distribution network refers to the power grid that receives electric energy from the transmission network or regional power plants and distributes it locally or step by step according to voltage to various users through distribution facilities. As the last gateway to the user in the process of electric energy transmission, the distribution network plays a very important role in the entire power system.

[0004] The distribution network consists of overhead lines, cables, towers, distribution transformers, disconnectors, reactive power compensation capacitors, and some ancillary facilities, and plays an important role in distributing electric energy in the power grid. Traditional distribution network monitoring relies on operation and maintenance personnel to regularly inspect distribution network equipment and obtain distribution network equipment operation data to ensure the normal operation of the distribution network. Traditional distribution network monitoring only stays at the data collection stage and lacks analysis of the load and voltage distribution of the entire distribution network. It is difficult to provide data support for the entire distribution network fault analysis and even the planning of the power network. In addition, the distribution network involves operations, marketing and other departments, and the monitoring data of different departments may be repeated or omitted. The above-mentioned traditional distribution network monitoring method cannot perform defect analysis on the entire distribution network fault, and it is difficult for different departments to obtain data from other departments, and it is also difficult to obtain data on distribution network partitions in a refined manner. Summary of the invention

[0005] In order to solve the problem that the existing technology cannot analyze the entire distribution network fault and different departments are difficult to obtain data from other departments, the present invention proposes a distribution network operation monitoring method based on a middle station, including:

[0006] The middle platform is used to obtain the operation data of the distribution network from multiple subsystems involved in the distribution network and perform data processing;

[0007] Inputting the processed operating data into a pre-established distribution network partition model and using a particle swarm algorithm to solve it, thereby dividing the distribution network into a plurality of partitions;

[0008] Based on the middle station, each partition of the distribution network is monitored;

[0009] Among them, the distribution network partitioning model is established based on minimizing line losses and maximizing new energy consumption.

[0010] Preferably, the construction process of the distribution network partition model includes:

[0011] The inter-zone dispatch objective function is constructed with the goal of minimizing the line loss between each zone of the distribution network;

[0012] The objective function of intra-district dispatch is constructed with the goal of maximizing the consumption of new energy in the distribution network;

[0013] The power flow between each partition of the distribution network is used as the boundary condition of the intra-partition scheduling, and constraint conditions are constructed for the inter-partition scheduling objective function and the intra-partition scheduling objective function to obtain a distribution network partition model;

[0014] The constraint conditions include at least one or more of the following: line flow constraints, controllable load constraints, distributed power supply operation constraints, energy storage operation constraints or system safety constraints.

[0015] Preferably, the operation data after data processing is input into a pre-established distribution network partition model and a particle swarm algorithm is used for solving the distribution network to divide the distribution network into a plurality of partitions, including:

[0016] Inputting the processed operation data into a pre-established distribution network partition model;

[0017] Based on the preset number of partitions, the division points of each partition of the distribution network are corresponded to multiple dimensions representing the position of each particle in the first particle swarm, the power flow between each partition at each time in the distribution network and the purchase of electricity from the upper power grid are corresponded to multiple dimensions representing the operating state of each particle in the first particle swarm, and based on the operating data, the improved particle swarm algorithm is used to optimize and solve the inter-partition scheduling objective function under the constraints of the constraints, so as to obtain multiple optional partitions of the distribution network and the power flow between each optional partition;

[0018] The output of new energy and the charging and discharging power of the energy storage system at each time in each optional partition of the distribution network are corresponded to the dimensions of each particle in the second particle swarm, and the power flow between each optional partition at each time is used as the boundary condition. Based on the operation data, an improved particle swarm algorithm is used to optimize and solve the scheduling objective function in the partition under the constraint of the constraint condition, so as to obtain the optimized scheduling scheme of each optional partition of the distribution network;

[0019] The operation data is optimized based on the optimized scheduling scheme of each optional partition, and the inter-partition scheduling objective function and the intra-partition scheduling objective function are cyclically iterated and solved based on the optimized operation data until the variance of the position change of the division point between each optional partition of the distribution network between two iterations is less than a preset position threshold or reaches a preset cycle number threshold, thereby obtaining multiple partitions of the distribution network;

[0020] The improved particle swarm algorithm uses a nonlinear reduction method to perform nonlinear improvement on the inertia weight and learning factor in the particle swarm algorithm.

[0021] Preferably, the inertia weight in the particle swarm algorithm is nonlinearly improved by the following formula:

[0022]

[0023] Among them, ω* is the inertia weight of the improved particle swarm algorithm, ω start is the initial value of the inertia weight, ω end is the final value of the inertia weight, T is the current number of iterations, T max is the maximum number of iterations, and k is the shape adjustment coefficient.

[0024] Preferably, the learning factor includes a first learning factor for adjusting the amount of individual optimal position learning and a second learning factor for adjusting the amount of global optimal position learning, and the first learning factor is improved offline based on the following formula:

[0025]

[0026] Among them, c1 is the first learning factor, c 1start is the initial value of the first learning factor, c 1end is the final value of the first learning factor, T is the current iteration number, T max is the maximum number of iterations, k is the shape adjustment coefficient;

[0027] The second learning is based on the following formula for nonlinear improvement:

[0028]

[0029] Among them, c2 is the second learning factor, c 2start is the initial value of the second learning factor, c 2end is the final value of the second learning factor.

[0030] Preferably, the middle station is used to obtain the operation data of the distribution network from multiple subsystems related to the distribution network and perform data processing, including:

[0031] Use the middle platform to obtain the operation data of the distribution network from multiple subsystems involved in the distribution network;

[0032] Perform data cleaning, data normalization and data fusion on the operation data obtained from each subsystem to obtain the operation data after data processing;

[0033] The subsystem includes at least one or more of the following: an operation subsystem, a marketing subsystem or a management subsystem.

[0034] Preferably, the monitoring of each partition of the distribution network based on the middle station includes:

[0035] When the subsystem of the distribution network needs to monitor the data in its own subsystem, the division mode of each partition of the distribution network is obtained through the middle station, and the data is obtained from its own subsystem as needed to monitor each partition of the distribution network;

[0036] When a subsystem of the distribution network needs to monitor data outside its own subsystem, the division of each partition of the distribution network is obtained through the middle station, and the required data is obtained from the middle station as needed to monitor each partition of the distribution network.

[0037] Based on the same inventive concept, the present invention also provides a distribution network operation monitoring system based on a middle station, including: a data acquisition and processing module, a partition division module and a monitoring module;

[0038] The data acquisition and processing module is used to obtain the operation data of the distribution network from multiple subsystems related to the distribution network using the middle station and perform data processing;

[0039] The partition division module is used to input the processed operation data into a pre-established distribution network partition model and use a particle swarm algorithm to solve it, so as to divide the distribution network into a plurality of partitions;

[0040] The monitoring module is used to monitor each partition of the distribution network based on the middle station;

[0041] Among them, the distribution network partitioning model is established based on minimizing line losses and maximizing new energy consumption.

[0042] Preferably, the construction process of the distribution network partition model in the partition division module includes:

[0043] The inter-zone dispatch objective function is constructed with the goal of minimizing the line loss between each zone of the distribution network;

[0044] The objective function of intra-district dispatch is constructed with the goal of maximizing the consumption of new energy in the distribution network;

[0045] The power flow between each partition of the distribution network is used as the boundary condition of the intra-partition scheduling, and constraint conditions are constructed for the inter-partition scheduling objective function and the intra-partition scheduling objective function to obtain a distribution network partition model;

[0046] The constraint conditions include at least one or more of the following: line flow constraints, controllable load constraints, distributed power supply operation constraints, energy storage operation constraints or system safety constraints.

[0047] Preferably, the partition division module is specifically used for:

[0048] Inputting the processed operation data into a pre-established distribution network partition model;

[0049] Based on the preset number of partitions, the division points of each partition of the distribution network are corresponded to multiple dimensions representing the position of each particle in the first particle swarm, the power flow between each partition at each time in the distribution network and the purchase of electricity from the upper power grid are corresponded to multiple dimensions representing the operating state of each particle in the first particle swarm, and based on the operating data, the improved particle swarm algorithm is used to optimize and solve the inter-partition scheduling objective function under the constraints of the constraints, so as to obtain multiple optional partitions of the distribution network and the power flow between each optional partition;

[0050] The output of new energy and the charging and discharging power of the energy storage system at each time in each optional partition of the distribution network are corresponded to the dimensions of each particle in the second particle swarm, and the power flow between each optional partition at each time is used as the boundary condition. Based on the operation data, an improved particle swarm algorithm is used to optimize and solve the scheduling objective function in the partition under the constraint of the constraint condition, so as to obtain the optimized scheduling scheme of each optional partition of the distribution network;

[0051] The operation data is optimized based on the optimized scheduling scheme of each optional partition, and the inter-partition scheduling objective function and the intra-partition scheduling objective function are cyclically iterated and solved based on the optimized operation data until the variance of the position change of the division point between each optional partition of the distribution network between two iterations is less than a preset position threshold or reaches a preset cycle number threshold, thereby obtaining multiple partitions of the distribution network;

[0052] The improved particle swarm algorithm uses a nonlinear reduction method to perform nonlinear improvement on the inertia weight and learning factor in the particle swarm algorithm.

[0053] Preferably, the inertia weight in the particle swarm algorithm in the partitioning module is nonlinearly improved by the following formula:

[0054]

[0055] Among them, ω* is the inertia weight of the improved particle swarm algorithm, ω start is the initial value of the inertia weight, ωend is the final value of the inertia weight, T is the current number of iterations, T max is the maximum number of iterations, and k is the shape adjustment coefficient.

[0056] Preferably, the learning factors in the partition division module include a first learning factor for adjusting the learning amount of the individual optimal position and a second learning factor for adjusting the learning amount of the global optimal position, and the first learning factor is improved offline based on the following formula:

[0057]

[0058] Among them, c1 is the first learning factor, c 1start is the initial value of the first learning factor, c 1end is the final value of the first learning factor, T is the current iteration number, T max is the maximum number of iterations, k is the shape adjustment coefficient;

[0059] The second learning is based on the following formula for nonlinear improvement:

[0060]

[0061] Among them, c2 is the second learning factor, c 2start is the initial value of the second learning factor, c 2end is the final value of the second learning factor.

[0062] Preferably, the data acquisition and processing module is specifically used for:

[0063] Use the middle platform to obtain the operation data of the distribution network from multiple subsystems involved in the distribution network;

[0064] Perform data cleaning, data normalization and data fusion on the operation data obtained from each subsystem to obtain the operation data after data processing;

[0065] The subsystem includes at least one or more of the following: an operation subsystem, a marketing subsystem or a management subsystem.

[0066] Preferably, the monitoring module is specifically used for:

[0067] When the subsystem of the distribution network needs to monitor the data in its own subsystem, the division mode of each partition of the distribution network is obtained through the middle station, and the data is obtained from its own subsystem as needed to monitor each partition of the distribution network;

[0068] When a subsystem of the distribution network needs to monitor data outside its own subsystem, the division of each partition of the distribution network is obtained through the middle station, and the required data is obtained from the middle station as needed to monitor each partition of the distribution network.

[0069] In yet another aspect, the present invention further provides a computing device, comprising: at least one processor and a memory;

[0070] The memory is used to store one or more programs;

[0071] When the one or more programs are executed by the one or more processors, a distribution network operation monitoring method based on a middle station as described above is implemented.

[0072] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed, a distribution network operation monitoring method based on a middle station as described above is implemented.

[0073] Compared with the prior art, the present invention has the following beneficial effects:

[0074] The present invention provides a distribution network operation monitoring method and system based on a middle station, comprising: using the middle station to obtain the operation data of the distribution network from multiple subsystems involved in the distribution network and perform data processing; inputting the processed operation data into a pre-established distribution network partition model and using a particle swarm algorithm to solve it, and dividing the distribution network into multiple partitions; based on the middle station, monitoring each partition of the distribution network; wherein the distribution network partition model is established based on minimizing line losses and maximizing new energy consumption; the present invention obtains the operation data of the distribution network from multiple subsystems through the middle station, which is beneficial to the subsequent defect analysis of the entire distribution network fault, and can also ensure data monitoring and calling between different departments; partitioning the distribution network through the distribution network partition model is beneficial to obtaining the data of the distribution network partitions in a refined manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 A flow chart of a distribution network operation monitoring method based on a middle station provided by the present invention;

[0076] Figure 2 A schematic diagram of the structure of a distribution network operation monitoring system based on a middle station provided by the present invention;

[0077] Figure 3 The present invention provides a schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0078] The present invention proposes a distribution network operation monitoring method and system based on a middle station, which obtains the operation data of the distribution network from multiple subsystems through the middle station, which is beneficial to the subsequent defect analysis of the entire distribution network fault, and can also ensure data monitoring and calling between different departments; the distribution network is partitioned through the distribution network partition model, which is beneficial to obtain the data of the distribution network partition in a refined manner. The present invention further adopts a nonlinear reduction method to perform nonlinear improvement on the inertia weight and learning factor in the particle swarm algorithm to optimize the particle swarm algorithm, improve the convergence accuracy of the algorithm, and then can optimize the energy parameters in a larger range under the constraints, ensuring the comprehensiveness of the energy parameter optimization process.

[0079] Embodiment 1:

[0080] A distribution network operation monitoring method based on the middle station, such as Figure 1 Shown: Included:

[0081] Step 1: Use the middle platform to obtain the operation data of the distribution network from multiple subsystems involved in the distribution network and process the data;

[0082] Step 2: Input the processed operating data into the pre-established distribution network partition model and use the particle swarm algorithm to solve it, dividing the distribution network into multiple partitions;

[0083] Step 3: Based on the middle station, monitor each partition of the distribution network;

[0084] Among them, the distribution network partitioning model is established based on minimizing line losses and maximizing new energy consumption.

[0085] Specifically, step 1 includes:

[0086] Use the middle platform to obtain the operation data of the distribution network from multiple subsystems involved in the distribution network;

[0087] Perform data cleaning, data normalization and data fusion on the operation data obtained from each subsystem to obtain the operation data after data processing;

[0088] Data cleaning includes:

[0089] A1: Outlier processing:

[0090] Missing value imputation: Impute missing values ​​using interpolation or mean.

[0091] Noise Removal: Use filters or smoothing algorithms to remove noise.

[0092] A2: Data verification:

[0093] Logical verification: Check the logical consistency of data.

[0094] Range check: Check whether the data is within a reasonable range.

[0095] Data normalization involves scaling the data to the [0,1] interval.

[0096] Data fusion includes:

[0097] B1: Multi-source data fusion:

[0098] Data splicing: combining data from different sources into one data set.

[0099] Data alignment: Ensure that the timestamps of different data are consistent.

[0100] B2: Data Synchronization:

[0101] Timestamp Alignment: Use timestamps to align data from different data sources.

[0102] Interpolation method: interpolate missing data.

[0103] Specifically, the construction process of the distribution network partition model in step 2 includes:

[0104] The inter-zone dispatch objective function is constructed with the goal of minimizing the line loss between each zone of the distribution network;

[0105] The objective function of intra-district dispatch is constructed with the goal of maximizing the consumption of new energy in the distribution network;

[0106] The power flow between each partition of the distribution network is used as the boundary condition of the intra-partition dispatch, and the constraint conditions are constructed for the inter-partition dispatch objective function and the intra-partition dispatch objective function to obtain the distribution network partition model;

[0107] The constraint conditions include at least one or more of the following: line flow constraints, controllable load constraints, distributed power supply operation constraints, energy storage operation constraints or system safety constraints.

[0108] The present invention obtains the operating data of the distribution network from multiple subsystems through the middle station, which is beneficial to the subsequent defect analysis of the entire distribution network fault and can also ensure data monitoring and calling between different departments.

[0109] Step 2 specifically includes:

[0110] Step 21: input the processed operation data into a pre-established distribution network partition model;

[0111] Step 22: Based on the preset number of partitions, the division points of each partition of the distribution network are corresponded to multiple dimensions representing the position of each particle in the first particle swarm, the power flow between each partition at each time in the distribution network and the power purchase from the upper power grid are corresponded to multiple dimensions representing the operating state of each particle in the first particle swarm, and based on the operating data, the improved particle swarm algorithm is used to optimize and solve the inter-partition scheduling objective function under the constraints of the constraints, and multiple optional partitions of the distribution network and the power flow between the optional partitions are obtained;

[0112] Step 23: The output of new energy and the charging and discharging power of the energy storage system at each time in each optional partition of the distribution network are corresponded to the dimensions of each particle in the second particle swarm. The power flow between each optional partition at each time is used as the boundary condition. Based on the operation data, the improved particle swarm algorithm is used to optimize and solve the scheduling objective function within the partition under the constraint of the constraint condition, and the optimized scheduling scheme of each optional partition of the distribution network is obtained;

[0113] Step 24: Optimize the operation data based on the optimized scheduling scheme of each optional partition, and then jump to step 22 to perform cyclic iterative solutions to the inter-partition scheduling objective function and the intra-partition scheduling objective function based on the optimized operation data until the variance of the position change of the division points between the optional partitions of the distribution network between two iterations is less than a preset position threshold or reaches a preset cycle number threshold, thereby obtaining multiple partitions of the distribution network;

[0114] The improved particle swarm algorithm uses a nonlinear reduction method to perform nonlinear improvement on the inertia weight and learning factor in the particle swarm algorithm.

[0115] In the standard multi-objective particle swarm algorithm, the particle speed and position update mechanism is obtained by organically combining the individual historical optimal position and the population historical optimal position, as shown in the following formula:

[0116]

[0117] Among them, ω is the inertia weight, c1 is the first learning factor for adjusting the individual optimal position learning amount, c2 is the second learning factor for adjusting the global optimal position learning amount, r1 and r2 are random numbers in the [0,1] interval, is the position of particle i after the Tth iteration, is the speed of particle i after the Tth iteration, is the individual optimal position currently searched by particle i, is the individual optimal position currently searched by particle i, is the global optimal position currently searched by particle i, and T is the current number of iterations.

[0118] Conventional inertia weight ω mostly adopts a single adjustment strategy of fixed value or linear decrease in the algorithm iteration process, which is difficult to take into account the local and global optimization capabilities of the algorithm. In order to improve the flowchart of the particle swarm algorithm, a nonlinear inertia weight adjustment strategy is adopted, so that the inertia weight in the early stage of the algorithm iteration takes a larger value, which has a good global optimization capability, and the inertia weight in the later stage of the iteration takes a smaller value, which has a stronger global optimization capability and improves the convergence accuracy. Therefore, the optimized inertia weight decreases nonlinearly during the iteration process. This embodiment performs nonlinear improvement in the following way:

[0119]

[0120] Among them, ω* is the inertia weight of the improved particle swarm algorithm, ω start is the initial value of the inertia weight, usually 0.9, ω end is the final value of the inertia weight, usually 0.4, T is the current iteration number, T max is the maximum number of iterations, k is the shape adjustment coefficient, which can adjust the slope of the inertia weight reduction curve (when k takes a negative value, the curve decreases nonlinearly, otherwise, it increases nonlinearly).

[0121] The first learning factor c1 and the second learning factor c2 respectively determine the size of the particle's learning amount for the individual optimal position and the global optimal position. In the standard multi-objective particle swarm algorithm, the first learning factor c1 and the second learning factor c2 are both constants. The weights of the self-cognition item and the social cognition item cannot be coordinated during the iteration process, which makes the algorithm easy to fall into the local optimal solution, resulting in poor performance in terms of convergence accuracy. For this reason, the first learning factor c1 of this application adopts a nonlinear decreasing learning factor, and the second learning factor c2 adopts a non-offline increasing learning factor, so that the self-cognition part of the algorithm plays a dominant role in the early stage of the iteration, and the social cognition part plays a dominant role in the later stage of the iteration. Therefore, the first learning factor of this application satisfies the following formula:

[0122]

[0123] Among them, c1 is the first learning factor, c 1start is the initial value of the first learning factor, c 1end is the final value of the first learning factor, T is the current iteration number, T max is the maximum number of iterations, k is the shape adjustment coefficient;

[0124] The second learning factor satisfies the following formula:

[0125]

[0126] Among them, c2 is the second learning factor, c 2start is the initial value of the second learning factor, c 2endis the final value of the second learning factor.

[0127] The present invention adopts nonlinear inertia weights and / or learning factors to improve the convergence accuracy of the algorithm, thereby being able to optimize energy parameters within a wider range under constraints, thereby ensuring the comprehensiveness of the energy parameter optimization process.

[0128] Step 3 specifically includes:

[0129] When the subsystem of the distribution network needs to monitor the data within its own subsystem, the distribution network division method is obtained through the middle station, and the data is obtained from its own subsystem as needed to monitor the distribution network divisions;

[0130] When a subsystem of the distribution network needs to monitor data outside its own subsystem, the division of each partition of the distribution network is obtained through the middle station, and the required data is obtained from the middle station as needed to monitor each partition of the distribution network.

[0131] The present invention can perform refined monitoring of each partition of the distribution network through the middle station. When the data to be monitored only involves its own subsystem, data can be obtained from its own subsystem for monitoring, which is relatively simple and quick. When necessary, data outside its own subsystem can also be obtained through the middle station to obtain more complete data for monitoring.

[0132] Embodiment 2:

[0133] The present invention based on the same inventive concept also provides a distribution network operation monitoring system based on a middle station, such as Figure 2 As shown, it includes: a data acquisition and processing module, a partitioning module and a monitoring module;

[0134] The data acquisition and processing module is used to obtain the operation data of the distribution network from multiple subsystems related to the distribution network using the middle station and perform data processing;

[0135] The partition division module is used to input the processed operation data into a pre-established distribution network partition model and use a particle swarm algorithm to solve it, so as to divide the distribution network into a plurality of partitions;

[0136] The monitoring module is used to monitor each partition of the distribution network based on the middle station;

[0137] Among them, the distribution network partitioning model is established based on minimizing line losses and maximizing new energy consumption.

[0138] Preferably, the construction process of the distribution network partition model in the partition division module includes:

[0139] The inter-zone dispatch objective function is constructed with the goal of minimizing the line loss between each zone of the distribution network;

[0140] The objective function of intra-district dispatch is constructed with the goal of maximizing the consumption of new energy in the distribution network;

[0141] The power flow between each partition of the distribution network is used as the boundary condition of the intra-partition scheduling, and constraint conditions are constructed for the inter-partition scheduling objective function and the intra-partition scheduling objective function to obtain a distribution network partition model;

[0142] The constraint conditions include at least one or more of the following: line flow constraints, controllable load constraints, distributed power supply operation constraints, energy storage operation constraints or system safety constraints.

[0143] Preferably, the partition division module is specifically used for:

[0144] Inputting the processed operation data into a pre-established distribution network partition model;

[0145] Based on the preset number of partitions, the division points of each partition of the distribution network are corresponded to multiple dimensions representing the position of each particle in the first particle swarm, the power flow between each partition at each time in the distribution network and the purchase of electricity from the upper power grid are corresponded to multiple dimensions representing the operating state of each particle in the first particle swarm, and based on the operating data, the improved particle swarm algorithm is used to optimize and solve the inter-partition scheduling objective function under the constraints of the constraints, so as to obtain multiple optional partitions of the distribution network and the power flow between each optional partition;

[0146] The output of new energy and the charging and discharging power of the energy storage system at each time in each optional partition of the distribution network are corresponded to the dimensions of each particle in the second particle swarm, and the power flow between each optional partition at each time is used as the boundary condition. Based on the operation data, an improved particle swarm algorithm is used to optimize and solve the scheduling objective function in the partition under the constraint of the constraint condition, so as to obtain the optimized scheduling scheme of each optional partition of the distribution network;

[0147] The operation data is optimized based on the optimized scheduling scheme of each optional partition, and the inter-partition scheduling objective function and the intra-partition scheduling objective function are cyclically iterated and solved based on the optimized operation data until the variance of the position change of the division point between each optional partition of the distribution network between two iterations is less than a preset position threshold or reaches a preset cycle number threshold, thereby obtaining multiple partitions of the distribution network;

[0148] The improved particle swarm algorithm uses a nonlinear reduction method to perform nonlinear improvement on the inertia weight and learning factor in the particle swarm algorithm.

[0149] Preferably, the inertia weight in the particle swarm algorithm in the partitioning module is nonlinearly improved by the following formula:

[0150]

[0151] Among them, ω* is the inertia weight of the improved particle swarm algorithm, ω start is the initial value of the inertia weight, ω end is the final value of the inertia weight, T is the current number of iterations, T max is the maximum number of iterations, and k is the shape adjustment coefficient.

[0152] Preferably, the learning factors in the partition division module include a first learning factor for adjusting the learning amount of the individual optimal position and a second learning factor for adjusting the learning amount of the global optimal position, and the first learning factor is improved offline based on the following formula:

[0153]

[0154] Among them, c1 is the first learning factor, c 1start is the initial value of the first learning factor, c 1end is the final value of the first learning factor, T is the current iteration number, T max is the maximum number of iterations, k is the shape adjustment coefficient;

[0155] The second learning is based on the following formula for nonlinear improvement:

[0156]

[0157] Among them, c2 is the second learning factor, c 2start is the initial value of the second learning factor, c 2end is the final value of the second learning factor.

[0158] Preferably, the data acquisition and processing module is specifically used for:

[0159] Use the middle platform to obtain the operation data of the distribution network from multiple subsystems involved in the distribution network;

[0160] Perform data cleaning, data normalization and data fusion on the operation data obtained from each subsystem to obtain the operation data after data processing;

[0161] The subsystem includes at least one or more of the following: an operation subsystem, a marketing subsystem or a management subsystem.

[0162] Preferably, the monitoring module is specifically used for:

[0163] When the subsystem of the distribution network needs to monitor the data in its own subsystem, the division mode of each partition of the distribution network is obtained through the middle station, and the data is obtained from its own subsystem as needed to monitor each partition of the distribution network;

[0164] When a subsystem of the distribution network needs to monitor data outside its own subsystem, the division of each partition of the distribution network is obtained through the middle station, and the required data is obtained from the middle station as needed to monitor each partition of the distribution network.

[0165] Example 3

[0166] like Figure 3 As shown, the present invention also provides an electronic device, which may be a computer device, a single-chip device, an intelligent mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, the processor, and the transceiver component are connected via a bus; the memory may be used to store an execution program, and an exemplary execution program may include instructions; the processor is used to execute the instructions stored in the memory. The memory may also be used to store data, which may be called and / or modified when the instructions are executed.

[0167] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in a storage medium to implement the corresponding method flow or corresponding functions, so as to implement the steps of a distribution network operation monitoring method based on the middle station in the above-mentioned embodiment.

[0168] Example 4

[0169] Based on the same inventive concept, the present invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It can be understood that the storage medium here can include both built-in storage media in electronic devices and, of course, extended storage media supported by electronic devices. The storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by a processor are also stored in the storage space, and these instructions can be one or more execution programs (including program codes). It should be noted that the storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage. The processor loads and executes one or more instructions stored in the storage medium, which can implement the steps of a distribution network operation monitoring method based on a middle station in the above embodiment.

[0170] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0171] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0172] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0173] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0174] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the scope of the claims of the present invention to be approved.

Claims

1. A distribution network operation monitoring method based on a middle station, characterized in that: include: The middle platform is used to obtain the operation data of the distribution network from multiple subsystems involved in the distribution network and perform data processing; Inputting the processed operating data into a pre-established distribution network partition model and using a particle swarm algorithm to solve it, thereby dividing the distribution network into a plurality of partitions; Based on the middle station, each partition of the distribution network is monitored; Among them, the distribution network partitioning model is established based on minimizing line losses and maximizing new energy consumption.

2. The method according to claim 1, characterized in that The construction process of the distribution network partition model includes: The inter-zone dispatch objective function is constructed with the goal of minimizing the line loss between each zone of the distribution network; The objective function of intra-district dispatch is constructed with the goal of maximizing the consumption of new energy in the distribution network; The power flow between each partition of the distribution network is used as the boundary condition of the intra-partition scheduling, and constraint conditions are constructed for the inter-partition scheduling objective function and the intra-partition scheduling objective function to obtain a distribution network partition model; The constraint conditions include at least one or more of the following: line flow constraints, controllable load constraints, distributed power supply operation constraints, energy storage operation constraints or system safety constraints.

3. The method according to claim 2, characterized in that The processed operation data is input into a pre-established distribution network partition model and a particle swarm algorithm is used to solve the distribution network, and the distribution network is divided into a plurality of partitions, including: Inputting the processed operation data into a pre-established distribution network partition model; Based on the preset number of partitions, the division points of each partition of the distribution network are corresponded to multiple dimensions representing the position of each particle in the first particle swarm, the power flow between each partition at each time in the distribution network and the purchase of electricity from the upper power grid are corresponded to multiple dimensions representing the operating state of each particle in the first particle swarm, and based on the operating data, the improved particle swarm algorithm is used to optimize and solve the inter-partition scheduling objective function under the constraints of the constraints, so as to obtain multiple optional partitions of the distribution network and the power flow between each optional partition; The output of new energy and the charging and discharging power of the energy storage system at each time in each optional partition of the distribution network are corresponded to the dimensions of each particle in the second particle swarm, and the power flow between each optional partition at each time is used as the boundary condition. Based on the operation data, an improved particle swarm algorithm is used to optimize and solve the scheduling objective function in the partition under the constraint of the constraint condition, so as to obtain the optimized scheduling scheme of each optional partition of the distribution network; The operation data is optimized based on the optimized scheduling scheme of each optional partition, and the inter-partition scheduling objective function and the intra-partition scheduling objective function are cyclically iterated and solved based on the optimized operation data until the variance of the position change of the division point between each optional partition of the distribution network between two iterations is less than a preset position threshold or reaches a preset cycle number threshold, thereby obtaining multiple partitions of the distribution network; The improved particle swarm algorithm uses a nonlinear reduction method to perform nonlinear improvement on the inertia weight and learning factor in the particle swarm algorithm.

4. The method according to claim 3, characterized in that The inertia weight in the particle swarm algorithm is improved nonlinearly by the following formula: Among them, ω* is the inertia weight of the improved particle swarm algorithm, ω start is the initial value of the inertia weight, ω end is the final value of the inertia weight, T is the current number of iterations, T max is the maximum number of iterations, and k is the shape adjustment coefficient.

5. The method according to claim 3, characterized in that The learning factor includes a first learning factor for adjusting the amount of individual optimal position learning and a second learning factor for adjusting the amount of global optimal position learning. The first learning factor is improved offline based on the following formula: Among them, c1 is the first learning factor, c 1start is the initial value of the first learning factor, c 1end is the final value of the first learning factor, T is the current iteration number, T max is the maximum number of iterations, k is the shape adjustment coefficient; The second learning is based on the following formula for nonlinear improvement: Among them, c2 is the second learning factor, c 2start is the initial value of the second learning factor, c 2end is the final value of the second learning factor.

6. The method according to claim 1, characterized in that The middle platform is used to obtain the operation data of the distribution network from multiple subsystems involved in the distribution network and perform data processing, including: Use the middle platform to obtain the operation data of the distribution network from multiple subsystems involved in the distribution network; Perform data cleaning, data normalization and data fusion on the operation data obtained from each subsystem to obtain the operation data after data processing; The subsystem includes at least one or more of the following: an operation subsystem, a marketing subsystem or a management subsystem.

7. The method according to claim 1, characterized in that Based on the middle station, each partition of the distribution network is monitored, including: When the subsystem of the distribution network needs to monitor the data in its own subsystem, the division mode of each partition of the distribution network is obtained through the middle station, and the data is obtained from its own subsystem as needed to monitor each partition of the distribution network; When a subsystem of the distribution network needs to monitor data outside its own subsystem, the division of each partition of the distribution network is obtained through the middle station, and the required data is obtained from the middle station as needed to monitor each partition of the distribution network.

8. A distribution network operation monitoring system based on a middle station, characterized in that: include: Data acquisition and processing module, partitioning module and monitoring module; The data acquisition and processing module is used to obtain the operation data of the distribution network from multiple subsystems related to the distribution network using the middle station and perform data processing; The partition division module is used to input the processed operation data into a pre-established distribution network partition model and use a particle swarm algorithm to solve it, so as to divide the distribution network into a plurality of partitions; The monitoring module is used to monitor each partition of the distribution network based on the middle station; Among them, the distribution network partitioning model is established based on minimizing line losses and maximizing new energy consumption.

9. The system according to claim 8, characterized in that The construction process of the distribution network partition model in the partition division module includes: The inter-zone dispatch objective function is constructed with the goal of minimizing the line loss between each zone of the distribution network; The objective function of intra-district dispatch is constructed with the goal of maximizing the consumption of new energy in the distribution network; The power flow between each partition of the distribution network is used as the boundary condition of the intra-partition scheduling, and constraint conditions are constructed for the inter-partition scheduling objective function and the intra-partition scheduling objective function to obtain a distribution network partition model; The constraint conditions include at least one or more of the following: line flow constraints, controllable load constraints, distributed power supply operation constraints, energy storage operation constraints or system safety constraints.

10. The system according to claim 9, characterized in that The partition division module is specifically used for: Inputting the processed operation data into a pre-established distribution network partition model; Based on the preset number of partitions, the division points of each partition of the distribution network are corresponded to multiple dimensions representing the position of each particle in the first particle swarm, the power flow between each partition at each time in the distribution network and the purchase of electricity from the upper power grid are corresponded to multiple dimensions representing the operating state of each particle in the first particle swarm, and based on the operating data, the improved particle swarm algorithm is used to optimize and solve the inter-partition scheduling objective function under the constraints of the constraints, so as to obtain multiple optional partitions of the distribution network and the power flow between each optional partition; The output of new energy and the charging and discharging power of the energy storage system at each time in each optional partition of the distribution network are corresponded to the dimensions of each particle in the second particle swarm, and the power flow between each optional partition at each time is used as the boundary condition. Based on the operation data, an improved particle swarm algorithm is used to optimize and solve the scheduling objective function in the partition under the constraint of the constraint condition, so as to obtain the optimized scheduling scheme of each optional partition of the distribution network; The operation data is optimized based on the optimized scheduling scheme of each optional partition, and the inter-partition scheduling objective function and the intra-partition scheduling objective function are cyclically iterated and solved based on the optimized operation data until the variance of the position change of the division point between each optional partition of the distribution network between two iterations is less than a preset position threshold or reaches a preset cycle number threshold, thereby obtaining multiple partitions of the distribution network; The improved particle swarm algorithm uses a nonlinear reduction method to perform nonlinear improvement on the inertia weight and learning factor in the particle swarm algorithm.

Images