Control method for grid-connected operation of distributed power sources
By predicting and adjusting the grid-connected capacity and transmission capacity of distributed power supplies, the energy waste caused by poor load prediction and grid-connected control strategies are solved, and the maximum utilization of energy and the smooth operation of power stations are achieved.
Patent Information
- Application Number
- CN202210368974.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-08
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-04-08
AI Technical Summary
In the prior art, poor load prediction and grid-connected control strategies lead to energy waste, especially in the complex grid scheduling in distributed power grid-connected power generation.
By obtaining multiple factors that affect the power generation capacity of the target station area and the distributed power generation capacity, the neural network is used to predict the power load and power generation capacity, and the grid-connected capacity of the distributed power supply and the upper transmission line are adjusted according to the power load and power generation capacity. The transmission capacity and user's electricity consumption behavior optimize energy utilization.
It realizes the prediction of various factors of electricity load and power generation capacity, adjusts the capacity of electricity consumption and grid-connected power generation, maximizes the use of the power source to obtain electricity, ensures the smooth operation of the power station, and saves energy.
Smart Images

Figure CN114725932B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of grid-connected power generation, and in particular to a distributed power supply grid-connected operation control method. Background Art
[0002] The 22nd meeting of the 5G Working Group of the International Telecommunication Union Radiocommunication Sector (ITU-R) was held. 5G was officially named IMT-2020, and the IMT-2020 vision and timetable were released. At the same time, 5G was divided into three main application scenarios:
[0003] eMBB (Enhanced Mobile Broadband);
[0004] URLLC (Ultra-reliable and Low Latency Communications);
[0005] mMTC (Massive Machine Type Communication).
[0006] The Internet of Things is mMTC—massive machine type communication, which is mainly aimed at network access scenarios for massive devices. 5G massive machine type communication (mMTC) focuses on solving the problem that traditional mobile communications cannot well support the Internet of Things and vertical industry applications. Low-power large connection scenarios are mainly aimed at application scenarios such as smart cities, environmental monitoring, smart homes, and forest fire prevention that target sensing and data collection. They have the characteristics of small data packets, low power consumption, and massive connections. This type of terminal is widely distributed and numerous, which not only requires the network to have the ability to support more than 100 billion connections and meet the 1 million / km2 connection density indicator requirements, but also to ensure ultra-low power consumption and ultra-low cost of the terminal.
[0007] The Internet of Things based on 5G networks facilitates the development and utilization of big data. Its importance is self-evident, especially for application scenarios like power grid power supply involving electricity consumption in thousands of households.
[0008] For example, as new technologies continue to emerge, more and more new energy sources and new energy storage devices will be applied to the power system. A large part of the application of new energy sources such as wind energy, solar energy, and biomass energy is decentralized and has a small capacity. These decentralized power generation devices with a capacity ranging from several kilowatts to tens of megawatts, environmentally compatible, and energy-saving, such as gas turbines, internal combustion engines, small photovoltaic power stations, fuel cells, wind turbines, etc., which are arranged near the power load, are called distributed generation (DG).
[0009] There are always some undesirable factors in the operation of existing power supply lines. How to deal with the peak and valley of electricity consumption in a short period of time is always a test for technicians in this field. Although distributed power sources can make use of renewable energy as much as possible, the grid-connected power generation of distributed power sources is related to many factors, which makes the already complex grid dispatching strategy more troublesome.
[0010] On the other hand, if the electricity consumption behavior of users on the demand side is in compliance with the dispatch to a certain extent, it can also improve the quality of power supply and reduce unnecessary energy waste. The combination of IoT mMTC and the power grid provides necessary data support for both power supply and power consumption, bringing opportunities for energy dispatch and user electricity consumption behavior guidance.
[0011] Based on this, it is necessary to develop and design a distributed power grid-connected operation control method. Summary of the invention
[0012] The embodiment of the present invention provides a distributed power supply grid-connected operation control method for solving the problem of energy waste caused by poor load forecasting and grid-connected control strategies in the prior art.
[0013] In a first aspect, an embodiment of the present invention provides a distributed power supply grid-connected operation control method, comprising:
[0014] Acquire multiple factors affecting the power consumption of the target area and multiple factors affecting the power generation capacity of the distributed power source, wherein the distributed power source is a distributed power source connected to the grid for power generation in the area;
[0015] Determine the power load in a predetermined time period according to the multiple factors affecting the power consumption of the target area;
[0016] Determining the power generation capacity of the distributed power source within the predetermined time period according to the multiple factors affecting the power generation capacity of the distributed power source;
[0017] According to the power load and the power generation capacity, the grid-connected capacity of the distributed power source, the transmission capacity of the upper transmission line and the power consumption behavior of multiple users are determined, wherein the upper transmission line is a transmission line that supplies power to the target substation, and the user is the power user of the target substation.
[0018] In a possible implementation, the obtaining of multiple factors affecting the target area power consumption and multiple factors affecting the distributed power generation capacity includes:
[0019] Obtaining the identification of the target station area;
[0020] According to the identification of the target area, the identification of each collection terminal is obtained, wherein the collection terminal is a terminal for collecting factors affecting the power consumption of the target area and a terminal for collecting factors affecting the power generation capacity of the distributed power source;
[0021] According to the identifier of each of the collection terminals, respectively obtain the collection data from each of the collection terminals;
[0022] The plurality of collected data are classified to obtain the plurality of factors affecting the power consumption of the target area and the plurality of factors affecting the power generation capacity of the distributed power source.
[0023] In a possible implementation, determining the power load in a predetermined time period according to the multiple factors affecting the power consumption of the target area includes:
[0024] Acquire a neural network, wherein the neural network is a neural network that has undergone prediction training;
[0025] Sorting the multiple factors affecting the power consumption of the target substation in a predetermined order to form a first data set;
[0026] The first data set is input into the neural network to obtain the power load in a predetermined time period.
[0027] In a possible implementation, the obtaining of the neural network includes:
[0028] Acquire multiple first historical data sets of the target area, wherein the first historical data sets include multiple factors affecting the power consumption of the target area in the corresponding historical period, the multiple factors affecting the power consumption of the target area in each of the first historical data sets are arranged in the same order, and each of the first historical data sets is provided with a label of the power load in the time period;
[0029] determining a loss function of the neural network;
[0030] According to the loss function, a plurality of the first historical data sets of the target station area are input into the neural network to train the neural network until the loss function value is less than a threshold value.
[0031] In a possible implementation, determining the power generation capacity of the distributed power source within the predetermined time period according to the multiple factors affecting the power generation capacity of the distributed power source includes:
[0032] Acquire multiple second historical data sets that affect the power generation capacity of the distributed power source, wherein the second historical data sets include multiple factors that affect the power generation capacity of the distributed power source in a corresponding historical period, and each of the second historical data sets corresponds to a power generation capacity in the time period;
[0033] Generate a second data set according to the multiple factors affecting the power generation capacity of the distributed power generation;
[0034] calculating a distance between the second data set and the plurality of second historical data sets;
[0035] Selecting the second historical data set that is closest to the second data set as the target data set;
[0036] The power generation capacity of the target data set corresponding to the time period is used as the power generation capacity of the distributed power source in the predetermined time period.
[0037] In a possible implementation, determining the grid-connected capacity of the distributed power source, the transmission capacity of the upper transmission line, and the power consumption behavior of multiple users according to the power load and the power generation capacity includes:
[0038] Calculating the difference between the power generation capacity and the power load as the remaining capacity;
[0039] If the remaining capacity is greater than a first threshold, enabling the energy storage electrical devices of the multiple users according to the remaining capacity;
[0040] If the remaining capacity is greater than a second threshold, reducing the grid-connected capacity of the distributed power source;
[0041] If the remaining capacity is less than a third threshold, increasing the grid-connected capacity of the distributed power source;
[0042] If the remaining capacity is less than a fourth threshold, the transmission capacity of the upper transmission line is increased.
[0043] In one possible implementation, the multiple factors affecting the power consumption of the target substation, the multiple factors affecting the power generation capacity of the distributed power sources, and the power consumption behaviors of the multiple users are obtained based on the Internet of Things system, wherein the Internet of Things system uses 5G technology to communicate with each collection terminal and the power consumption terminal, the collection terminal is used to collect the factors affecting the power consumption of the target substation and the factors affecting the power generation capacity of the distributed power sources, and the power consumption terminal is an energy storage power consumption device.
[0044] In a second aspect, an embodiment of the present invention provides a load forecasting and grid-connected control device, comprising:
[0045] An influencing factor acquisition module, used to acquire multiple factors affecting the power consumption of the target area and multiple factors affecting the power generation capacity of the distributed power source, wherein the distributed power source is a distributed power source connected to the grid for power generation in the area;
[0046] A power load prediction module, used to determine the power load in a predetermined time period according to the multiple factors affecting the power consumption of the target substation;
[0047] A power generation capacity prediction module, used to determine the power generation capacity of the distributed power source within the predetermined time period according to the multiple factors affecting the power generation capacity of the distributed power source; and
[0048] A grid-connected control module is used to determine the grid-connected capacity of the distributed power source, the transmission capacity of the upper-level transmission line, and the electricity consumption behavior of multiple users according to the power load and the power generation capacity, wherein the upper-level transmission line is a transmission line that supplies power to the target substation, and the user is the electricity user of the target substation.
[0049] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.
[0050] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.
[0051] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0052] The embodiment of the present invention discloses a distributed power grid-connected operation control method, the method obtains multiple factors affecting the power consumption of the target area and multiple factors affecting the power generation capacity of the distributed power source; according to the multiple factors affecting the power consumption of the target area, the power load of the predetermined time period is determined; according to the multiple factors affecting the power generation capacity of the distributed power source, the power generation capacity of the distributed power source in the predetermined time period is determined; according to the power load and the power generation capacity, the grid-connected capacity of the distributed power source, the transmission capacity of the upper transmission line and the power consumption behavior of multiple users are determined. Therefore, the method of the present invention can predict the power load and power generation capacity through multiple factors, and adjust the power consumption and grid-connected power generation capacity through the predicted data, so as to make the most of the electric energy obtained by the distributed power source, and make the electric energy output by the transmission line stable, ensure the smooth operation of the power station, realize the maximum utilization of energy, and save energy. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0054] Figure 1 It is a schematic diagram of the connection mode between the substation area and the upper transmission line provided by the embodiment of the present invention;
[0055] Figure 2 It is a flow chart of a distributed power supply grid-connected operation control method provided by an embodiment of the present invention;
[0056] Figure 3 It is a basic structural diagram of the LSTM network model provided by an embodiment of the present invention;
[0057] Figure 4 It is a schematic diagram of the prediction principle of the proximity method provided by an embodiment of the present invention;
[0058] Figure 5 It is a functional block diagram of a load forecasting and grid-connected control device provided in an embodiment of the present invention;
[0059] Figure 6 It is a functional block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0060] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary details.
[0061] In order to make the purpose, technical solutions and advantages of the present invention more clear, a specific implementation method will be described below in conjunction with the accompanying drawings.
[0062] The following is a detailed description of an embodiment of the present invention. This example is implemented based on the technical solution of the present invention, and provides a detailed implementation method and a specific operation process, but the protection scope of the present invention is not limited to the following embodiments.
[0063] Figure 1 The schematic diagram of the connection between the substation and the upper transmission line is shown.
[0064] In the figure, a substation 102 is provided with a distributed power source 103 and multiple users' electrical equipment 104, some of which are energy storage equipment, such as electric vehicles, thermal storage water heaters, etc. These electrical equipment can store energy in various energy forms such as electrical energy and thermal energy. Distributed power sources 103 have many forms in real life, such as solar panels, wind power generation equipment, etc.
[0065] The power grid 102 is supplied with electricity from a traditional power plant by an upper transmission line 101. The electricity of the traditional power plant comes from many sources, such as thermal power, hydropower or nuclear power.
[0066] Figure 2 A flow chart of a distributed power supply grid-connected operation control method provided in an embodiment of the present invention.
[0067] like Figure 2 As shown, it shows a flow chart of the implementation of the distributed power grid-connected operation control method provided by the embodiment of the present invention, which is described in detail as follows:
[0068] In step 201, multiple factors affecting the power consumption of the target substation and multiple factors affecting the power generation capacity of the distributed power source are obtained, wherein the distributed power source is a distributed power source connected to the substation for grid-connected power generation.
[0069] In some embodiments, step 201 includes: obtaining an identification of the target substation; obtaining identifications of each collection terminal based on the identification of the target substation, wherein the collection terminal is a terminal for collecting factors affecting power consumption of the target substation and a terminal for collecting factors affecting the power generation capacity of the distributed power source; obtaining collection data from each collection terminal based on the identification of each collection terminal; classifying the multiple collection data to obtain the multiple factors affecting power consumption of the target substation and the multiple factors affecting the power generation capacity of the distributed power source.
[0070] In some embodiments, step 201 includes: obtaining the multiple factors affecting the power consumption of the target substation, the multiple factors affecting the power generation capacity of the distributed power source, and determining the power consumption behavior of the multiple users based on the Internet of Things system, wherein the Internet of Things system uses 5G technology to communicate with each collection terminal and the power consumption terminal, the collection terminal is used to collect the factors affecting the power consumption of the target substation and the factors affecting the power generation capacity of the distributed power source, and the power consumption terminal is an energy storage power consumption device.
[0071] Exemplarily, each target substation is equipped with a corresponding collection terminal, which is used to collect different types of data, such as substation power consumption, reactive power, maximum active power, current, voltage and other indicators. In some application scenarios, it also includes the substation's weather, temperature, wind speed, sunlight intensity, and time. After these data are collected by the collection terminal, they are formed into big data through the Internet of Things built by 5G, which is used for data processing and analysis.
[0072] The big data analysis of the target substation is usually carried out on the data obtained by the collection terminals related to the substation. Therefore, a necessary step is to obtain the identification of the substation, which is a unique identification, and obtain the relevant data affecting the operation of the substation through the identification association.
[0073] After the data is acquired, it is classified into data that affects the power consumption of the substation and data that affects the power generation capacity of distributed power sources. It should be noted that some data can affect both of the above situations. For example, when the temperature is too high, the power consumption will increase appropriately, and at the same time, the expected power generation capacity will also increase, so the temperature should be included in both the data that affects the power consumption of the substation and the data that affects the power generation capacity of distributed power sources.
[0074] In step 202, the power load in a predetermined time period is determined according to the multiple factors affecting the power consumption of the target area.
[0075] In some implementations, step 201 includes:
[0076] Obtain a neural network, wherein the neural network is a neural network that has been trained for prediction; sort the multiple factors that affect the power consumption of the target substation in a predetermined order to form a first data set; input the first data set into the neural network to obtain the power load in a predetermined time period.
[0077] In some embodiments, the acquisition of the neural network includes: acquiring multiple first historical data sets of the target substation, wherein the first historical data sets include multiple factors affecting the electricity consumption of the target substation in the corresponding historical period, the multiple factors affecting the electricity consumption of the target substation in each of the first historical data sets are ranked the same, and each of the first historical data sets is provided with a label of the electricity load in the time period; determining the loss function of the neural network; and according to the loss function, inputting the multiple first historical data sets of the target substation into the neural network to train the neural network until the loss function value is less than a threshold value.
[0078] For example, an artificial neural network (ANN) abstracts the human brain neural network from the perspective of information processing, establishes a simple model, and forms different networks according to different connection methods. In engineering and academia, it is often simply referred to as a neural network or a quasi-neural network. A neural network is a computing model composed of a large number of nodes (or neurons) connected to each other. Each node represents a specific output function, called an activation function. The connection between each two nodes represents a weighted value for the signal passing through the connection, called a weight, which is equivalent to the memory of an artificial neural network. The output of the network varies depending on the connection method of the network, the weight value and the activation function. The network itself is usually an approximation of a certain algorithm or function in nature, or it may be an expression of a logical strategy. Unless otherwise specified in the patent application for this invention, a neural network refers to an artificial neural network.
[0079] The present invention patent application proposes a method for predicting power load through a neural network. In a specific application scenario, the neural network adopts an LSTM network.
[0080] LSTM network (Long Short-Term Memory) is a time recurrent neural network, which is specially designed to solve the long-term dependency problem of general RNN (Recursive Neural Network). All RNNs have a chain form of repeated neural network modules.
[0081] The structure of the recurrent neural network (RNN) and its expansion in the time domain. The internal recurrent neural units constitute the hidden layer in the RNN network. The output of each network node will be fed back to itself and its next node at the same time. This multi-level feedback mechanism enables the RNN network to have a memory function. At time t, the hidden layer receives the current input x t , and its own state h at the previous moment t-1 , forming a ring-shaped network structure, so the RNN network has a certain short-term memory capacity. In addition, its parameters can also be shared, so it has advantages when processing the nonlinear characteristics of the sequence for learning.
[0082] RNN usually uses the back propagation algorithm for model training, but due to its own structural defects, when inputting long sequence data, as the network deepens, the network parameters will decay or increase exponentially, and the gradient value will be approximately equal to 0 or approach infinity, which leads to the gradient vanishing and gradient exploding problems. Due to the rapid development of deep learning in recent years, related research and applications have become more and more in-depth, and corresponding solutions have been proposed for the above problems of recurrent neural networks.
[0083] The LSTM network model provides a new solution for dealing with long-term dependent sequence problems. It is essentially a special RNN network. Compared with the internal neurons of RNN, LSTM not only contains a short-term memory state control unit h, but also adds a control unit c for storing long-term memory. Compared with the long-term memory unit c, the short-term memory unit updates more frequently. With both short-term memory and long-term memory neurons, the LSTM recurrent neural network makes up for the defects of the RNN network model, enabling it to effectively process long-interval time series data.
[0084] Figure 3 The basic structure of the LSTM network model is shown. The LSTM network introduces three gated recurrent units: forget gate, input gate, and output gate. Each unit works together to control the updating and forgetting of memory, realize the storage and flow of memory in the hidden layer units, and improve the prediction accuracy of the network. Figure 3 As shown in the figure, the LSTM network uses the forget valve f t 、Input valve i t , output valve o t and control unit status C t , decide which data needs to be retained and which data needs to be forgotten, thereby solving the long-distance dependency problem of RNN.
[0085] As for the implementation mode of the present invention, the present invention arranges the multiple factors affecting the power consumption of the target substation in a predetermined order, inputs the order into a trained LSTM network, and predicts the power load through the LSTM network.
[0086] In the training of LSTM network, historical data is used to train the LSTM network. The history is first arranged in a predetermined order to form a data set, which is also the first historical data set.
[0087] Before training, a training sample group and a verification sample group are first prepared. Both the training sample group and the verification sample group are data groups composed of multiple first historical data sets, wherein each historical data set is marked with a label of the power load in a predetermined time period.
[0088] Then, the loss function of the neural network is selected. The role of the loss function is to calculate the difference between the forward calculation result of each iteration of the neural network and the true value, so as to guide the next step of training in the right direction. For the patent application of this invention, the true value is the label of the power load of the first historical sample.
[0089] After training with the training sample group, it is then verified with the verification sample group. The prediction accuracy of the trained neural network will gradually improve with training. When the prediction accuracy verified by the verification group is no longer significantly improved, the transmission parameters of the neural network can be fixed at this time, as the LSTM neural network that has been trained for prediction.
[0090] At this time, the first data set is input into the trained LSTM neural network, which will give a predicted power load for a predetermined time period. It is worth noting that the order of arrangement of the multiple factors in the first data set is the same as the order of arrangement of the factors in the first historical data set.
[0091] In step 203, the power generation capacity of the distributed power source within the predetermined time period is determined according to the multiple factors affecting the power generation capacity of the distributed power source.
[0092] In some embodiments, step 203 includes: obtaining multiple second historical data sets that affect the power generation capacity of the distributed power sources, wherein the second historical data sets include multiple factors that affect the power generation capacity of the distributed power sources in the corresponding historical period, and each of the second historical data sets corresponds to a power generation capacity in the time period; generating a second data set according to the multiple factors that affect the power generation capacity of the distributed power sources; calculating the distance between the second data set and the multiple second historical data sets; selecting the second historical data set that is closest to the second data set as the target data set; and using the power generation capacity of the target data set corresponding to the time period as the power generation capacity of the distributed power source in the predetermined time period.
[0093] Exemplarily, similarly, the prediction of the distributed power generation capacity is based on historical data, and various influencing factors in the same historical period are aggregated into a data set, namely, the second historical data set.
[0094] Multiple factors currently affecting the generation capacity of distributed power sources are also collected to form a data set, namely, the second data set.
[0095] Figure 4 The figure shows a principle diagram of the prediction method according to the embodiment of the present invention.
[0096] In the figure, C1, C2, ... C5 are the second historical data sets respectively.
[0097] Cx is the second data set. The distance between the second data and each second historical data set is calculated, and the second historical data set with the smallest distance is selected as the closest historical data set. This proves that the scenario corresponding to Cx is basically the same as the application scenario of the closest historical data set.
[0098] Since each historical data set corresponds to a historical period and the power generation capacity of the historical period is traceable, the power generation capacity of the closest historical data set is selected as the predicted power generation capacity of the distributed power source.
[0099] To judge the distance between two data sets, the most common distance algorithms can be used, such as Euclidean distance, Earth Mover's distance (EMD distance), Manhattan distance, Jaccard distance, Mahalanobis distance, etc.
[0100] Specifically, in an application scenario, the Euclidean distance is used and can be calculated according to the following formula:
[0101]
[0102] Where, d j is the distance between Cx and the jth second historical data, x i is the i-th element of Cx, y i is the j-th element of Cj, and n is the number of elements in the data set.
[0103] In step 204, the grid-connected capacity of the distributed power source, the transmission capacity of the upper transmission line, and the electricity consumption behavior of multiple users are determined based on the power load and the power generation capacity, wherein the upper transmission line is a transmission line that supplies power to the target substation, and the user is an electricity user in the target substation.
[0104] In some embodiments, step 204 includes: calculating the difference between the power generation capacity and the power load as the remaining capacity; if the remaining capacity is greater than a first threshold, enabling the energy storage power equipment of the multiple users according to the remaining capacity; if the remaining capacity is greater than a second threshold, reducing the grid-connected capacity of the distributed power source; if the remaining capacity is less than a third threshold, increasing the grid-connected capacity of the distributed power source; if the remaining capacity is less than a fourth threshold, increasing the transmission capacity of the upper transmission line.
[0105] Exemplarily, the difference between the predicted power generation capacity and the predicted power load is taken as the remaining capacity, and the grid connection plan is determined according to the change of the remaining capacity.
[0106] When there is a lot of remaining capacity, it is preferred to use the remaining capacity for energy storage devices rather than reducing the grid-connected capacity of distributed power sources, in order to maximize the use of the capacity of distributed power sources.
[0107] Energy storage devices include rechargeable cars, thermal storage devices, or devices that convert electrical energy into other energy forms for storage.
[0108] In one implementation, the energy storage device is connected to the Internet of Things system through the 5G network. When the remaining capacity reaches a first threshold, the energy storage device is notified or directly controlled to use electricity.
[0109] When the remaining capacity cannot be consumed by electrical equipment, the grid-connected capacity of the distributed power system should be appropriately reduced to ensure the stability of the load on the upper-level transmission lines.
[0110] From the above, it can be seen that the second threshold is greater than the first threshold.
[0111] When the remaining capacity is small, the power generation efficiency of distributed power sources should be increased and the grid-connected capacity should be increased to maximize the utilization of energy obtained from distributed power sources.
[0112] When the remaining capacity cannot be fully compensated by distributed power sources, the transmission capacity of the upstream transmission lines should be increased.
[0113] In an embodiment of the present invention, a distributed power grid-connected operation control method is provided, wherein the method obtains multiple factors affecting the power consumption of the target substation and multiple factors affecting the power generation capacity of the distributed power source; determines the power load of a predetermined time period according to the multiple factors affecting the power consumption of the target substation; determines the power generation capacity of the distributed power source within the predetermined time period according to the multiple factors affecting the power generation capacity of the distributed power source; determines the grid-connected capacity of the distributed power source, the transmission capacity of the upper transmission line, and the power consumption behavior of multiple users according to the power load and the power generation capacity. Therefore, the method of the present invention can predict the power load and power generation capacity through multiple factors, and adjust the power consumption and grid-connected power generation capacity through the predicted data, so as to make the most of the electric energy obtained by the distributed power source, and make the electric energy output by the transmission line stable, ensure the smooth operation of the power station, realize the maximum utilization of energy, and save energy.
[0114] It should be understood that the size of the serial numbers of the steps in the above implementation does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation method of the present invention.
[0115] The following is an implementation of the device of the present invention. For details not described in detail, reference may be made to the corresponding method implementation described above.
[0116] Figure 5 is a functional block diagram of a load forecasting and grid-connected control device provided in an embodiment of the present invention, referring to Figure 5 The load forecasting and grid-connected control device 5 includes: an influencing factor acquisition module 501 , a power load forecasting module 502 , a power generation capacity forecasting module 503 and a grid-connected control module 504 .
[0117] The influencing factor acquisition module 501 is used to acquire multiple factors that affect the power consumption of the target area and multiple factors that affect the power generation capacity of the distributed power source, wherein the distributed power source is a distributed power source that is connected to the grid for power generation in the area;
[0118] The power load prediction module 502 is used to determine the power load in a predetermined time period according to the multiple factors affecting the power consumption of the target substation;
[0119] A power generation capacity prediction module 503, configured to determine the power generation capacity of the distributed power source within the predetermined time period according to the multiple factors affecting the power generation capacity of the distributed power source; and
[0120] The grid-connected control module 504 is used to determine the grid-connected capacity of the distributed power source, the transmission capacity of the upper-level transmission line, and the electricity consumption behavior of multiple users based on the power load and the power generation capacity, wherein the upper-level transmission line is a transmission line that supplies power to the target substation, and the user is the electricity user of the target substation.
[0121] Figure 6 is a functional block diagram of a terminal provided by an embodiment of the present invention. Figure 6 As shown, the terminal 6 of this embodiment includes: a processor 600, a memory 601, and a computer program 602 stored in the memory 601 and executable on the processor 600. When the processor 600 executes the computer program 602, the steps in the above-mentioned distributed power grid-connected operation control method and the embodiment are implemented, for example Figure 1 Steps 101 to 104 are shown.
[0122] Exemplarily, the computer program 602 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 601 and executed by the processor 600 to implement the present invention.
[0123] The terminal 6 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 6 may include, but is not limited to, a processor 600 and a memory 601. Those skilled in the art will appreciate that Figure 6 It is only an example of terminal 6 and does not constitute a limitation on terminal 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.
[0124] The processor 600 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 gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0125] The memory 601 may be an internal storage unit of the terminal 6, such as a hard disk or memory of the terminal 6. The memory 601 may also be an external storage device of the terminal 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 6. Further, the memory 601 may also include both an internal storage unit of the terminal 6 and an external storage device. The memory 601 is used to store the computer program and other programs and data required by the terminal. The memory 601 may also be used to temporarily store data that has been output or is to be output.
[0126] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method implementation method, which will not be repeated here.
[0127] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0128] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0129] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0131] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0132] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned implementation method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned distributed power grid-connected operation control method and the load forecasting and grid-connected control device implementation method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.
[0133] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A distributed power grid-connected operation control method, It is characterized in that include: Acquire multiple factors affecting the power consumption of the target area and multiple factors affecting the power generation capacity of the distributed power source, wherein the distributed power source is a distributed power source connected to the grid for power generation in the area; Determine the power load in a predetermined time period according to the multiple factors affecting the power consumption of the target area; Determining the power generation capacity of the distributed power source within the predetermined time period according to the multiple factors affecting the power generation capacity of the distributed power source; According to the power load and the power generation capacity, determine the grid-connected capacity of the distributed power source, the transmission capacity of the upper transmission line, and the power consumption behavior of multiple users, wherein the upper transmission line is a transmission line that supplies power to the target substation, and the user is an electricity user in the target substation; in, The obtaining of multiple factors affecting the target area's electricity consumption and multiple factors affecting the distributed power generation capacity includes: Obtaining the identification of the target station area; According to the identification of the target area, the identification of each collection terminal is obtained, wherein the collection terminal is a terminal for collecting factors affecting the power consumption of the target area and a terminal for collecting factors affecting the power generation capacity of the distributed power source; According to the identifier of each of the collection terminals, respectively obtain the collection data from each of the collection terminals; Classifying the plurality of collected data, and respectively obtaining the plurality of factors affecting the power consumption of the target area and the plurality of factors affecting the power generation capacity of the distributed power source; in, The step of determining the power generation capacity of the distributed power source within the predetermined time period according to the multiple factors affecting the power generation capacity of the distributed power source includes: Acquire multiple second historical data sets that affect the power generation capacity of the distributed power source, wherein the second historical data sets include multiple factors that affect the power generation capacity of the distributed power source in a corresponding historical period, and each of the second historical data sets corresponds to a power generation capacity in the time period; Generate a second data set according to the multiple factors affecting the power generation capacity of the distributed power generation; calculating a distance between the second data set and the plurality of second historical data sets; Selecting the second historical data set that is closest to the second data set as the target data set; The power generation capacity of the target data set corresponding to the time period is used as the power generation capacity of the distributed power source in the predetermined time period.
2. The distributed power grid-connected operation control method according to claim 1, It is characterized in that The step of determining the power load in a predetermined time period according to the multiple factors affecting the power consumption of the target area includes: Acquire a neural network, wherein the neural network is a neural network that has undergone prediction training; Sorting the multiple factors affecting the power consumption of the target substation in a predetermined order to form a first data set; The first data set is input into the neural network to obtain the power load in a predetermined time period.
3. The distributed power grid-connected operation control method according to claim 2, It is characterized in that The obtaining of the neural network comprises: Acquire multiple first historical data sets of the target area, wherein the first historical data sets include multiple factors affecting the power consumption of the target area in the corresponding historical period, the multiple factors affecting the power consumption of the target area in each of the first historical data sets are arranged in the same order, and each of the first historical data sets is provided with a label of the power load in the time period; determining a loss function of the neural network; According to the loss function, a plurality of the first historical data sets of the target station area are input into the neural network to train the neural network until the loss function value is less than a threshold value.
4. The distributed power grid-connected operation control method according to claim 1, It is characterized in that The determining, according to the power load and the power generation capacity, the grid-connected capacity of the distributed power source, the transmission capacity of the upper transmission line, and the power consumption behavior of multiple users includes: Calculating the difference between the power generation capacity and the power load as the remaining capacity; If the remaining capacity is greater than a first threshold, enabling the energy storage electrical devices of the multiple users according to the remaining capacity; If the remaining capacity is greater than a second threshold, reducing the grid-connected capacity of the distributed power source; If the remaining capacity is less than a third threshold, increasing the grid-connected capacity of the distributed power source; If the remaining capacity is less than a fourth threshold, the transmission capacity of the upper transmission line is increased.
5. The distributed power grid-connected operation control method according to any one of claims 1 to 4, It is characterized in that Based on the Internet of Things system, the multiple factors affecting the electricity consumption of the target substation, the multiple factors affecting the power generation capacity of the distributed power sources, and the electricity consumption behaviors of the multiple users are obtained, wherein the Internet of Things system adopts 5G technology to communicate with each collection terminal and the power consumption terminal, the collection terminal is used to collect the factors affecting the electricity consumption of the target substation and the factors affecting the power generation capacity of the distributed power sources, and the power consumption terminal is an energy storage type power consumption device.
6. A load forecasting and grid-connected control device, It is characterized in that For implementing the distributed power grid-connected operation control method according to claim 1, the load forecasting and grid-connected control device comprises: An influencing factor acquisition module, used to acquire multiple factors affecting the power consumption of the target area and multiple factors affecting the power generation capacity of the distributed power source, wherein the distributed power source is a distributed power source connected to the grid for power generation in the area; A power load prediction module, used to determine the power load in a predetermined time period according to the multiple factors affecting the power consumption of the target substation; A power generation capacity prediction module, used to determine the power generation capacity of the distributed power source within the predetermined time period according to the multiple factors affecting the power generation capacity of the distributed power source; and A grid-connected control module is used to determine the grid-connected capacity of the distributed power source, the transmission capacity of the upper-level transmission line, and the electricity consumption behavior of multiple users according to the power load and the power generation capacity, wherein the upper-level transmission line is a transmission line that supplies power to the target substation, and the user is the electricity user of the target substation.
7. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.
8. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.
Citation Information
Patent Citations
Power grid load prediction method and device and computing equipment
CN109800929A
Rural power grid distributed photovoltaic consumption method considering energy storage and DR and terminal equipment
CN110429653A
Surplus power management system
JP2002345149A
