Power distribution network power dispatching method, electronic equipment with power distribution network power dispatching method and storage medium

Abstract

The invention discloses a power distribution network power dispatching method, electronic equipment with the power distribution network power dispatching method and a storage medium. The method comprises the steps that time information is acquired, and the time information comprises dispatching time of power dispatching of a power distribution network; the load prediction model is used to predict the load of the load node of the power distribution network at the scheduling time to obtain predicted load information, the predicted load information comprises the predicted power supply amount required by the load node of the power distribution network at the scheduling time, and the load prediction model is constructed based on the power of the load node acquired at different acquisition time points; performing target constraint calculation on the predicted load information by using a total electric quantity cost calculation model to obtain a scheduling result, the scheduling result comprising the minimum scheduling power supply quantity of the load node; and scheduling the power of the power distribution network based on the scheduling result. The technical problem of low resource utilization rate caused by inaccurate load prediction and insufficient scheduling optimization in a traditional power distribution network power scheduling method is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power dispatching, and in particular to a method for power dispatching in a distribution network, and an electronic device and a storage medium having the same. Background Art

[0002] In modern power systems, with the continuous growth of electricity demand, the load changes in the distribution network of power stations are becoming increasingly complex. If electricity is not dispatched according to demand in a timely manner, some load nodes may suffer from insufficient or excessive power supply.

[0003] Existing power dispatching methods mostly rely on regular power dispatching based on historical load data, and usually adopt simple time series models, such as moving average method, weighted average method, etc., which are difficult to reflect the load conditions of different nodes in real time and accurately, resulting in low dispatching efficiency, high energy consumption, and even power facility losses and power supply shortages; at the same time, scheduled dispatching and dispatching schemes based on historical data lack flexibility and cannot adapt to the dynamic characteristics of user load changes in a timely manner, which easily leads to excess or insufficient electricity.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiment of the present invention provides a method for power dispatching in a distribution network and an electronic device and a storage medium having the same, so as to at least solve the technical problem of low resource utilization caused by inaccurate load prediction and insufficient dispatch optimization in traditional power dispatching methods for distribution networks.

[0006] According to one aspect of an embodiment of the present invention, a method for power dispatching in a distribution network is provided, comprising: acquiring time information, the time information including the dispatching time at which the distribution network will perform power dispatching; predicting the load of a load node of the distribution network at the dispatching time using a load forecasting model to obtain predicted load information, the predicted load information including the predicted power supply required by the load node of the distribution network at the dispatching time, the load forecasting model being constructed based on the power of the load node obtained at different acquisition time points; performing target constraint calculation on the predicted load information using a total power cost calculation model to obtain a dispatching result, the dispatching result including the minimum dispatching power supply of the load node; and dispatching the power of the distribution network based on the dispatching result.

[0007] Furthermore, the total electricity cost calculation model is used to perform target constraint calculation on the predicted load information, including: establishing parameter constraint conditions and constraint targets for the target constraint calculation; inputting the predicted load information into the total electricity cost calculation model to perform target constraint calculation.

[0008] Furthermore, parameter constraints for target constraint calculation are established, including: determining that the minimum scheduled power supply of the load node is greater than or equal to the predicted power supply of the load node as a first parameter constraint; and determining that the minimum scheduled power supply of the load node is within the load parameter interval of the load node as a second parameter constraint, wherein the load parameter interval is determined by the maximum load capacity and minimum load capacity of the load node.

[0009] Furthermore, establishing a constraint target for target constraint calculation includes: determining the lowest electricity cost of each load node as the constraint target.

[0010] Furthermore, the method for constructing a load prediction model includes: obtaining power information, the power information including the power of each load node at multiple different collection time points; determining load parameter information based on the power information, wherein the load parameter information is the required power supply of each load node at the collection time point; and generating a load prediction model based on the load parameter information.

[0011] Furthermore, a load prediction model is generated based on the load parameter information, including: generating a load parameter time series corresponding to each load node based on the load parameter information; and generating a load prediction model by fitting the load parameter time series using an autoregressive integral moving average model.

[0012] Further, determining load parameter information based on power information includes: calculating the product of the power of each load node and the corresponding time period as load parameter information, wherein the time period is the time interval between two temporally adjacent collection time points of the load node.

[0013] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0014] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0015] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0016] In an embodiment of the present invention, a load prediction model and a total electricity cost optimization calculation method are adopted. The prediction model is constructed by integrating historical load data, and the target constraint optimization is performed in combination with cost calculation, so as to achieve the purpose of accurately predicting the load demand of the distribution network and optimizing power dispatching, thereby achieving the technical effect of improving the utilization rate of power resources, reducing costs and ensuring stable and reliable power supply, and further solving the technical problem of low resource utilization caused by inaccurate load prediction and insufficient dispatching optimization in traditional distribution network power dispatching methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 It is a hardware structure block diagram of a computer terminal of a method for power dispatching in a distribution network according to one optional embodiment of the present invention;

[0019] Figure 2 is a flow chart of a method for power dispatching in a distribution network according to one optional embodiment of the present invention;

[0020] Figure 3 It is a flow chart of a method for optimizing power dispatching and balancing in a distribution network according to one optional embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to an embodiment of the present invention, a method embodiment of a method for power dispatching in a distribution network 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 a 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.

[0024] The method embodiment can be executed in an electronic device including a memory and a processor in a computer or a similar computing device. For example, the electronic device running on the computer, such as Figure 1 As shown, the electronic device of the computer may include one or more processors 102 (the processor may include but is not limited to a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microprocessor (MCU), a field programmable logic device (FPGA), a neural network processor (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, etc.) and a memory 104 for storing data. Optionally, the electronic device of the above-mentioned computer may also include a transmission device 106 for communication functions, an input and output device 108, and a display device 110. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the electronic device of the computer. For example, the electronic device of the computer may include more or fewer components than the above structure description, or have a configuration different from the above structure description.

[0025] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the generation method of the large-scale fault auxiliary decision of the distribution network in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the generation method of the large-scale fault auxiliary decision of the distribution network is realized. The memory 104 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 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal 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.

[0026] The transmission device 106 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 mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as 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 (RF) module, which is used to communicate with the Internet wirelessly.

[0027] The display device 110 may be, for example, a touch screen type liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or a "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and a user may interact with the GUI by finger contact and / or gestures on a touch-sensitive surface, wherein the human-computer interaction functions here may optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for executing the above human-computer interaction functions are configured / stored in a computer program product or a readable storage medium executable by one or more processors.

[0028] In the existing technology, the performance and efficiency of power system dispatch and optimization solutions are evaluated in the following aspects:

[0029] Load forecast accuracy: Accurately forecasting the load conditions of each power consumption node is crucial to the accuracy of power dispatch. Forecast errors will directly affect the power supply plan and power costs.

[0030] Balance between power supply capacity and demand: An efficient scheduling model needs to be established to ensure that the power supply capacity meets the power demand in different time periods, avoiding power outages caused by insufficient supply or waste caused by oversupply.

[0031] Complexity of multi-node scheduling: Distribution networks usually contain multiple power consumption nodes. How to effectively coordinate power supply among multiple nodes is an important issue.

[0032] Efficiency of optimization algorithms: When solving large-scale optimization problems, the convergence speed and computational efficiency of the algorithm determine the timeliness of scheduling decisions.

[0033] This solution mainly uses the autoregressive integrated moving average model to predict and calculate the load conditions of each power consumption node.

[0034] The Autoregressive Integrated Moving Average model (ARIMA model for short) is a statistical forecasting model widely used in time series analysis, especially for the forecasting of non-stationary time series data. The ARIMA model combines the autoregressive model (AR), the difference (I, for Integrated) and the moving average model (MA) to capture the characteristics of long-term trends, seasonal fluctuations and short-term random fluctuations in the series.

[0035] In power system load forecasting, the ARIMA model can capture the periodicity, trend and random volatility of the load through historical data, and then predict future load demand, providing a theoretical basis and technical support for power dispatch and balance optimization.

[0036] Figure 2 is a flow chart of a method for power dispatching in a distribution network according to one optional embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0037] Step S102, obtaining time information, where the time information includes the dispatching time when the distribution network will perform power dispatching;

[0038] Step S104, using the load prediction model to predict the load of the load node of the distribution network at the scheduling time, to obtain predicted load information, the predicted load information includes the predicted power supply required by the load node of the distribution network at the scheduling time, the load prediction model is constructed based on the power of the load node obtained at different acquisition time points;

[0039] Step S106, using the total power cost calculation model to perform target constraint calculation on the predicted load information to obtain a scheduling result, which includes the minimum scheduled power supply of the load node;

[0040] Step S108: dispatching the power of the distribution network based on the dispatching result.

[0041] Through the above steps S102 to S108, in an embodiment of the present invention, a load prediction model and a total electricity cost optimization calculation method are adopted, a prediction model is constructed by integrating historical load data, and target constraint optimization is performed in combination with cost calculation, so as to achieve the purpose of accurately predicting the load demand of the distribution network and optimizing power dispatching, thereby achieving the technical effect of improving the utilization rate of power resources, reducing costs and ensuring stable and reliable power supply, and further solving the technical problem of low resource utilization caused by inaccurate load prediction and insufficient dispatching optimization in traditional distribution network power dispatching methods.

[0042] The present invention urgently needs a power dispatching and load balancing optimization method based on node load conditions to solve the problems of inaccurate load prediction, insufficient dispatching optimization and low resource utilization in the traditional power dispatching process. The present invention provides a power dispatching and balancing optimization method for a distribution network. Figure 3 As shown, the following steps are included:

[0043] Step 1: Obtaining the load parameters of the distribution network: When the target power station is stably generating electricity and supplying power, set several collection time points, collect the instantaneous power corresponding to each load node of the distribution network on the target power station at the collection time points, and obtain the load parameters corresponding to each load node through the instantaneous power; the load parameters are the required power supply of the load node at the collection time points;

[0044] Step 2: Construction of load prediction model: Obtain the corresponding load parameters of each load node at each acquisition time point, and generate the load parameter time series corresponding to each load node; According to the generated load parameter time series, use the autoregressive integral moving average model to fit and generate the load prediction model of the corresponding load node;

[0045] Step 3: Load prediction of load nodes: According to the generated load prediction model, calculate and predict the predicted load parameters of the next scheduling time node;

[0046] Step 4: Calculation of the dispatching results: The load parameters of the next dispatching time node calculated are combined with the total electricity cost formula. After setting constraints on the parameters of the total electricity cost formula, the goal is to minimize the electricity cost of each node, and the dispatching results after dispatch optimization are obtained; the constraints include the maximum load parameter and the minimum load parameter of the load node and the total power supply of the target power station;

[0047] Step 5: Dynamic adjustment of power supply at load nodes: The dispatched power supply of the target power station is dynamically adjusted according to the actual load parameters to optimize the dispatch results, making it more in line with the actual application scenario.

[0048] Optionally, the total electricity cost calculation model is used to perform target constraint calculation on the predicted load information, including: establishing parameter constraint conditions and constraint targets for the target constraint calculation; inputting the predicted load information into the total electricity cost calculation model to perform target constraint calculation.

[0049] Parameter constraints are necessary to ensure that the power dispatch scheme is both economical and feasible. These constraints usually include:

[0050] Maximum and minimum power supply of load nodes: Ensure that the power supply of each node does not exceed its tolerance range while ensuring basic power requirements.

[0051] Total power supply of the target power station: This constraint is to ensure that the power supply of the entire distribution network does not exceed the power generation capacity of the power station.

[0052] Power cost constraint: This constraint is based on the unit power supply cost and is usually associated with the unit time zone electricity price to ensure the economy of power dispatch decisions.

[0053] The total electricity cost is calculated as:

[0054]

[0055] Where S i,t0 is the predicted power supply of the corresponding load node, C i,t0 is the unit electricity cost;

[0056] It should be noted that C i,t0 The unit power supply cost can be adjusted in real time according to the unit time zone electricity price, specifically the unit time zone electricity price at the scheduling time point t0, to adapt to the power supply price at different power supply times, so as to better meet the actual power supply needs and more accurate power supply cost calculation.

[0057] The predicted load information is input into the total electricity cost calculation model to perform target constraint calculation. The total electricity cost formula is solved to find a scheduling solution that minimizes the electricity cost while satisfying all parameter constraints. During the calculation process, the model will consider the predicted load information, power supply cost, and total power supply capacity of each node to generate the optimal scheduling result. For example, when it is predicted that the load of a certain load node will increase significantly at the scheduling time point, the scheduling algorithm of the present invention will adjust the power supply of the power station in advance according to the target constraint calculation to ensure that the node can obtain sufficient power supply. At the same time, by optimizing the power supply of other nodes, the power demand of the entire distribution network is balanced to avoid unnecessary power waste, and ultimately achieve economic, efficient and stable operation of the entire power system.

[0058] By calculating the target constraints through the above steps, the present invention can ensure that power dispatching not only meets the actual needs of each node, but also achieves the best economy and resource utilization efficiency. This not only improves the scientific and intelligent level of power dispatching, but also effectively avoids the problem of over- or under-powering, ensuring the stable operation of the power system.

[0059] Optionally, parameter constraints for target constraint calculation are established, including: determining the minimum scheduled power supply of the load node to be greater than or equal to the predicted power supply of the load node as a first parameter constraint; determining the minimum scheduled power supply of the load node to be within the load parameter interval of the load node as a second parameter constraint, wherein the load parameter interval is determined by the maximum load capacity and minimum load capacity of the load node; and determining the lowest electricity cost for each load node as the constraint target.

[0060] Specifically, the minimum dispatched power supply of the load node is greater than or equal to the predicted power supply of the load node as the first parameter constraint condition, that is, the predicted load parameters (predicted power supply) of each load node at the scheduling time node predicted by the ARIMA model, ensuring that when performing power dispatch, the minimum power supply dispatched to each node is not less than its predicted power supply. This means that even if a certain error is considered on the basis of the predicted power supply, the power dispatch system can ensure that the power supply of each node will not be lower than the expected demand, avoiding the situation of insufficient power supply.

[0061] The constraints are:

[0062]

[0063] The minimum dispatched power supply of the load node is greater than or equal to the predicted power supply of the load node, which is determined as the first parameter constraint:

[0064]

[0065] Where D max,i is the maximum load parameter of the corresponding load node;

[0066] The minimum dispatching power supply of the load node is determined to be within the load parameter interval of the load node as the second parameter constraint condition:

[0067]

[0068] Where D min,i is the minimum load parameter of the corresponding load node;

[0069]

[0070] Where S total is the maximum power generation of the target power station; the minimum dispatching power supply S of the corresponding load node is obtained by calculation i,t0 .

[0071] A load parameter interval is set for each load node, and the interval is determined by the maximum load capacity and minimum load capacity of the load node. When performing power dispatching, ensure that the minimum power supply dispatched to each node not only satisfies the first parameter constraint, but also is within the load parameter interval of the node. On the basis of satisfying the above two parameter constraints, the technical solution of the present invention aims to minimize the power cost of each load node by solving the total power cost formula. By setting appropriate constraint targets, the total power cost formula is calculated using an optimization algorithm (such as linear programming) to obtain the lowest power cost for each node as the dispatching result.

[0072] Linear programming is a method widely used in mathematics and operations research, which is used to find the value of decision variables that optimize the linear objective function under given linear constraints. Linear programming is an optimization method used in the power dispatching and balancing optimization scheme of the distribution network of the present invention, which is used to solve the problem of minimizing the total electricity cost while satisfying a series of linear constraints. This method not only improves the scientificity and intelligence level of power dispatching, but also provides strong support for the stable operation and cost control of the power system.

[0073] The present invention adjusts the dispatched power supply of the target power station to meet the actual power demand of each load node at the dispatch time point, while ensuring that the power distribution of the entire distribution network is optimal in terms of economy and resource utilization efficiency. This condition setting can ensure that power dispatching can meet demand without exceeding the carrying capacity of the equipment.

[0074] Optionally, establishing a constraint target for target constraint calculation includes: determining the lowest electricity cost of each load node as the constraint target.

[0075] The constraint objective of the present invention is to minimize the electricity cost of each node. This means that on the basis of satisfying the above constraints, the power dispatching scheme needs to reduce the total cost of power distribution as much as possible and improve resource utilization while meeting the power demand.

[0076] Optionally, the method for constructing a load prediction model includes: obtaining power information, the power information including the power of each load node at multiple different collection time points; determining load parameter information based on the power information, wherein the load parameter information is the required power supply of each load node at the collection time point; and generating a load prediction model based on the load parameter information.

[0077] Specifically, the instantaneous power corresponding to each load node of the distribution network on the target power station is collected at the collection time point, and the load parameters corresponding to each load node are obtained through the instantaneous power. The specific collection process is as follows:

[0078] By setting up load power monitoring equipment on each load node, it is used to collect the load power P of the load node in real time. i,t , the load parameter L corresponding to the load node is obtained by calculation i,t , the load parameter calculation formula is as follows:

[0079] L i，t =P i，t ·T i，t

[0080] Where i represents the number of each load node on the distribution network, t represents the number of each acquisition time point, T i,t is the time interval between two adjacent acquisition time points.

[0081] After obtaining the power information, it is necessary to calculate the load parameter information of each load node at each acquisition time point, that is, the required power supply. This calculation can be completed by multiplying the instantaneous power at each time point by the time interval as shown in the above formula.

[0082] Optionally, generating a load prediction model based on the load parameter information includes: generating a load parameter time series corresponding to each load node based on the load parameter information; and generating a load prediction model by fitting an autoregressive integral moving average model based on the load parameter time series.

[0083] Obtain the corresponding load parameter L of each load node at each acquisition time point i,t The load parameter time series is obtained by integration, and the formula is as follows:

[0084] Y=Y1,Y2,...,Y n .According to the generated load parameter time series, the autoregressive integrated moving average model (ARIMA) is used for fitting to generate the load prediction model of the corresponding load node. The specific construction process is: the autoregressive integrated moving average model is used to fit the load data time series to obtain the predicted load model:

[0085] Y t =φ1Y t-1 +φ2Y t-2 +…+φ p Y t-p +θ1∈ t-1 +θ2∈ t-2 +…+θ q ∈ t-q +∈ t

[0086] where φ p is the influence coefficient of the load parameter at the historical acquisition time point on the predicted load parameter, p is the autoregressive order of the predicted load model, θ qis the prediction error influence coefficient of the load parameter at the historical acquisition time point, q is the moving average order, ∈ t is the random error coefficient of the current scheduling time node, which is generally assumed to obey a normal distribution with a mean of zero.

[0087] Test the fitted model to ensure its accuracy and reliability. If there is a large deviation between the model prediction results and the actual data, it may be necessary to adjust the model parameters or consider more complex time series analysis methods.

[0088] According to the generated load prediction model, the predicted load parameters of the next scheduling time node are calculated and predicted. The specific calculation process is as follows:

[0089] The load parameters of the corresponding load node at the scheduling time node are obtained through the load prediction model:

[0090]

[0091] Where t0 represents the scheduling time node, The load parameters predicted by the model.

[0092] Optionally, determining load parameter information based on power information includes: calculating the product of the power of each load node and the corresponding time period as the load parameter information, wherein the time period is the time interval between two temporally adjacent collection time points of the load node.

[0093] In a specific embodiment, data is collected once every hour, from 8 am to 8 am the next day, for a total of 24 time points. There are 3 load nodes, numbered 1, 2, and 3. At 10 am, the instantaneous power of load node 1 is 150 kW, the instantaneous power of load node 2 is 100 kW, and the instantaneous power of load node 3 is 200 kW. The time interval between two adjacent collection time points is 1 hour. Based on the above data, we can calculate the load parameter information of each load node between 10 am and 11 am: Load node 1: L 1，10 =150kWh Load node 2: L 2,10 =100kWh Load node 3: L 3，10 = 200 kWh Thus, for the collection time point of 10 a.m., we have obtained the load parameter information of the three load nodes, that is, the required power supply. This process will be repeated at each collection time point until all data within 24 time points are collected.

[0094] By collecting instantaneous power at each time point and calculating load parameter information, we can obtain the power demand of each load node in the distribution network in different time periods. This information is crucial for building a load forecasting model, which helps us accurately predict future load demand, thereby optimizing power dispatching and balancing power supply to ensure efficient operation of the power system. In the present invention, this series of calculations and predictions will ultimately be used to determine the minimum dispatching power supply for each node to minimize the total power cost while meeting load demand and power supply stability.

[0095] If scheduling is based solely on prediction models without considering actual load conditions, it may lead to uneven resource allocation or oversupply, resulting in energy waste and increased economic costs. Dynamic adjustment can ensure that power resources are more reasonably allocated. Dynamically adjusting the scheduling optimization results based on actual load parameters is an important means to ensure efficient and stable operation of the power system while achieving resource optimization and cost control. This strategy enables the power system to better adapt to real-time changes in power demand and improve the flexibility and accuracy of power scheduling.

[0096] The scheduling results after scheduling optimization are dynamically adjusted according to the actual load parameters. The specific implementation process is as follows:

[0097] Adjust the actual load data collected at the scheduling time node:

[0098] S′i,t0=Si,t0+ΔS i，t0

[0099] Where: S'i,t0 is the actual power supply after dynamic adjustment;

[0100]

[0101] Where △S i,t0 is the dynamically adjusted power supply, L i,t0 The actual load of the node at the current scheduling time.

[0102] In an optional embodiment, we will use a simplified model of a 10kV distribution network, which includes three load nodes (node ​​1, node 2, node 3), and a target power station. The goal is to dynamically adjust the power supply from the power station to each node based on the real-time load parameters to optimize the power dispatch of the entire system while ensuring power supply stability and cost efficiency. Assume that we have used the ARIMA model to predict the load parameters of each node at the next scheduling time node (for example, the next 1 hour). The prediction results are as follows: Node 1: predicted load parameter is 120kWh; Node 2: predicted load parameter is 80kWh; Node 3: predicted load parameter is 100kWh; = Assume that after the prediction model is applied, we get the following dispatch power supply: Node 1: 120kWh; Node 2: 80kWh Node 3: 100kWh; Set the power supply of each node to meet the interval of its maximum and minimum load parameters, and the total power supply of the entire power station shall not exceed its maximum power generation. We set: the maximum load parameter of node 1 is 150kWh and the minimum is 50kWh; the maximum load parameter of node 2 is 100kWh and the minimum is 30kWh; the maximum load parameter of node 3 is 120kWh and the minimum is 40kWh; the maximum power generation of the power station is 400kWh. Dynamically adjust the dispatched power supply according to the actual load parameters and monitor in real time: At the dispatch time node (the next hour), we monitor the actual load parameters of each node in real time. The actual load of node 1 is 130kWh (slightly higher than the forecast); the actual load of node 2 is 70kWh (close to the forecast); the actual load of node 3 is 110kWh (slightly higher than the forecast). Based on the actual load parameters, we dynamically adjust the dispatched power supply. The adjustment strategy is as follows: adjust the power supply of node 1 to 130kWh to meet its current load demand; maintain the power supply of node 2 at 80kWh because the actual load parameters are close to its predicted value; adjust the power supply of node 3 to 110kWh to adapt to its actual load changes. According to the adjusted strategy, the power station needs to provide the following power supply to each node: Node 1: 130kWh; Node 2: 80kWh; Node 3: 110kWh, total power supply: 130kWh+80kWh+110kWh=320kWh, which meets the constraint of the power station's maximum power generation of 400kWh. By real-time monitoring and dynamic adjustment of power supply, we ensure that the power supply needs of each node are met, while avoiding waste or over-allocation of electricity, optimizing power dispatch, and reducing the total power cost. This approach improves the flexibility and response speed of the power system and ensures the stability and economy of power supply.

[0103] The present invention has the following innovative features:

[0104] 1. The embodiments of the present invention calculate the electricity cost based on the predicted load parameters in combination with the total electricity cost formula (such as electricity price, power generation cost, etc.), set constraints (maximum / minimum load parameters, total power supply, etc.), and then use linear programming or other optimization algorithms to solve the best scheduling solution.

[0105] 2. The embodiments of the present invention can effectively reduce the electricity cost of each node through scheduling optimization, achieve optimal resource allocation, and ensure that all load nodes can obtain a stable power supply under set constraints, thereby reducing the risks caused by overload or insufficient power supply.

[0106] 3. The embodiments of the present invention use a dynamic adjustment mechanism so that the system can quickly adapt to load changes, thereby improving the stability and reliability of the overall power supply. Timely power supply adjustment can avoid cost waste and reduce economic losses caused by insufficient power supply.

[0107] The present invention provides a method based on historical data analysis of load nodes, selects an autoregressive integrated moving average ARIMA model, and uses past load parameter time series data for fitting to establish a load forecasting model. Through the application of the ARIMA model, the trend of load changes can be effectively captured, so that the changes in load demand of each load node can be known in advance, and the distribution of power supply is adjusted with the goal of minimizing the electricity cost of each node. Automated load forecasting reduces the necessity of manual estimation, improves the efficiency and scientificity of scheduling, and is more in line with actual usage.

[0108] The embodiment of the present application also provides an electronic device, comprising: a memory storing an executable program; a processor for running the program, wherein when the program is running, the method for power dispatching of a distribution network in each embodiment of the present invention is executed. The specific steps are as follows:

[0109] Step S102, obtaining time information, where the time information includes the dispatching time when the distribution network will perform power dispatching;

[0110] Step S104, using the load prediction model to predict the load of the load node of the distribution network at the scheduling time, to obtain predicted load information, the predicted load information includes the predicted power supply required by the load node of the distribution network at the scheduling time, the load prediction model is constructed based on the power of the load node obtained at different acquisition time points;

[0111] Step S106, using the total power cost calculation model to perform target constraint calculation on the predicted load information to obtain a scheduling result, which includes the minimum scheduled power supply of the load node;

[0112] Step S108: dispatching the power of the distribution network based on the dispatching result.

[0113] The embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the method for power dispatching of the distribution network in each embodiment of the present invention. The specific steps are as follows:

[0114] Step S102, obtaining time information, where the time information includes the dispatching time when the distribution network will perform power dispatching;

[0115] Step S104, using the load prediction model to predict the load of the load node of the distribution network at the scheduling time, to obtain predicted load information, the predicted load information includes the predicted power supply required by the load node of the distribution network at the scheduling time, the load prediction model is constructed based on the power of the load node obtained at different acquisition time points;

[0116] Step S106, using the total power cost calculation model to perform target constraint calculation on the predicted load information to obtain a scheduling result, which includes the minimum scheduled power supply of the load node;

[0117] Step S108: dispatching the power of the distribution network based on the dispatching result.

[0118] The embodiments of the present application also provide a computer program product, including a computer program, which implements the method for power dispatching of a distribution network in various embodiments of the present invention when executed by a processor. The specific steps are as follows:

[0119] Step S102, obtaining time information, where the time information includes the dispatching time when the distribution network will perform power dispatching;

[0120] Step S104, using the load prediction model to predict the load of the load node of the distribution network at the scheduling time, to obtain predicted load information, the predicted load information includes the predicted power supply required by the load node of the distribution network at the scheduling time, the load prediction model is constructed based on the power of the load node obtained at different acquisition time points;

[0121] Step S106, using the total power cost calculation model to perform target constraint calculation on the predicted load information to obtain a scheduling result, which includes the minimum scheduled power supply of the load node;

[0122] Step S108: dispatching the power of the distribution network based on the dispatching result.

[0123] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0124] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0125] 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.

[0126] 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 can be 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.

[0127] 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0128] 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.

[0129] 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, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0130] 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 power dispatching in a distribution network, characterized in that: include: Acquiring time information, wherein the time information includes a dispatching time at which the distribution network will perform power dispatching; The load prediction model is used to predict the load of the load node of the distribution network at the scheduling time to obtain predicted load information, wherein the predicted load information includes the predicted power supply required by the load node of the distribution network at the scheduling time, and the load prediction model is constructed based on the power of the load node obtained at different acquisition time points; Using a total power cost calculation model to perform target constraint calculation on the predicted load information to obtain a scheduling result, wherein the scheduling result includes a minimum scheduling power supply of the load node; The power of the distribution network is dispatched based on the dispatch result.

2. The method according to claim 1, characterized in that The target constraint calculation is performed on the predicted load information using the total electricity cost calculation model, including: Establishing parameter constraint conditions and constraint targets for the target constraint calculation; The predicted load information is input into the total electricity cost calculation model to perform the target constraint calculation.

3. The method according to claim 2, characterized in that Establishing parameter constraints for the target constraint calculation includes: Determining that the minimum scheduled power supply of the load node is greater than or equal to the predicted power supply of the load node as a first parameter constraint condition; The minimum scheduled power supply of the load node is determined as a second parameter constraint condition to be within a load parameter interval of the load node, wherein the load parameter interval is determined by a maximum load capacity and a minimum load capacity of the load node.

4. The method according to claim 2, characterized in that: Establishing the constraint target of the target constraint calculation includes: determining the lowest electricity cost of each of the load nodes as the constraint target.

5. The method according to claim 1, characterized in that The method for constructing the load prediction model includes: Acquiring power information, the power information including the power of each of the load nodes at a plurality of different acquisition time points; Determine load parameter information based on the power information, wherein the load parameter information is the required power supply of each load node within the collection time point; The load prediction model is generated based on the load parameter information.

6. The method according to claim 5, characterized in that Generating the load prediction model based on the load parameter information includes: Generate a load parameter time series corresponding to each of the load nodes based on the load parameter information; Based on the load parameter time series, an autoregressive integrated moving average model is used for fitting to generate the load prediction model.

7. The method according to claim 5, characterized in that Determining load parameter information based on the power information includes: The product of the power of each load node and the corresponding time period is calculated as the load parameter information, wherein the time period is the time interval between two temporally adjacent collection time points of the load node.

8. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 7 when running.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images