Power resource scheduling method and device based on minimum power supply cost, and storage medium

Abstract

The invention discloses a power resource scheduling method and device based on minimum power supply cost and a storage medium. The method comprises the following steps: determining the probability of each power supply equipment in each power supply power interval of a target time period through a power prediction model, and generating power supply power probability distribution of the power supply equipment corresponding to the target time period according to the probability; determining a constraint condition corresponding to the power supply equipment according to the power supply power probability distribution; constructing a power supply cost calculation model according to the power supply cost corresponding to the power supply equipment; and solving the power supply cost calculation model according to the constraint condition through a particle swarm algorithm based on the updated inertia weight, determining the minimum power supply cost, and scheduling the power resources according to the minimum power supply cost.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a method, device and storage medium for scheduling electric power resources based on minimum power supply cost. Background Art

[0002] As a large number of renewable energy power generation facilities are connected to the power grid, their inherent randomness and unpredictability have brought increasing pressure on the operation of the power system. At present, China's power system mainly relies on the peak-shaving capacity of thermal power stations to maintain the overall regulation performance. However, with the access of a high proportion of renewable energy, the regulation task of the power system has become more complex and arduous; traditional energy not only needs to cope with conventional load changes, but also needs to compensate for the fluctuations in renewable energy output. Once the output of renewable energy exceeds the regulation capacity of the system, it may lead to the waste of wind or solar energy, the so-called wind or solar abandonment phenomenon, which is undoubtedly a huge waste of resources.

[0003] In addition to the power resources of new energy equipment, the power resources of the power system also include the power resources of thermal power units, the power resources of energy storage equipment, and the power resources of the national power grid. The existence of these resources is to ensure the full utilization of new energy and improve the adaptability and stability of the power grid. However, when configuring these power resources, it is usually still based on empirical judgment or simulation model-based methods. However, the accuracy and reliability of these traditional configuration methods are relatively low, and lack sufficient scientific basis, so it is difficult to meet the needs of the development of today's power system.

[0004] With respect to the technical problem that the power resource scheduling scheme in the above-mentioned prior art cannot accurately schedule power resources, no effective solution has been proposed so far. Summary of the invention

[0005] The embodiments of the present application provide a method, device and storage medium for scheduling electric power resources based on minimum power supply cost, so as to at least solve the technical problem that the electric power resource scheduling scheme existing in the prior art cannot accurately schedule electric power resources.

[0006] According to one aspect of an embodiment of the present application, a method for scheduling power resources based on minimum power supply cost is provided, including: determining the probability of each power supply power interval of each power supply device in a target time period through a power prediction model, and generating a power supply power probability distribution of the power supply device corresponding to the target time period according to the probability; determining the constraint conditions corresponding to the power supply device according to the power supply power probability distribution; constructing a power supply cost calculation model according to the power supply cost corresponding to the power supply device; and solving the power supply cost calculation model according to the constraint conditions through a particle swarm algorithm based on an updated inertia weight, determining the minimum power supply cost, and scheduling power resources according to the minimum power supply cost, wherein the expression of the particle swarm algorithm is:

[0007] V i k+1 =ω k V i k +c1r1(P i k -X i k )+c2r2(G k -X i k ) (1)

[0008] X i k+1 =X i k +V i k+1 (2)

[0009] Where k represents the number of iterations; i represents the particle number; V i k , X i k are the velocity and position of particle i before updating; V i k+1 , X i k+1 are the updated speed and position of particle i respectively; P i k , G k are the individual optimal position of particle i and the global optimal position of the group respectively; ω k It represents the inertia weight after being updated by the preset PID module; c1 and c2 represent learning factors; r1 and r2 represent random numbers between 0 and 1.

[0010] According to another aspect of the embodiment of the present application, a power resource scheduling device based on minimum power supply cost is also provided, including: a determination generation module, which is used to determine the probability of each power supply power interval of each power supply device in the target time period through the power prediction model, and generate the power supply power probability distribution of the power supply device corresponding to the target time period according to the probability; a condition determination module, which is used to determine the constraint conditions corresponding to the power supply device according to the power supply power probability distribution; a model construction module, which is used to construct a power supply cost calculation model according to the power supply cost corresponding to the power supply device; and a cost determination module, which is used to solve the power supply cost calculation model according to the constraint conditions through a particle swarm algorithm based on an updated inertia weight, determine the minimum power supply cost, and schedule power resources according to the minimum power supply cost, wherein the expression of the particle swarm algorithm is:

[0011] V i k+1 =ω k V i k +c1r1(P i k -X i k )+c2r2(G k -X i k ) (1)

[0012] X i k+1 =X i k +V i k+1 (2)

[0013] Where k represents the number of iterations; i represents the particle number; V i k , X i k are the velocity and position of particle i before updating; V i k+1 , X i k+1 are the updated speed and position of particle i respectively; P i k , G k are the individual optimal position of particle i and the global optimal position of the group respectively; ω k It represents the inertia weight after being updated by the preset PID module; c1 and c2 represent learning factors; r1 and r2 represent random numbers between 0 and 1.

[0014] According to another aspect of an embodiment of the present application, a power resource scheduling device based on minimum power supply cost is also provided, including: a processor; and a memory connected to the processor, for providing the processor with instructions for processing the following processing steps: determining the probability of each power supply power interval of each power supply device in a target time period through a power prediction model, and generating a power supply power probability distribution of the power supply device corresponding to the target time period according to the probability; determining the constraint conditions corresponding to the power supply device according to the power supply power probability distribution; constructing a power supply cost calculation model according to the power supply cost corresponding to the power supply device; and solving the power supply cost calculation model according to the constraint conditions through a particle swarm algorithm based on an updated inertia weight, determining the minimum power supply cost, and scheduling power resources according to the minimum power supply cost, wherein the expression of the particle swarm algorithm is:

[0015] V i k+1 =ω k V i k +c1r1(P i k -X i k )+c2r2(G k -X i k ) (1)

[0016] X i k+1 =X i k +V i k+1 (2)

[0017] Where k represents the number of iterations; i represents the particle number; V i k , X i k are the velocity and position of particle i before updating; V i k+1 , X i k+1 are the updated speed and position of particle i respectively; P i k , G k are the individual optimal position of particle i and the global optimal position of the group respectively; ω k It represents the inertia weight after being updated by the preset PID module; c1 and c2 represent learning factors; r1 and r2 represent random numbers between 0 and 1.

[0018] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0019] According to another aspect of the embodiments of the present application, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0020] In an embodiment of the present application, the power dispatching platform uses the maximum power supply of the new energy equipment as the final power supply of the new energy equipment, so that all the power supply generated by the new energy equipment can be used, avoiding the energy waste caused by abandoning wind and light. And the technical solution determines the dispatching strategy of the power supply equipment according to the minimum power supply cost, so that sufficient power supply can be provided with minimum loss, thereby improving the utilization rate of power resources. And the technical solution obtains the optimal dispatching scheme for each power supply equipment based on the minimum power supply cost through the particle swarm algorithm, so that each power supply equipment can be flexibly dispatched. Compared with the traditional configuration method, the technical solution improves the accuracy and reliability of power resource configuration according to the particle swarm algorithm based on artificial intelligence. And then solves the technical problem that the power resource dispatching scheme existing in the prior art cannot accurately dispatch power resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1 is a hardware structure block diagram of a computing device for implementing the method according to Embodiment 1 of the present application;

[0023] Figure 2 is a schematic diagram of the power resource dispatching system according to Embodiment 1 of the present application;

[0024] Figure 3 It is a flowchart of the method for scheduling electric power resources based on minimum power supply cost according to the first aspect of Embodiment 1 of the present application;

[0025] Figure 4A is a schematic diagram of probability distribution of new energy equipment according to Example 1 of the present application;

[0026] Figure 4B is a schematic diagram of a power prediction model for new energy equipment according to Example 1 of the present application;

[0027] Figure 5 is another probability distribution diagram of the new energy device according to Example 1 of the present application;

[0028] Figure 6 It is a sequential flow chart of the method for scheduling electric power resources based on minimum power supply cost according to the first aspect of Embodiment 1 of the present application;

[0029] Figure 7 is a schematic diagram of a power resource scheduling device based on minimum power supply cost according to Embodiment 2 of the present application; and

[0030] Figure 8 It is a schematic diagram of the power resource scheduling device based on minimum power supply cost described in Example 3 of the present application. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] Example 1

[0034] According to this embodiment, a method embodiment of a power resource scheduling method based on minimum power supply cost is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] The method embodiment provided in this embodiment can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Figure 1FIG. 1 shows a hardware structure block diagram of a computing device for implementing a power resource scheduling method based on minimum power supply cost. Figure 1 As shown, the computing device may include one or more processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, and a transmission device for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0036] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computing device. As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0037] The memory can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the power resource scheduling method based on the minimum power supply cost in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the power resource scheduling method based on the minimum power supply cost of the above-mentioned application is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computing device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0038] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computing device. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0039] The display may be, for example, a touch screen liquid crystal display (LCD) that may enable a user to interact with a user interface of the computing device.

[0040] It should be noted that, in some optional embodiments, the above Figure 1 The computing device shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computing devices described above.

[0041] Figure 2 Schematic diagram of the power resource dispatching system according to this embodiment. Figure 2 As shown, the system includes: a power dispatching platform 10.

[0042] refer to Figure 2 As shown, the technical solution can be used to implement the dispatching of a regional power grid, specifically, the regional power grid can be, for example, a power grid in a city area. The regional power grid is powered by power generation equipment of different energy types, such as photovoltaic, wind power, energy storage system and thermal power units.

[0043] The power dispatching platform 10 can communicate with photovoltaic equipment, wind power equipment, energy storage system, thermal power unit and power load through the Internet of Things, so as to obtain the power supply power of photovoltaic equipment, wind power equipment, energy storage system and thermal power unit, as well as the power consumption of power load. The power load can include residential power, industrial power, commercial power, agricultural power and transportation power, etc.

[0044] The power dispatching platform 10 can also achieve a balance between the power consumption and power supply of the power load of the regional power grid through power dispatching. Among them, compared with photovoltaic equipment and wind power equipment, thermal power units are relatively stable and controllable. In addition, the energy storage system can be charged during flat and valley periods and discharged during peak and peak periods, thereby realizing power dispatching in a "peak shaving and valley filling" manner. In addition, when the power supply of the power supply equipment of the regional power grid cannot meet the power load, electricity can be purchased from the national power grid. The electricity price of the national power grid also varies according to the peak and valley, with the valley price being lower and the peak price being higher.

[0045] Therefore, the power dispatching platform can balance power supply and power load by dispatching thermal power units and energy storage systems, as well as purchasing electricity from the national power grid.

[0046] It should be noted that the power dispatching platform 10 in the system can be applicable to the hardware structure described above.

[0047] Under the above operating environment, according to the first aspect of this embodiment, a method for scheduling power resources based on minimum power supply cost is provided. The method comprises: Figure 2 The power dispatching platform 10 shown in is implemented. Figure 3 A schematic diagram showing the process of the method is shown in FIG. Figure 3 As shown, the method includes:

[0048] S302: Determine the probability of each power supply power interval of each power supply device in the target time period through the power prediction model, and generate the power supply power probability distribution of the power supply device corresponding to the target time period according to the probability;

[0049] S304: Determine the constraint conditions corresponding to the power supply equipment according to the probability distribution;

[0050] S306: constructing a power supply cost calculation model according to the power supply cost corresponding to the power supply equipment; and

[0051] S308: Solve the power supply cost calculation model according to the constraint conditions through the particle swarm algorithm based on the updated inertia weight, determine the minimum power supply cost, and schedule the power resources according to the minimum power supply cost, wherein the expression of the particle swarm algorithm is:

[0052] V i k+1 =ω k V i k +c1r1(P i k -X i k )+c2r2(G i k -X ik ) (1)

[0053] X i k+1 =X i k +V i k+1 (2)

[0054] Where k represents the number of iterations; i represents the particle number; V i k , X i k are the velocity and position of particle i before updating; V i k+1 , X i k+1 are the updated speed and position of particle i respectively; P i k , X i k are the individual optimal position of particle i and the global optimal position of the group respectively; ω k It represents the inertia weight after being updated by the preset PID module; c1 and c2 represent learning factors; r1 and r2 represent random numbers between 0 and 1.

[0055] Specifically, the power dispatching platform 10 divides a day into multiple time periods (i.e., dispatching time periods), for example, each hour can be used as a dispatching time period, so that the target date can be divided into 24 dispatching time periods. Then, the power dispatching platform 10 takes each dispatching time period as a target time period in turn, thereby determining the power supply power of each power supply device in the target time period in turn. The power supply equipment includes new energy equipment, thermal power units, energy storage equipment, and national power grids.

[0056] More specifically, new energy equipment generates electric power resources based on wind power and sunlight, including photovoltaic equipment and wind power equipment. The power dispatching platform 10 collects weather forecast data for the target time period. The weather forecast data includes sunshine intensity data, cloud cover data, temperature data, wind speed, temperature, and air pressure data. The power dispatching platform 10 then inputs the weather forecast data for the target time period into the preset power prediction model for new energy equipment, so that the power prediction model outputs the probability pa1~pa9 of the power resources generated by the new energy equipment in each power supply power interval during the target time period based on the weather forecast data. And each power supply power interval includes: 1000KWH~900KWH, 900KWH~800KWH,...., 200KWH~100KWH. The power dispatching platform 10 then generates the power supply probability distribution of the new energy equipment based on the probability of each power supply power interval corresponding to the target time period. One scheduling period corresponds to the power supply probability distribution of a new energy device, Figure 4A The power supply probability distribution of the target period is shown.

[0057] More specifically, Figure 4B The schematic diagram of the power prediction model of new energy equipment is shown. The power prediction model of new energy equipment includes an input layer, a hidden layer and an output layer, wherein the activation function of the output layer is a softmax function. Figure 4B As shown, the power dispatching platform 10 generates a corresponding feature vector A[a1, a2, ..., a L ] T Then the power dispatching platform 10 converts the feature vector A[a1,a2,...,a L ] T The input layer is input to the hidden layer. After the hidden layer processes the feature vector, the output layer generates the probabilities pa1~pa9 of each power supply interval through the softmax activation function according to the feature information obtained after the hidden layer processing.

[0058] Furthermore, for the thermal power units, the power dispatching platform 10 collects the power supply history data of the thermal power units in the same dispatching period as the target period within the sample period, and then inputs the power supply history data into the power prediction model of the thermal power units, and predicts the power supply of the thermal power units in the target period through the power prediction model, thereby outputting the probability pb1~pb9 of the power resources that can be provided by the thermal power units in the target period in each power supply interval. Among them, each power supply interval includes: 1000KWH~900KWH, 900KWH~800KWH,...., 200KWH~100KWH. Afterwards, the power dispatching platform 10 generates the power supply probability distribution of the thermal power units with the probabilities of each power supply interval corresponding to the target period (not shown in the figure). More specifically, the power prediction model of the thermal power unit includes an input layer, a hidden layer and an output layer, wherein the activation function of the output layer is a softmax function. The power dispatching platform 10 generates a power supply probability distribution of the thermal power units according to the sample period t1~t m The power supply history data generates the corresponding feature vector B[b1,b2,...,b m ] T . Then the power dispatching platform 10 converts the feature vector B[b1,b2,...,b m ] T The input layer is input to the hidden layer. After the hidden layer processes the feature vector, the output layer generates the probabilities pb1~pb9 of each power supply interval through the softmax activation function according to the feature information obtained after the hidden layer processing.

[0059] Furthermore, for energy storage devices, the power dispatching platform 10 collects the power supply history data of the energy storage devices in the same scheduling period as the target period within the sample period, and then inputs the power supply history data into the power prediction model of the energy storage devices, and predicts the power supply of the energy storage devices in the target period through the power prediction model, thereby outputting the probability pc1~pc9 of the power resources that the energy storage devices can provide in the target period in each power supply power interval. Wherein each power supply power interval includes: 1000KWH~900KWH, 900KWH~800KWH,...., 200KWH~100KWH. Afterwards, the power dispatching platform 10 generates the power supply power probability distribution of the energy storage device with the probability of each power supply power interval corresponding to the target period (not shown in the figure). More specifically, the power prediction model of the energy storage device includes an input layer, a hidden layer and an output layer, wherein the activation function of the output layer is a softmax function. The power dispatching platform 10 generates the power supply probability distribution of the energy storage device according to the sample period t1~t m The power supply history data generates the corresponding feature vector C[c1,c2,...,c m ] T . Then the power dispatching platform 10 converts the feature vector C[c1,c2,...,c m ] T The input layer is input to the hidden layer. After the hidden layer processes the feature vector, the output layer generates the probabilities pc1~pc9 of each power supply interval based on the feature information obtained after the hidden layer processing through the softmax activation function.

[0060] Furthermore, for the national power grid, the power dispatching platform 10 collects the power supply historical data of the national power grid in the same dispatching period as the target period within the sample period, and then inputs the power supply historical data into the power forecasting model of the national power grid, and predicts the power supply of the energy storage equipment in the target period through the power forecasting model, thereby outputting the probability pd1~pd9 of the power resources provided by the national power grid in each power supply power interval during the target period. Each power supply power interval includes: 1000KWH~900KWH, 900KWH~800KWH,...., 200KWH~100KWH. Afterwards, the power dispatching platform 10 generates the power supply probability distribution of the national power grid (not shown in the figure) with the probabilities of each power supply power interval corresponding to the target period. More specifically, the power forecasting model of the national power grid includes an input layer, a hidden layer and an output layer, wherein the activation function of the output layer is a softmax function. The power dispatching platform 10 generates the power supply probability distribution of the national power grid according to the sample period t1~t m The power supply history data generates the corresponding feature vector D[d1,d2,...,d m ] TThen the power dispatching platform 10 converts the feature vector D[d1,d2,...,d m ] T The input layer is input to the hidden layer. After the hidden layer processes the feature vector, the output layer generates the probabilities pd1~pd9 of each power supply interval through the softmax activation function according to the feature information obtained after the hidden layer processing.

[0061] Furthermore, in addition to the power supply equipment, the power dispatching platform 10 will also determine the power consumption probability distribution of the power load. Thus, the power dispatching platform 10 collects the power consumption history data of the power load in the same dispatching period as the target period within the sample period, and then inputs the power consumption history data into the power prediction model of the power load, and predicts the power consumption in the target period through the power prediction model, thereby outputting the probability of the power load in each power consumption interval in the target period. Among them, each power consumption interval includes: 1000KWH~900KWH, 900KWH~800KWH, ...., 200KWH~100KWH. After that, the power dispatching platform 10 generates the power consumption probability distribution of the power load (not shown in the figure) with the probability of each power consumption interval corresponding to the target period.

[0062] More specifically, the power load prediction model includes an input layer, a hidden layer, and an output layer, wherein the activation function of the output layer is a softmax function. m Use the historical data of electric power to generate the corresponding feature vector SY[y1,y2,...,y m ] T Then the power dispatching platform 10 converts the feature vector SY[y1,y2,...,y m ] T The input layer is input to the hidden layer. After the hidden layer processes the feature vector, the output layer generates the probabilities py1~py9 of each power consumption interval through the softmax activation function according to the feature information obtained after the hidden layer processing.

[0063] Furthermore, the power dispatching platform 10 determines the maximum value Xa of the power supply Xa that the new energy equipment can provide according to the power supply power probability distribution of the new energy equipment. max and the minimum value Xa min In order to avoid the phenomenon of wind and solar power abandonment, the maximum power supply power Xa is used. max Determine the constraints of new energy equipment, that is, Xa = Xa max .

[0064] Furthermore, the power dispatching platform 10 determines the maximum value Xb of the power supply Xb that the thermal power unit can provide according to the power supply probability distribution of the thermal power unit.max and the minimum value Xb min , then according to the maximum power supply Xb max And the minimum power supply Xb min Determine the constraints of the thermal power unit, namely Xb max ≥Xb≥Xb min .

[0065] Furthermore, the power dispatching platform 10 determines the maximum value Xc of the power supply Xc that the energy storage device can provide according to the power supply power probability distribution of the energy storage device. max and the minimum value Xc min , then according to the maximum power supply Xc max And the minimum power supply Xc min Determine the constraints Xc of the energy storage device max ≥Xc≥Xc min .

[0066] Furthermore, the power dispatching platform 10 determines the maximum value Xd of the power supply Xd that can be provided by the national power grid according to the power supply power probability distribution of the national power grid. max And the minimum value Xd min , then according to the maximum power supply power Xd max And the minimum power supply Xd min Determine the constraints Xd of the national power grid max ≥Xd≥Xd min .

[0067] Furthermore, the power dispatching platform 10 determines the constraint between the power consumption and the power supply according to the power supply of the new energy equipment, thermal power units, energy storage equipment and the national power grid and the power consumption Y of the power load. The constraint is: the sum of the power supply of the new energy equipment, thermal power units, energy storage equipment and the national power grid is less than or equal to the maximum value Y of the power consumption of the power load. max That is, Xa+Xb+Xc+Xd≥Y max .

[0068] Furthermore, the power dispatching platform 10 calculates the power supply cost of the target period according to the power supply power of the new energy equipment, thermal power units, energy storage equipment and the national power grid in the target period, and constructs a power supply cost calculation model according to the power supply cost.

[0069] Furthermore, the power dispatching platform 10 solves the power supply cost calculation model through the particle swarm algorithm, and determines the minimum power supply cost under the premise of meeting the constraint conditions. The power dispatching platform 10 is pre-set with a PID module, so that the inertia weight in the particle swarm algorithm is updated through the PID module in each iteration. Thus, the particle swarm algorithm is as follows:

[0070] First, the power dispatching platform 10 initializes the initial positions of particles 1 to n generated by the particle swarm algorithm. Initial Speed Initial individual optimal position Initial global best position Initial inertia weight ω0, learning factors c1, c2, random numbers r1, r2. The initial position All meet the constraints.

[0071] And among them

[0072]

[0073] Afterwards, the power dispatching platform 10 updates the individual optimal position of particle i and the global optimal position of the group according to the iterative formula of the particle swarm algorithm, where the iterative formula of the particle swarm algorithm is:

[0074] V i k+1 =ω k V i k +c1r1(P i k -X i k )+c2r2(G k -X i k ) (1)

[0075] X i k+1 =X i k +V i k+1 (2)

[0076] Where k represents the number of iterations; i represents the particle number, i = 1 to n; V i k , X i k are the velocity and position of particle i before updating; V i k+1 , X i k+1 are the updated speed and position of particle i respectively; P i k , G k are the individual optimal position of particle i and the global optimal position of the group respectively; ω kIt represents the inertia weight after being updated by the preset PID module; c1 and c2 represent learning factors; r1 and r2 represent random numbers between 0 and 1.

[0077] For example, in the first iteration, the iteration formula of the particle swarm algorithm is:

[0078] V i 1 =ω0V i 0 +c1r1(P i 0 -X i 0 )+c2r2(G0-X i 0 ) (3)

[0079] X i 1 =X i 0 +V i 1 (4)

[0080] The power dispatching platform 10 is pre-set with a PID module, so that the power dispatching platform 10 updates the inertia weight ω0 through the PID module to obtain ω1 for the next iteration, and generates an updated individual optimal position P i 1 and the global optimal position G1. Then the power dispatching platform 10 substitutes the global optimal position G1 into the power supply cost calculation model to determine whether the power supply cost generated by the power supply cost calculation model is the minimum power supply cost under the premise of meeting the constraint conditions. If the power supply cost is not the minimum power supply cost under the premise of meeting the constraint conditions, the iteration continues until the minimum power supply cost under the premise of meeting the constraint conditions is determined.

[0081] Furthermore, after obtaining the minimum power supply cost, the power dispatching platform 10 obtains the global optimal position corresponding to the minimum power supply cost, and performs corresponding dispatch of the new energy equipment, thermal power units, energy storage equipment and the national power grid according to the power supply power of the new energy equipment, thermal power units, energy storage equipment and the national power grid corresponding to the global optimal position.

[0082] As described in the background technology, with the large-scale access of new energy power generation facilities to the power grid, their inherent randomness and unpredictability have brought increasing pressure on the operation of the power system. At present, China's power system mainly relies on the peak-shaving capacity of thermal power stations to maintain the overall regulation performance. However, with the access of a high proportion of new energy, the regulation task of the power system has become more complex and arduous; traditional energy not only needs to cope with conventional load changes, but also needs to compensate for the fluctuations in the output of new energy. Once the output of new energy exceeds the regulation capacity of the system, it may lead to the waste of wind or solar energy, that is, the so-called abandonment of wind or light, which is undoubtedly a great waste of resources. In addition to the power resources of new energy equipment, the power resources of the power system also include the power resources of thermal power units, the power resources of energy storage equipment, and the power resources of the national power grid. The existence of these resources is to ensure the full utilization of new energy and improve the adaptability and stability of the power grid. However, when configuring these power resources, it is usually still based on empirical judgment or simulation model-based methods. However, the accuracy and reliability of these traditional configuration methods are relatively low, and lack sufficient scientific basis, so it is difficult to meet the needs of the development of today's power system.

[0083] In view of the technical problems described above, through the technical solutions of the embodiments of the present application, the power dispatching platform uses the maximum power supply of the new energy equipment as the final power supply of the new energy equipment, so that all the power supply generated by the new energy equipment can be used, avoiding the energy waste caused by abandoning wind and light. And this technical solution determines the dispatching strategy of the power supply equipment according to the minimum power supply cost, so that sufficient power supply can be provided with minimum loss, thereby improving the utilization rate of power resources. And this technical solution obtains the optimal dispatching scheme for each power supply equipment based on the minimum power supply cost through the particle swarm algorithm, so that each power supply equipment can be flexibly dispatched. Compared with the traditional configuration method, this technical solution improves the accuracy and reliability of power resource configuration according to the particle swarm algorithm based on artificial intelligence. And then solves the technical problem that the power resource dispatching scheme existing in the prior art cannot accurately dispatch power resources.

[0084] Optionally, the operation of determining the constraint conditions corresponding to the power supply equipment according to the power supply probability distribution includes: determining a confidence interval of the power supply probability distribution according to a preset probability threshold; and determining the constraint conditions corresponding to the power supply equipment according to the confidence interval.

[0085] Specifically, the power dispatching platform 10 obtains the power supply probability distribution of the new energy equipment, and determines the confidence interval of the power supply probability distribution according to a preset probability threshold. Figure 5 As shown, for example, the probability threshold is 0.2, so the power dispatching platform 10 determines the confidence interval of the power supply probability distribution as UL according to the probability threshold. a~UR a . After that, the power dispatching platform 10 will UR a As the maximum power supply Xa max , UL a As the minimum power supply value Xa min In order to avoid wind and solar power abandonment, the maximum power supply power Xa is used. max Determine the constraints of new energy equipment, that is, Xa = Xa max .

[0086] Furthermore, the power dispatching platform 10 obtains the power supply probability distribution of the thermal power unit, and determines the confidence interval UL of the power supply probability distribution according to a preset probability threshold. b ~UR b . After that, the power dispatching platform 10 will UR b As the maximum power supply Xb max , UL b As the minimum power supply value Xb min Then the power dispatching platform 10 calculates the maximum power supply power Xb max And the minimum power supply Xb min Determine the constraints of the thermal power unit, namely Xb max ≥Xb≥Xb min .

[0087] Furthermore, the power dispatching platform 10 obtains the power supply probability distribution of the energy storage device, and determines the confidence interval UL of the power supply probability distribution according to a preset probability threshold. c ~UR c . After that, the power dispatching platform 10 will UR c As the maximum power supply Xc max , UL c As the minimum power supply Xc min Then the power dispatching platform 10 calculates the maximum power supply power Xc max And the minimum power supply Xc min Determine the constraints of the energy storage device, namely Xc max ≥Xc≥Xc min .

[0088] Furthermore, the power dispatching platform 10 obtains the power supply probability distribution of the national power grid, and determines the confidence interval UL of the power supply probability distribution according to a preset probability threshold. d ~UR d . After that, the power dispatching platform 10 will UR d As the maximum power supply Xd max , UL d As the minimum power supply value Xdmin Then the power dispatching platform 10 calculates the maximum power supply power Xd max And the minimum power supply Xd min Determine the constraints of the national power grid, namely Xd max ≥Xd≥Xd min .

[0089] Furthermore, the power dispatching platform 10 obtains the power consumption probability distribution of the power load, and determines the confidence interval UL of the power consumption probability distribution according to a preset probability threshold. Y ~UR Y . After that, the power dispatching platform 10 will UR Y As the maximum power consumption Y max , UL Y As the minimum power consumption Y min .

[0090] Furthermore, the power dispatching platform 10 determines the constraint between the power consumption and the power supply according to the power supply power Xa of the new energy equipment, the power supply power Xb of the thermal power unit, the power supply power Xc of the energy storage equipment, the power supply power Xd of the national power grid and the power consumption Y of the power load, that is, Xa+Xb+Xc+Xd≥Y max .

[0091] Therefore, the technical solution provides a reasonable range for the power supply power by determining a confidence interval for the power supply power probability distribution, thereby improving the accuracy of the constraint conditions corresponding to the power supply power.

[0092] Optionally, the operation of constructing a power supply cost calculation model based on the power supply cost corresponding to the power supply equipment includes: calculating the power supply cost corresponding to the power supply equipment based on the power supply power of the power supply equipment, wherein the power supply equipment includes new energy equipment, thermal power units, energy storage equipment and a national power grid; and constructing a power supply cost calculation model based on the power supply cost, wherein the power supply cost calculation model is: FX=Fa+Fb+Fc+Fd, wherein FX represents the power supply cost calculation model, Fa represents the power supply cost of the new energy equipment, Fb represents the power supply cost of the thermal power unit, Fc represents the power supply cost of the energy storage equipment, and Fd represents the power supply cost of the national power grid.

[0093] Specifically, the power dispatching platform 10 calculates the power supply cost Fa of the new energy equipment based on the preset operating cost coefficient θ1 of the new energy equipment and the power supply power Xa of the new energy equipment: Fa=θ1*Xa. Then the power dispatching platform 10 calculates the power supply cost Fb of the thermal power unit based on the preset operating cost coefficient θ2 of the thermal power unit and the power supply power Xb of the thermal power unit: Fb=θ2*Xb. Then the power dispatching platform 10 calculates the power supply cost Fc of the energy storage equipment based on the preset operating cost coefficient θ3 of the energy storage equipment and the power supply power Xc of the energy storage equipment: Fc=θ3*Xc. Then the power dispatching platform 10 calculates the power supply cost Fd of the national power grid based on the electricity price Cd of the target period and the power supply power Xd of the national power grid: Fd=Cd*Xd.

[0094] Furthermore, the power dispatching platform 10 constructs a power supply cost calculation model based on the power supply cost Fa of new energy equipment, the power supply cost Fb of thermal power units, the power supply cost Fc of energy storage equipment and the power supply cost Fd of the national power grid, wherein the power supply cost calculation model is: FX=Fa+Fb+Fc+Fd.

[0095] Therefore, this technical solution constructs a power supply cost calculation model according to the power supply cost of the power supply equipment that needs to be scheduled, and then comprehensively judges the power supply power that each power supply equipment needs to provide based on the power supply cost calculation model, so that the distribution of power supply of each power supply equipment is more reasonable.

[0096] Optionally, the operation of solving the power supply cost calculation model according to constraints by using a particle swarm algorithm based on the updated inertia weight to determine the minimum power supply cost includes: calculating the average value of the distance between the first position of each particle and the first global optimal position according to the first position of each particle and the first global optimal position; calculating the average value using a PID module to determine the updated inertia weight; and solving the power supply cost calculation model according to constraints using the particle swarm algorithm with the updated inertia weight to determine the minimum power supply cost.

[0097] Specifically, the power dispatching platform 10 needs to update the inertia weight ω k When , the position X of each particle i (i = 1 ~ n) in the previous iteration will be obtained i k-1 (i.e., the first position) and the current global best position G k-1 (i.e., the first global optimal position), and then calculate the first position X of each particle i i k-1 With the first global optimal position G k-1 The sum of the distances between them, and then calculate the average value of the sum of the distances ave k :

[0098]

[0099] Furthermore, the power dispatching platform 10 uses the PID module to calculate the average value ave k Calculate and determine the updated inertia weight ω k The power dispatching platform 10 then uses the updated inertia weight ω k The particle swarm algorithm is used to solve the power supply cost calculation model according to the constraints and determine the minimum power supply cost.

[0100] Therefore, the technical solution accurately determines the inertia weight by calculating the update trend of each particle indicated by the average value of the sum of the distances between the position of each particle and the global optimal position.

[0101] Optionally, the operation of calculating the average value by using the PID module to determine the updated inertia weight includes: processing the average value according to the proportional weight, integral weight, and differential weight preset in the PID module to determine the updated inertia weight.

[0102] Specifically, the PID module includes a proportional unit, an integral unit and a differential unit. The power dispatching platform 10 uses the proportional value calculation formula of the proportional unit of the PID module according to the average value ave k , calculate the ratio value CP k The formula for calculating the ratio is:

[0103] CP k =ave k .

[0104] Furthermore, the power dispatching platform 10 uses the integral value calculation formula through the integral unit of the PID module according to the average value ave k , calculate the integral value CI k The integral value calculation formula is:

[0105]

[0106] where ave j Represents the average value calculated in the jth round of iterations.

[0107] Furthermore, the power dispatching platform 10 uses the differential value calculation formula through the differential unit of the PID module according to the average value ave k , calculate the differential value CD k The differential value calculation formula is:

[0108] CD k =ave k -ave k-1 .

[0109] where avek Represents the average value calculated in the k-1th round of iterations.

[0110] Furthermore, the PID module is also preset with a proportional weight WP, an integral weight WI and a differential weight WD, so that the power dispatching platform 10 is based on the proportional weight WP preset by the PID module and the corresponding proportional value CP k , integral weight WI and its corresponding integral value CI k , differential weight WD and its corresponding differential value CD k Perform weighted summation to determine the updated inertia weight ω k :

[0111] ω k =CP k *WP+CI k *WI+CD k *WD.

[0112] Therefore, this technical solution utilizes the PID module to effectively reduce overshoot and ensure the stability of calculation through comprehensive adjustment of the three parts of proportion, integration and differentiation.

[0113] Optionally, the particle swarm algorithm with updated inertia weight is used to solve the power supply cost calculation model according to the constraints to determine the operation of minimum power supply cost, including: updating the first individual optimal position of each particle and the first global optimal position of the group to determine the updated second individual optimal position and the second global optimal position; and when the second global optimal position meets the constraints, the particle swarm algorithm with updated inertia weight is used to solve the power supply cost calculation model according to the second global optimal position to determine the minimum power supply cost.

[0114] Specifically, the power dispatching platform 10 needs to calculate the individual optimal position P of the k-1th round. i k-1 (i.e., the first individual optimal position) and the global optimal position of the group G k-1 (i.e., the first global optimal position) is updated to obtain the individual optimal position P of the kth round i k (and the second individual optimal position) and the global optimal position G k (i.e., the second global optimal position), the power dispatching platform 10 will convert the individual optimal position P i k-1 Bring it into the power supply cost calculation model to calculate the individual optimal position P i k-1 The corresponding power supply cost FX(P i k-1 ). The power dispatching platform 10 also calculates the position X of each particle.i k-1 Bring it into the power supply cost calculation model to calculate the cost of the power supply at location X i k-1 The corresponding power supply cost FX(X i k-1 ).

[0115] Furthermore, the power dispatching platform 10 converts the power supply cost FX(P i k-1 ) and power supply cost FX(X i k-1 ) is compared, when FX(P i k-1 )≥FX(X i k-1 ), then the second individual's optimal position P i k =X i k-1 When FX(P i k-1 )<FX(X i k-1 ), then the second individual's optimal position P i k =P i k-1 Then the power dispatching platform 10 calculates the second individual optimal position P of each particle. i k Compare and take the smallest second individual best position as the global best position G k .

[0116] Furthermore, the power dispatching platform 10 determines the global optimal position G k Whether it meets the constraints. The constraints are: Xa=Xa min , and Xb max ≥Xb≥Xb min , and Xc max ≥Xc≥Xc min , and Xd max ≥Xd≥Xd min , and Xa+Xb+Xc+Xd≥Y max .

[0117] When the constraints are met, the power dispatching platform 10 obtains the updated inertia weight ω k , individual best position P i k and the global optimal position G k Then, the inertia weight ω k , individual best position P i kand the global optimal position G k Substituting into formula (1) and formula (2), we get position X i k+1 .

[0118] If the constraints are not met, the power dispatching platform 10 ends the iteration and sets the global optimal position G of the k-1th round to k-1 As the minimum power supply cost.

[0119] Therefore, the present technical solution uses the constraint condition as the condition for ending the iteration. Compared with the algorithm in the prior art that determines whether to end the iteration based on the number of iterations, the present technical solution is not limited by the number of iterations, can more accurately determine the minimum power supply cost, and reduces limitations.

[0120] In summary, reference Figure 6 As shown, the power dispatching platform 10 determines the minimum power supply cost and performs the following steps for the corresponding dispatching:

[0121] S601: The power dispatching platform 10 determines the probability of each power supply power interval of each power supply device in the target time period through the power prediction model, and generates the power supply power probability distribution of the power supply device corresponding to the target time period according to the probability;

[0122] S602: The power dispatching platform 10 determines a confidence interval of the power supply probability distribution according to a preset probability threshold, and determines a constraint condition corresponding to the power supply equipment according to the confidence interval;

[0123] S603: The power dispatching platform 10 calculates the power supply cost corresponding to the power supply equipment according to the power supply power of the power supply equipment, and then constructs a power supply cost calculation model according to the power supply cost;

[0124] S604: The power dispatching platform 10 calculates the average value of the distance between the first position of each particle and the first global optimal position according to the first position of each particle and the first global optimal position;

[0125] S605: The power dispatching platform 10 processes the average value according to the proportional weight, integral weight and differential weight preset by the PID module to determine the updated inertia weight;

[0126] S606: The power dispatching platform 10 updates the first individual optimal position of each particle and the first global optimal position of the group, and determines an updated second individual optimal position and a second global optimal position;

[0127] S607: When the second global optimal position meets the constraint conditions, the power dispatching platform 10 uses the particle swarm algorithm with updated inertia weight to solve the power supply cost calculation model according to the second global optimal position to determine the minimum power supply cost.

[0128] In addition, according to a second aspect of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0129] In addition, according to a third aspect of this embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0130] Therefore, according to this embodiment, the power dispatching platform uses the maximum power supply of the new energy equipment as the final power supply of the new energy equipment, so that all the power supply generated by the new energy equipment can be used, avoiding the energy waste caused by abandoning wind and light. And this technical solution determines the dispatching strategy of the power supply equipment according to the minimum power supply cost, so that sufficient power supply can be provided with minimum loss, thereby improving the utilization rate of power resources. And this technical solution obtains the optimal dispatching scheme for each power supply equipment based on the minimum power supply cost through the particle swarm algorithm, so that each power supply equipment can be flexibly dispatched. Compared with the traditional configuration method, this technical solution improves the accuracy and reliability of power resource configuration according to the particle swarm algorithm based on artificial intelligence. And then solves the technical problem that the power resource dispatching scheme existing in the prior art cannot accurately dispatch power resources.

[0131] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0132] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0133] Example 2

[0134] Figure 7 The apparatus 700 for scheduling power resources based on the minimum power supply cost according to this embodiment is shown. The apparatus 700 corresponds to the method according to the first aspect of the embodiment 1. Figure 7 As shown, the device 700 includes: a probability determination module 710, which is used to determine the probability of each power supply power interval of each power supply device in the target time period through the power prediction model, and generate the power supply power probability distribution of the power supply device corresponding to the target time period according to the probability; a condition determination module 720, which is used to determine the constraint conditions corresponding to the power supply device according to the power supply power probability distribution; a model construction module 730, which is used to construct a power supply cost calculation model according to the power supply cost corresponding to the power supply device; and a cost determination module 740, which is used to solve the power supply cost calculation model according to the constraint conditions through a particle swarm algorithm based on an updated inertia weight, determine the minimum power supply cost, and schedule power resources according to the minimum power supply cost, wherein the expression of the particle swarm algorithm is:

[0135] V i k+1 =ω k V i k +c1r1(P i k -X i k )+c2r2(G k -X i k ) (1)

[0136] X i k+1 =X i k +V i k+1 (2)

[0137] Where k represents the number of iterations; i represents the particle number; Vi k , X i k are the velocity and position of particle i before updating; V i k+1 , X i k+1 are the updated speed and position of particle i respectively; P i k , G k are the individual best position of particle i and the global best position of the group respectively; ω k It represents the inertia weight after being updated by the preset PID module; c1 and c2 represent learning factors; r1 and r2 represent random numbers between 0 and 1.

[0138] Optionally, the condition determination module 720 includes: a first determination submodule, used to determine the confidence interval of the power supply probability distribution according to a preset probability threshold; and a second determination submodule, used to determine the constraint condition corresponding to the power supply device according to the confidence interval.

[0139] Optionally, the model building module 730 includes: a first calculation submodule, used to calculate the power supply cost corresponding to the power supply equipment according to the power supply power of the power supply equipment, wherein the power supply equipment includes new energy equipment, thermal power units, energy storage equipment and a national power grid; and a model building submodule, used to construct a power supply cost calculation model according to the power supply cost, wherein the power supply cost calculation model is: FX=Fa+Fb+Fc+Fd, wherein FX represents the power supply cost calculation model, Fa represents the power supply cost of the new energy equipment, Fb represents the power supply cost of the thermal power unit, Fc represents the power supply cost of the energy storage equipment, and Fd represents the power supply cost of the national power grid.

[0140] Optionally, the cost determination module 740 includes: a second calculation submodule, used to calculate the average value of the distance between the first position of each particle and the first global optimal position based on the first position of each particle and the first global optimal position; a third determination submodule, used to calculate the average value using the PID module to determine the updated inertia weight; and a fourth determination submodule, used to solve the power supply cost calculation model according to the constraint conditions using the particle swarm algorithm with the updated inertia weight to determine the minimum power supply cost.

[0141] Optionally, the third determination submodule includes: a first determination unit, used to process the average value according to the proportional weight, integral weight and differential weight preset by the PID module to determine the updated inertia weight.

[0142] Optionally, the fourth determination submodule includes: a second determination unit, used to update the first individual optimal position of each particle and the first global optimal position of the group, and determine the updated second individual optimal position and the second global optimal position; and a third determination unit, used to solve the power supply cost calculation model according to the second global optimal position using the particle swarm algorithm with updated inertia weight to determine the minimum power supply cost when the second global optimal position meets the constraint conditions.

[0143] Therefore, according to this embodiment, the power dispatching platform uses the maximum power supply of the new energy equipment as the final power supply of the new energy equipment, so that all the power supply generated by the new energy equipment can be used, avoiding the energy waste caused by abandoning wind and light. And this technical solution determines the dispatching strategy of the power supply equipment according to the minimum power supply cost, so that sufficient power supply can be provided with minimum loss, thereby improving the utilization rate of power resources. And this technical solution obtains the optimal dispatching scheme for each power supply equipment based on the minimum power supply cost through the particle swarm algorithm, so that each power supply equipment can be flexibly dispatched. Compared with the traditional configuration method, this technical solution improves the accuracy and reliability of power resource configuration according to the particle swarm algorithm based on artificial intelligence. And then solves the technical problem that the power resource dispatching scheme existing in the prior art cannot accurately dispatch power resources.

[0144] Example 3

[0145] Figure 8 The apparatus 800 for scheduling power resources based on the minimum power supply cost according to this embodiment is shown, and the apparatus 800 corresponds to the method according to the first aspect of embodiment 1. Figure 8 As shown, the device 800 includes: a processor 810; and a memory 820, which is connected to the processor 810 and is used to provide the processor 810 with instructions for processing the following processing steps: determining the probability of each power supply interval of each power supply device in the target time period through the power prediction model, and generating the power supply probability distribution of the power supply device corresponding to the target time period according to the probability; determining the constraint conditions corresponding to the power supply device according to the power supply probability distribution; constructing a power supply cost calculation model according to the power supply cost corresponding to the power supply device; and solving the power supply cost calculation model according to the constraint conditions through a particle swarm algorithm based on an updated inertia weight, determining the minimum power supply cost, and scheduling power resources according to the minimum power supply cost, wherein the expression of the particle swarm algorithm is:

[0146] V i k+1 =ω k V i k +c1r1(P i k -Xi k )+c2r2(G k -X i k ) (1)

[0147] X i k+1 =X i k +V i k+1 (2)

[0148] Where k represents the number of iterations; i represents the particle number; V i k , X i k are the velocity and position of particle i before updating; V i k+1 , X i k+1 are the updated speed and position of particle i respectively; P i k , G k are the individual best position of particle i and the global best position of the group respectively; ω k It represents the inertia weight after being updated by the preset PID module; c1 and c2 represent learning factors; r1 and r2 represent random numbers between 0 and 1.

[0149] Optionally, the operation of determining the constraint conditions corresponding to the power supply equipment according to the power supply probability distribution includes: determining a confidence interval of the power supply probability distribution according to a preset probability threshold; and determining the constraint conditions corresponding to the power supply equipment according to the confidence interval.

[0150] Optionally, the operation of constructing a power supply cost calculation model based on the power supply cost corresponding to the power supply equipment includes: calculating the power supply cost corresponding to the power supply equipment based on the power supply power of the power supply equipment, wherein the power supply equipment includes new energy equipment, thermal power units, energy storage equipment and a national power grid; and constructing a power supply cost calculation model based on the power supply cost, wherein the power supply cost calculation model is: FX=Fa+Fb+Fc+Fd, wherein FX represents the power supply cost calculation model, Fa represents the power supply cost of the new energy equipment, Fb represents the power supply cost of the thermal power unit, Fc represents the power supply cost of the energy storage equipment, and Fd represents the power supply cost of the national power grid.

[0151] Optionally, the operation of solving the power supply cost calculation model according to constraints by using a particle swarm algorithm based on the updated inertia weight to determine the minimum power supply cost includes: calculating the average value of the distance between the first position of each particle and the first global optimal position according to the first position of each particle and the first global optimal position; calculating the average value using a PID module to determine the updated inertia weight; and solving the power supply cost calculation model according to constraints using the particle swarm algorithm with the updated inertia weight to determine the minimum power supply cost.

[0152] Optionally, the operation of calculating the average value by using the PID module to determine the updated inertia weight includes: processing the average value according to the proportional weight, integral weight and differential weight preset by the PID module to determine the updated inertia weight.

[0153] Optionally, the particle swarm algorithm with updated inertia weight is used to solve the power supply cost calculation model according to the constraints to determine the operation of minimum power supply cost, including: updating the first individual optimal position of each particle and the first global optimal position of the group to determine the updated second individual optimal position and the second global optimal position; and when the second global optimal position meets the constraints, the particle swarm algorithm with updated inertia weight is used to solve the power supply cost calculation model according to the second global optimal position to determine the minimum power supply cost.

[0154] Therefore, according to this embodiment, the power dispatching platform uses the maximum power supply of the new energy equipment as the final power supply of the new energy equipment, so that all the power supply generated by the new energy equipment can be used, avoiding the energy waste caused by abandoning wind and light. And this technical solution determines the dispatching strategy of the power supply equipment according to the minimum power supply cost, so that sufficient power supply can be provided with minimum loss, thereby improving the utilization rate of power resources. And this technical solution obtains the optimal dispatching scheme for each power supply equipment based on the minimum power supply cost through the particle swarm algorithm, so that each power supply equipment can be flexibly dispatched. Compared with the traditional configuration method, this technical solution improves the accuracy and reliability of power resource configuration according to the particle swarm algorithm based on artificial intelligence. And then solves the technical problem that the power resource dispatching scheme existing in the prior art cannot accurately dispatch power resources.

[0155] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0156] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0157] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, 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 units or modules, which can be electrical or other forms.

[0158] 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 solution of this embodiment.

[0159] 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.

[0160] If the integrated 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 technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0161] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for dispatching power resources based on minimum power supply cost, It is characterized in that include: Determine the probability of each power supply power interval of each power supply device in the target time period through the power prediction model, and generate the power supply power probability distribution of the power supply device corresponding to the target time period according to the probability; Determining a constraint condition corresponding to the power supply device according to the power supply power probability distribution; Constructing a power supply cost calculation model according to the power supply cost corresponding to the power supply equipment; and The power supply cost calculation model is solved according to the constraint conditions by a particle swarm algorithm based on the updated inertia weight, the minimum power supply cost is determined, and the power resources are scheduled according to the minimum power supply cost, wherein the expression of the particle swarm algorithm is: V i k+1 =ω k V i k +c 1 r 1 (P i k -X i k )+c 2 r 2 (G k -X i k ) (1) X i k+1 =X i k +V i k+1 (2) Where k represents the number of iterations; i represents the particle number; V i k , X i k are the velocity and position of particle i before updating; V i k+1 , X i k+1 are the updated speed and position of particle i respectively; P i k , G k are the individual best position of particle i and the global best position of the group respectively; ω k Indicates the inertia weight after updating using the preset PID module; c 1 、c 2 represents the learning factor; r 1 、r 2 Represents a random number between 0 and 1.

2. The method according to claim 1, It is characterized in that The operation of determining a constraint condition corresponding to the power supply device according to the power supply power probability distribution includes: Determining a confidence interval of the power supply probability distribution according to a preset probability threshold; and A constraint condition corresponding to the power supply device is determined according to the confidence interval.

3. The method according to claim 1, It is characterized in that The operation of constructing a power supply cost calculation model according to the power supply cost corresponding to the power supply equipment includes: Calculating the power supply cost corresponding to the power supply equipment according to the power supply power of the power supply equipment, wherein the power supply equipment includes new energy equipment, thermal power units, energy storage equipment and a national power grid; and The power supply cost calculation model is constructed according to the power supply cost, wherein the power supply cost calculation model is: FX=Fa+Fb+Fc+Fd, Wherein FX represents the power supply cost calculation model, Fa represents the power supply cost of the new energy equipment, Fb represents the power supply cost of the thermal power unit, Fc represents the power supply cost of the energy storage device, and Fd represents the power supply cost of the national power grid.

4. The method according to claim 1, It is characterized in that The operation of solving the power supply cost calculation model according to the constraint conditions by using a particle swarm algorithm based on the updated inertia weight to determine the minimum power supply cost includes: Calculating an average value of the distance between the first position of each particle and the first global optimal position according to the first position of each particle and the first global optimal position; Calculating the average value using the PID module to determine an updated inertia weight; and The power supply cost calculation model is solved according to the constraint conditions using the particle swarm algorithm of the updated inertia weight to determine the minimum power supply cost.

5. The method according to claim 4, It is characterized in that The operation of calculating the average value by using the PID module to determine the updated inertia weight includes: The average value is processed according to the proportional weight, integral weight and differential weight preset by the PID module to determine the updated inertia weight.

6. The method according to claim 4, It is characterized in that The operation of solving the power supply cost calculation model according to the constraint condition by using the particle swarm algorithm of the updated inertia weight to determine the minimum power supply cost includes: Updating the first individual best position of each particle and the first global best position of the group, and determining updated second individual best position and second global best position; and When the second global optimal position meets the constraint conditions, the power supply cost calculation model is solved according to the second global optimal position using the particle swarm algorithm of the updated inertia weight to determine the minimum power supply cost.

7. A power resource scheduling device based on minimum power supply cost, It is characterized in that include: A probability determination module, used to determine the probability of each power supply power interval of each power supply device in the target time period through the power prediction model, and generate a power supply power probability distribution of the power supply device corresponding to the target time period according to the probability; A condition determination module, used to determine the constraint condition corresponding to the power supply device according to the power supply power probability distribution; A model building module, used to build a power supply cost calculation model according to the power supply cost corresponding to the power supply equipment; and The cost determination module is used to solve the power supply cost calculation model according to the constraint conditions by using a particle swarm algorithm based on the updated inertia weight, determine the minimum power supply cost, and schedule the power resources according to the minimum power supply cost, wherein the expression of the particle swarm algorithm is: V i k+1 =ω k V i k +c 1 r 1 (P i k -X i k )+c 2 r 2 (G k -X i k ) (1) X i k+1 =X i k +V i k+1 (2) Where k represents the number of iterations; i represents the particle number; V i k , X i k are the velocity and position of particle i before updating; V i k+1 , X i k+1 are the updated speed and position of particle i respectively; P i k , G k are the individual best position of particle i and the global best position of the group respectively; ω k Indicates the inertia weight after updating using the preset PID module; c 1 、c 2 represents the learning factor; r 1 、r 2 Represents a random number between 0 and 1.

8. A power resource scheduling device based on minimum power supply cost, It is characterized in that include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Determine the probability of each power supply power interval of each power supply device in the target time period through the power prediction model, and generate the power supply power probability distribution of the power supply device corresponding to the target time period according to the probability; Determining a constraint condition corresponding to the power supply device according to the power supply power probability distribution; Constructing a power supply cost calculation model according to the power supply cost corresponding to the power supply equipment; and The power supply cost calculation model is solved according to the constraint conditions by a particle swarm algorithm based on the updated inertia weight, the minimum power supply cost is determined, and the power resources are scheduled according to the minimum power supply cost, wherein the expression of the particle swarm algorithm is: V i k+1 =ω k V i k +c 1 r 1 (P i k -X i k )+c 2 r 2 (G k -X i k ) (1) X i k+1 =X i k +V i k+1 (2) Where k represents the number of iterations; i represents the particle number; V i k , X i k are the velocity and position of particle i before updating; V i k+1 , X i k+1 are the updated speed and position of particle i respectively; P i k , G k are the individual best position of particle i and the global best position of the group respectively; ω k Indicates the inertia weight after updating using the preset PID module; c 1 、c 2 represents the learning factor; r 1 、r 2 Represents a random number between 0 and 1.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

Images