A method and device for optimizing layout of distributed power grid-connected

Abstract

The application relates to a kind of distributed power grid-connected optimization layout method and device, the method comprises: obtaining the grid state data of the distributed power grid to be installed;The distributed power installation parameter of the distributed power grid to be installed is determined using the grid state data of the distributed power grid to be installed;According to the distributed power installation parameter of the distributed power grid to be installed, the distributed power is installed in the distributed power grid to be installed;Wherein, the grid state data includes: distributed power access node level, load demand and geographical environment data.The technical scheme provided by the application has good universality, can truly fit the actual operation of distributed power grid, and can provide real, reliable and effective guidance data for the grid-connected of distributed power in the grid.

Description

Technical Field

[0001] The present invention relates to the field of distributed power grid connection, and in particular to a method and device for optimizing the layout of distributed power grid connection. Background Art

[0002] With the rapid development of society and the economy, cascading failures caused by a single power supply model have repeatedly occurred in large power grids. Therefore, a single power supply model can no longer meet the needs of social development. Distributed power sources, primarily based on renewable energy sources such as wind and solar, offer advantages such as flexibility, safety, and cleanliness. However, these energy sources are significantly affected by natural factors such as the geographical environment and weather. When connecting distributed power sources to the grid, improper installation location and capacity configuration will not only fail to realize the many advantages of distributed power sources, but may also have counterproductive effects, such as increased system network losses, increased node voltage offsets, increased short-circuit capacity, complicated relay protection settings, and exceeding the maximum power transmission limit of the conductors.

[0003] Most existing distributed generation grid-connected layout methods use a particle swarm optimization algorithm to optimize the installation location and capacity configuration of distributed generation after establishing an optimization objective function for distributed generation grid connection and determining the constraints. However, this method is computationally complex, has poor versatility, and cannot accurately reflect the actual operation of distributed generation grids. Therefore, it cannot provide real, reliable, and effective guidance data for the integration of distributed generation in power grids. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the purpose of the present invention is to truly fit the distributed power grid in actual operation and provide real, reliable and effective guidance data for the grid connection of distributed power sources in the power grid.

[0005] The purpose of the present invention is achieved by adopting the following technical solutions:

[0006] A method for optimizing the layout of distributed power grid connection is improved in that the method comprises:

[0007] Obtaining grid status data of the grid where the distributed power generation is to be installed;

[0008] Determining the distributed power installed parameters of the distributed power grid to be installed using the grid state data of the distributed power grid to be installed;

[0009] Installing a distributed power supply in the distributed power supply grid to be installed according to the distributed power supply installed parameters of the distributed power supply grid to be installed;

[0010] The grid status data includes: distributed power supply access node level, load demand and geographical environment data.

[0011] Preferably, the determining of the distributed power installed parameters of the distributed power grid to be installed by using the grid state data of the distributed power grid to be installed includes:

[0012] The grid status data of the distributed power grid to be installed is used as the input of a pre-established distributed power grid optimization layout neural network model, the output of the pre-established distributed power grid optimization layout neural network model is obtained, and the output is used as the distributed power installed parameters of the distributed power grid to be installed.

[0013] Furthermore, the training process of the pre-established distributed power grid optimization layout neural network model includes:

[0014] The grid state data of the grid with distributed power installed when no distributed power is installed is used as the input layer training sample of the initial neural network model, and the distributed power installed parameters of the grid with distributed power installed are used as the output layer training sample of the initial neural network model. The initial neural network model is trained to obtain the pre-established distributed power grid optimization layout neural network model.

[0015] Preferably, the distributed power supply installation parameters include: the type of distributed power supply, the number of distributed power supplies and the capacity of the distributed power supply.

[0016] Furthermore, the process of determining the level of the distributed power supply access node includes:

[0017] If the voltage U of the i-th distributed generation access node i Satisfaction|U i -U0|≤a, then the i-th distributed power access node is a stable distributed power access node;

[0018] If the voltage U of the i-th distributed generation access node i Satisfy a<|U i -U0|<b, then the i-th distributed power access node is a small-fluctuation distributed power access node;

[0019] If the voltage U of the i-th distributed generation access node i Satisfaction|U i -U0|≤b, then the i-th distributed power access node is an unstable distributed power access node;

[0020] Wherein, U0 is the standard voltage of the distributed power supply access node, a is the first threshold, and b is the second threshold.

[0021] Furthermore, the constraints for installing a distributed power supply in the grid to be installed with a distributed power supply include:

[0022] If the distributed power access node level is a stable distributed power access node, the node is connected to an uncontrolled distributed power source. If the distributed power access node level is a small-fluctuation distributed power access node, the node is connected to a combined power source of a controllable distributed power source and an uncontrollable distributed power source. If the distributed power access node level is an unstable distributed power access node, the node is connected to a controllable distributed power source.

[0023] Furthermore, the uncontrolled distributed power supply includes a fuel cell power supply and a gas turbine power supply; the controllable distributed power supply includes a photovoltaic cell power supply, a wind turbine power supply and a hydroelectric generator power supply.

[0024] Preferably, the geographical environment data includes: sunshine, wind energy and water flow.

[0025] An optimized layout device for distributed power grid connection, wherein the device comprises:

[0026] An acquisition unit, used to acquire grid status data of the grid to be equipped with a distributed power supply;

[0027] A determining unit, configured to determine the distributed power installed parameters of the distributed power grid to be installed using the grid state data of the distributed power grid to be installed;

[0028] An installation unit, configured to install a distributed power supply in the distributed power supply grid to be installed according to the distributed power supply installed parameters of the distributed power supply grid to be installed;

[0029] The grid status data includes: distributed power supply access node level, load demand and geographical environment data.

[0030] Preferably, the determining unit is specifically configured to:

[0031] The grid status data of the distributed power grid to be installed is used as the input of a pre-established distributed power grid optimization layout neural network model, the output of the pre-established distributed power grid optimization layout neural network model is obtained, and the output is used as the distributed power installed parameters of the distributed power grid to be installed.

[0032] Compared with the closest prior art, the present invention has the following beneficial effects:

[0033] The technical solution provided by the present invention obtains grid status data of a distributed power grid to be installed; uses the grid status data of the distributed power grid to be installed to determine the distributed power generation installed parameters of the distributed power grid to be installed; and installs distributed power in the distributed power grid to be installed based on the distributed power generation installed parameters of the distributed power grid to be installed. The distributed power grid connection optimization layout method provided by the present invention has high versatility and can truly fit the actual distributed power grid in operation, and can provide real, reliable, and effective guidance data for the grid connection of distributed power in the power grid.

[0034] By constructing a distributed power grid optimization layout neural network model and inputting the grid status data of the grid to be equipped with distributed power sources into the distributed power grid optimization layout neural network model, the present invention can quickly and efficiently obtain the distributed power generation installation parameters of the grid to be equipped with distributed power sources, thereby achieving an optimized layout of distributed power sources. This greatly improves operation speed and saves manpower. The grid status data takes into account the grid's operating status and geographical environmental conditions, allowing distributed power sources to fully utilize their respective advantages in the grid, significantly reducing the increase in system network losses caused by unreasonable distributed power source installation location and capacity configuration, and effectively avoiding abnormal conditions such as reduced voltage stability, thereby ensuring the safe production and stable operation of the distribution network containing distributed power sources. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of a method for optimizing the layout of distributed power grid connection provided by the present invention;

[0036] Figure 2 Schematic diagram of the structure of a neural network model for optimizing the layout of a distributed power grid provided by an embodiment of the present invention;

[0037] Figure 3 This is a schematic structural diagram of an optimized layout device for distributed power grid connection provided by the present invention;

[0038] Figure 4 The figure is a schematic diagram of the structure of a device for determining the level of a distributed power supply access node provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0041] This embodiment provides an optimized layout method for distributed power grid connection, such as Figure 1 The specific steps are as follows:

[0042] Step 101. Obtaining grid status data of the grid to be equipped with distributed power generation;

[0043] The grid status data includes: distributed power supply access node level, load demand and geographical environment data.

[0044] The process of determining the level of the distributed power supply access node includes:

[0045] If the voltage U of the i-th distributed generation access node i Satisfaction|U i -U0|≤a, then the i-th distributed power access node is a stable distributed power access node;

[0046] If the voltage U of the i-th distributed generation access node i Satisfy a<|U i -U0|<b, then the i-th distributed power access node is a small-fluctuation distributed power access node;

[0047] If the voltage U of the i-th distributed generation access node i Satisfaction|U i -U0|≤b, then the i-th distributed power access node is an unstable distributed power access node;

[0048] Wherein, U0 is the standard voltage of the distributed power supply access node, a is the first threshold, and b is the second threshold.

[0049] For example, a=b=7%.

[0050] The voltages of the above-mentioned distributed power supply access nodes are obtained through power flow calculation.

[0051] The geographical environment data include: sunshine, wind energy and water flow.

[0052] Step 102: Determine the distributed power installed parameters of the distributed power grid to be installed using the grid state data of the distributed power grid to be installed;

[0053] The grid status data of the distributed power grid to be installed is used as the input of a pre-established distributed power grid optimization layout neural network model, the output of the pre-established distributed power grid optimization layout neural network model is obtained, and the output is used as the distributed power installed parameters of the distributed power grid to be installed.

[0054] like Figure 2 The figure shows the structure of the neural network model for distributed power grid optimization layout, which includes an input layer, a hidden layer, and an output layer. The training process of the pre-established distributed power grid optimization layout neural network model includes:

[0055] The grid state data of the grid with distributed power installed when no distributed power is installed is used as the input layer training sample of the initial neural network model, and the distributed power installed parameters of the grid with distributed power installed are used as the output layer training sample of the initial neural network model. The initial neural network model is trained to obtain the pre-established distributed power grid optimization layout neural network model.

[0056] The grid state data of the grid with distributed power installed and the process of determining the data when no distributed power is installed are the same as the grid state data and the process of determining the data in step 101, and this step will not be repeated.

[0057] For example, to train the distributed power grid optimization layout neural network model, it is necessary to determine the number of input layer nodes, the number of hidden layer nodes, the weights of the input layer and the hidden layer, the thresholds of the input layer and the hidden layer weights, the number of output layer nodes, the weights of the hidden layer and the output layer, the thresholds of the hidden layer and the output layer weights, the hidden layer transfer function, and the output layer transfer function of the distributed power grid optimization layout neural network model.

[0058] The input is passed to the hidden layer nodes through the input layer, and then passed to the output layer after being processed by the transfer function; the actual output of the output layer is compared with the expected output. If the preset learning end condition is not met, precision debugging is continued, and the error is gradually reduced by adjusting the connection weights and thresholds of each layer until the training requirements are met.

[0059] The conditions for the predetermined learning to end are: the target error is 0.0001 or the maximum number of iterations is 1000 or the initial learning rate reaches 0.1.

[0060] For example, the activation function of the pre-established distributed power grid optimization layout neural network model is an S-type activation function.

[0061] Step 103: Install a distributed power supply in the distributed power supply grid to be installed according to the distributed power supply installed parameters of the distributed power supply grid to be installed;

[0062] The distributed power generation installation parameters include: the type of distributed power generation, the number of distributed power generation and the capacity of distributed power generation.

[0063] The constraints for installing a distributed power supply in the grid to be installed with a distributed power supply include:

[0064] If the distributed power access node level is a stable distributed power access node, the node is connected to an uncontrolled distributed power source. If the distributed power access node level is a small-fluctuation distributed power access node, the node is connected to a combined power source of a controllable distributed power source and an uncontrollable distributed power source. If the distributed power access node level is an unstable distributed power access node, the node is connected to a controllable distributed power source.

[0065] The non-controlled distributed power supply includes a fuel cell power supply and a gas turbine power supply; the controllable distributed power supply includes a photovoltaic cell power supply, a wind turbine power supply and a hydroelectric generator power supply.

[0066] Based on the same inventive concept, the present invention also provides an optimized layout device for distributed power grid connection, such as Figure 3 As shown, the device includes:

[0067] An acquisition unit, used to acquire grid status data of the grid to be equipped with a distributed power supply;

[0068] A determining unit, configured to determine the distributed power installed parameters of the distributed power grid to be installed using the grid state data of the distributed power grid to be installed;

[0069] An installation unit, configured to install a distributed power supply in the distributed power supply grid to be installed according to the distributed power supply installed parameters of the distributed power supply grid to be installed;

[0070] The grid status data includes: distributed power supply access node level, load demand and geographical environment data.

[0071] The determining unit is specifically configured to:

[0072] The grid status data of the distributed power grid to be installed is used as the input of a pre-established distributed power grid optimization layout neural network model, the output of the pre-established distributed power grid optimization layout neural network model is obtained, and the output is used as the distributed power installed parameters of the distributed power grid to be installed.

[0073] The training process of the pre-established distributed power grid optimization layout neural network model includes:

[0074] The grid state data of the grid with distributed power installed when no distributed power is installed is used as the input layer training sample of the initial neural network model, and the distributed power installed parameters of the grid with distributed power installed are used as the output layer training sample of the initial neural network model. The initial neural network model is trained to obtain the pre-established distributed power grid optimization layout neural network model.

[0075] The distributed power generation installation parameters include: the type of distributed power generation, the number of distributed power generation and the capacity of distributed power generation.

[0076] The process of determining the level of the distributed power supply access node includes:

[0077] If the voltage U of the i-th distributed generation access node i Satisfaction|U i -U0|≤a, then the i-th distributed power access node is a stable distributed power access node;

[0078] If the voltage U of the i-th distributed generation access node i Satisfy a<|U i -U0|<b, then the i-th distributed power access node is a small-fluctuation distributed power access node;

[0079] If the voltage U of the i-th distributed generation access node i Satisfaction|U i -U0|≤b, then the i-th distributed power access node is an unstable distributed power access node;

[0080] Wherein, U0 is the standard voltage of the distributed power supply access node, a is the first threshold, and b is the second threshold.

[0081] The constraints for installing a distributed power supply in the grid to be installed with a distributed power supply include:

[0082] If the distributed power access node level is a stable distributed power access node, the node is connected to an uncontrolled distributed power source. If the distributed power access node level is a small-fluctuation distributed power access node, the node is connected to a combined power source of a controllable distributed power source and an uncontrollable distributed power source. If the distributed power access node level is an unstable distributed power access node, the node is connected to a controllable distributed power source.

[0083] The non-controlled distributed power supply includes a fuel cell power supply and a gas turbine power supply; the controllable distributed power supply includes a photovoltaic cell power supply, a wind turbine power supply and a hydroelectric generator power supply.

[0084] The geographical environment data include: sunshine, wind energy and water flow.

[0085] Based on the same inventive concept, the present invention also provides a device for determining the level of a distributed power supply access node, such as Figure 4 As shown, the device includes:

[0086] The first judgment unit is used to determine if the voltage U i Satisfaction|U i -U0|≤a, then the i-th distributed power access node is a stable distributed power access node;

[0087] The second judgment unit is used to determine if the voltage U i Satisfy a<|U i -U0|<b, then the i-th distributed power access node is a small-fluctuation distributed power access node;

[0088] The third judgment unit is used to determine if the voltage U i Satisfaction|U i -U0|≤b, then the i-th distributed power access node is an unstable distributed power access node;

[0089] Wherein, U0 is the standard voltage of the distributed power supply access node, a is the first threshold, and b is the second threshold.

[0090] Preferably, a=b=7%.

[0091] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0092] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 steps in the process. 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.

[0093] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 The function specified in one or more boxes.

[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for optimizing the layout of distributed power grid connection, characterized in that: The method comprises: Obtaining grid status data of the grid where the distributed power generation is to be installed; Determining the distributed power installed parameters of the distributed power grid to be installed using the grid state data of the distributed power grid to be installed; Installing a distributed power supply in the distributed power supply grid to be installed according to the distributed power supply installed parameters of the distributed power supply grid to be installed; The grid status data includes: distributed power access node level, load demand and geographical environment data; The method of determining the distributed power installed parameters of the distributed power grid to be installed by using the grid state data of the distributed power grid to be installed includes: Using the grid state data of the distributed power grid to be installed as input to a pre-established distributed power grid optimization layout neural network model, obtaining the output of the pre-established distributed power grid optimization layout neural network model, and using the output as the distributed power generation installed parameters of the distributed power grid to be installed; The distributed power generation installed parameters include: the type of distributed power generation, the number of distributed power generation and the capacity of distributed power generation; The process of determining the level of the distributed power supply access node includes: If the voltage U of the i-th distributed generation access node i Satisfaction|U i -U0|≤a, then the i-th distributed power access node is a stable distributed power access node; If the voltage U of the i-th distributed power source access node i satisfies a < |U i - U0| < b, then the i-th distributed power source access node is a small fluctuation distributed power source access node; If the voltage U of the i-th distributed generation access node i Satisfaction|U i -U0|≤b, then the i-th distributed power access node is an unstable distributed power access node; Wherein, U0 is the standard voltage of the distributed power access node, a is the first threshold, and b is the second threshold; The constraints for installing a distributed power supply in the grid to be installed with a distributed power supply include: If the distributed power access node level is a stable distributed power access node, the node is connected to an uncontrolled distributed power source. If the distributed power access node level is a small-fluctuation distributed power access node, the node is connected to a combined power source of controllable distributed power source and uncontrollable distributed power source. If the distributed power access node level is an unstable distributed power access node, the node is connected to a controllable distributed power source.

2. The method according to claim 1, wherein The training process of the pre-established distributed power grid optimization layout neural network model includes: The grid state data of the grid with distributed power installed when no distributed power is installed is used as the input layer training sample of the initial neural network model, and the distributed power installed parameters of the grid with distributed power installed are used as the output layer training sample of the initial neural network model. The initial neural network model is trained to obtain the pre-established distributed power grid optimization layout neural network model.

3. The method according to claim 1, wherein The non-controlled distributed power supply includes a fuel cell power supply and a gas turbine power supply; the controllable distributed power supply includes a photovoltaic cell power supply, a wind turbine power supply and a hydroelectric generator power supply.

4. The method according to claim 1, wherein The geographical environment data include: sunshine, wind energy and water flow.

5. An optimized layout device for distributed power grid connection, characterized in that: The device comprises: An acquisition unit, used to acquire grid status data of the grid to be equipped with a distributed power supply; A determining unit, configured to determine the distributed power installed parameters of the distributed power grid to be installed using the grid state data of the distributed power grid to be installed; An installation unit, configured to install a distributed power supply in the distributed power supply grid to be installed according to the distributed power supply installed parameters of the distributed power supply grid to be installed; The grid status data includes: distributed power supply access node level, load demand and geographical environment data. The determining unit is specifically used to: Using the grid state data of the distributed power grid to be installed as input to a pre-established distributed power grid optimization layout neural network model, obtaining the output of the pre-established distributed power grid optimization layout neural network model, and using the output as the distributed power generation installed parameters of the distributed power grid to be installed; The distributed power generation installed parameters include: the type of distributed power generation, the number of distributed power generation and the capacity of distributed power generation; The process of determining the level of the distributed power supply access node includes: If the voltage U of the i-th distributed generation access node i Satisfaction|U i -U0|≤a, then the i-th distributed power access node is a stable distributed power access node; If the voltage U of the i-th distributed power source access node i satisfies a < |U i - U0| < b, then the i-th distributed power source access node is a small fluctuation distributed power source access node; If the voltage U of the i-th distributed generation access node i Satisfaction|U i -U0|≤b, then the i-th distributed power access node is an unstable distributed power access node; Wherein, U0 is the standard voltage of the distributed power access node, a is the first threshold, and b is the second threshold; The constraints for installing a distributed power supply in the grid to be installed with a distributed power supply include: If the distributed power access node level is a stable distributed power access node, the node is connected to an uncontrolled distributed power source. If the distributed power access node level is a small-fluctuation distributed power access node, the node is connected to a combined power source of controllable distributed power source and uncontrollable distributed power source. If the distributed power access node level is an unstable distributed power access node, the node is connected to a controllable distributed power source.

Images