Output power determination method and device capable of adjusting load and electronic equipment

Abstract

The invention discloses a load-adjustable output power determination method and device and electronic equipment. The method comprises the following steps: acquiring power data of a target power grid; based on the electric power data, determining outsourcing electric quantity of the target power grid, aggregated output and first output power of an adjustable load of the target power grid, the aggregated output being output power of an adjustable load-energy storage aggregation unit of the target power grid; determining second output power of the adjustable load based on load data of the adjustable load in the power data and the first output power; and determining a target output power of the adjustable load based on the outsourcing electric quantity, the aggregated output and the second output power. According to the invention, the technical problem that the determination result of the output power of the adjustable load in the power grid is inaccurate in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power systems, and in particular, to a method and device for determining output power of adjustable load and an electronic device. BACKGROUND

[0002] New power systems are the inevitable requirement for adapting to the trend of energy technology progress and promoting system transformation and upgrading. Adjustable load plays a crucial role in new power systems. The demand side of adjustable load can be used as an important means to reduce peak load and balance the gap in power supply, and has an important role in power system operation and control. By tapping the adjustable load resources on the demand side, including industrial, residential and new load areas of electrical equipment, the peak shaving characteristics and peak shaving potential of adjustable load can be analyzed to achieve peak load reduction and valley filling of the power grid and improve the efficiency of power grid operation. In addition, the participation of adjustable load in power grid regulation can improve the flexibility of the power system, achieve efficient interaction between supply and demand, and support renewable energy consumption and safe and stable operation of the power grid. Therefore, determining the output power of adjustable load is crucial for the safe and stable operation of new power systems.

[0003] In related technologies, the output power of adjustable load is mainly determined by traditional optimization scheduling methods. In this process, the scheduling priority of adjustable load is usually lower than that of energy storage resources, which limits the role of adjustable load in power system scheduling and cannot fully utilize its regulation capacity. At the same time, traditional scheduling decisions rely on load forecasting, but existing forecasting models have limited forecasting accuracy when dealing with complex power grid systems and high-dimensional data, resulting in large errors in forecasting results. Therefore, the related technologies have the technical problem of inaccurate determination of the output power of adjustable load in the power grid.

[0004] At present, there is no effective solution to the above problems. SUMMARY

[0005] Embodiments of the present application provide a method and device for determining the output power of adjustable load and an electronic device to at least solve the technical problem of inaccurate determination of the output power of adjustable load in the power grid in related technologies.

[0006] According to an aspect of the embodiments of the present application, a method for determining output power of an adjustable load is provided, comprising: obtaining power data of a target power grid; determining, based on the power data, an amount of purchased power, an aggregated output power, and a first output power of the adjustable load of the target power grid, wherein the aggregated output power refers to an output power of an adjustable load-energy storage aggregation unit of the target power grid; determining, based on load data of the adjustable load in the power data and the first output power, a second output power of the adjustable load; and determining, based on the amount of purchased power, the aggregated output power, and the second output power, a target output power of the adjustable load.

[0007] According to another aspect of the embodiments of the present application, a device for determining output power of an adjustable load is provided, comprising: a data obtaining module configured to obtain power data of a target power grid; a first determining module configured to determine, based on the power data, an amount of purchased power, an aggregated output power, and a first output power of the adjustable load of the target power grid, wherein the aggregated output power refers to an output power of an adjustable load-energy storage aggregation unit of the target power grid; a second determining module configured to determine, based on load data of the adjustable load in the power data and the first output power, a second output power of the adjustable load; and a third determining module configured to determine, based on the amount of purchased power, the aggregated output power, and the second output power, a target output power of the adjustable load.

[0008] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, which stores a plurality of instructions adapted to be loaded and executed by a processor to implement any of the methods for determining output power of an adjustable load.

[0009] According to another aspect of the embodiments of the present application, an electronic device is provided, comprising: one or more processors and a memory configured to store one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement any of the methods for determining output power of an adjustable load.

[0010] According to another aspect of the embodiments of the present application, a computer program product is provided, which, when executed on a data processing device, is adapted to execute the steps of the method for determining output power of an adjustable load.

[0011] In this embodiment, power data of the target power grid is acquired; based on the power data, the purchased electricity, aggregated output, and first output power of the adjustable load of the target power grid are determined, wherein aggregated output refers to the output power of the adjustable load-energy storage aggregation unit of the target power grid; based on the load data and first output power of the adjustable load in the power data, a second output power of the adjustable load is determined; and based on the purchased electricity, aggregated output, and second output power, a target output power of the adjustable load is determined. This achieves the goal of determining the output power of the adjustable load-energy storage aggregation unit and the purchased electricity of the target power grid by acquiring power data of the target power grid, thereby determining the target output power of the adjustable load of the target power grid. This improves the accuracy of the determination of the output power of the adjustable load in the power grid, and solves the technical problem of inaccurate determination of the output power of the adjustable load in the power grid in related technologies. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0013] Figure 1 This is a flowchart of a method for determining the output power of an adjustable load according to an embodiment of this application;

[0014] Figure 2 This is a flowchart of an optional method for determining the output power of an adjustable load according to an embodiment of this application;

[0015] Figure 3 This is a structural diagram of an optional dynamic BP neural network provided according to an embodiment of this application;

[0016] Figure 4 This is a schematic diagram of an optional second output power prediction result based on a dynamic BP neural network according to an embodiment of this application;

[0017] Figure 5 This is a schematic diagram of an optional adjustable load output power determination device according to an embodiment of this application. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] According to an embodiment of this application, a method embodiment for determining the output power of an adjustable load is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0021] Figure 1 This is a flowchart of a method for determining the output power of an adjustable load according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0022] Step S102: Obtain power data of the target power grid;

[0023] This involves acquiring power data from the target power grid, such as load data for adjustable loads included within the target grid. By acquiring and processing this power data, a solid data foundation is provided for subsequently determining the output power of the adjustable loads.

[0024] Step S104: Based on the power data, determine the purchased electricity, aggregated output, and first output power of the adjustable load of the target power grid, wherein the aggregated output refers to the output power of the adjustable load-energy storage aggregation unit of the target power grid;

[0025] Understandably, based on the power data of the target power grid, a target-oriented optimal scheduling model is used to determine the purchased electricity, aggregated output, and the initial output power of the adjustable load of the target power grid within a predetermined time period (e.g., one day). Aggregated output refers to the output power of the adjustable load-energy storage aggregation unit of the target power grid. Through accurate prediction and optimized scheduling, the accuracy of the target output power determination results for adjustable loads can be improved, thereby allocating grid resources more rationally, reducing unnecessary purchased electricity, maximizing the flexibility of adjustable loads, and reducing grid operating costs.

[0026] Optionally, adjustable loads in the local power grid (i.e., the target power grid) can be aggregated with energy storage units for day-ahead optimized scheduling to determine the purchased electricity (including purchased active power and purchased reactive power) from the upper-level power grid and the aggregated output of the adjustable load-energy storage aggregation unit (including active power aggregation output and reactive power aggregation output).

[0027] Optionally, aggregating adjustable loads and energy storage units in a local power grid for day-ahead optimal dispatch is of great significance for the efficient operation of the power system. First, due to the large scale of the power system, unified dispatch of all adjustable loads is impractical; therefore, optimizing the dispatch of adjustable loads in local power grids becomes a feasible and necessary choice. The main objective of day-ahead optimal dispatch is to determine the amount of electricity purchased by the local power grid from the upper-level grid for the next day, reducing unnecessary energy waste and lowering grid operating costs. Second, aggregating adjustable loads and energy storage units for optimal dispatch can fully leverage their synergistic effects. Adjustable loads have a strong ability to participate in dispatch, but considering their high volatility, grid dispatch may prioritize the use of energy storage units, thus limiting the regulatory role of adjustable loads. By aggregating them, a larger dispatch space can be reserved for adjustable loads in day-ahead dispatch where forecast data accuracy is low, allowing them to fully realize their potential in short-term dispatch. This method not only reduces dependence on traditional energy sources but also ensures the operational reliability of the local power grid, providing a more efficient and accurate solution for the optimal dispatch of local power grids. This local grid distributed energy storage optimization scheduling based on adjustable load-energy storage aggregation units can better handle integer and continuous variables in the local grid, making the local grid scheduling results more accurate, thereby improving the efficiency of tapping and utilizing the power system's resource regulation potential.

[0028] In one optional embodiment, determining the purchased electricity, aggregated output, and first output power of the adjustable load of the target power grid based on power data includes: obtaining the purchased electricity, aggregated output, and first output power using a target optimization scheduling model based on power data. The target optimization scheduling model includes an objective function and constraints. The objective function is used to minimize the operating cost of the target power grid. The constraints include power balance constraints, node power constraints, node voltage constraints, and branch transmission power constraints of the target power grid. A node refers to a specific location in the target power grid that needs to exhibit electrical attributes.

[0029] It can be understood that inputting power data into the target optimization scheduling model yields the purchased power (e.g., purchased active and reactive power) of the target grid, the aggregated output of the adjustable load-energy storage aggregation unit (e.g., active and reactive power aggregation), and the initial output power of the adjustable load. This target optimization scheduling model includes an objective function and constraints. The objective function minimizes the operating cost of the target grid. Constraints include power balance constraints, node power constraints, node voltage constraints, and branch transmission power constraints. By setting reasonable constraints and an objective function, the accuracy of the target output power of the adjustable load can be significantly improved, thereby optimizing grid operation and enhancing power system stability.

[0030] In one optional embodiment, the objective optimization scheduling model includes: when the purchased electricity includes purchased active power and purchased reactive power, and the aggregated power output includes aggregated active power output and aggregated reactive power output, the objective function is:

[0031]

[0032] Where f1 represents the objective function, and T represents the scheduling period. P represents the active power purchase cost of the target power grid at time t. t s This represents the purchased active power of the target power grid at time t. This represents the reactive power purchase cost of the target power grid at time t. This represents the purchased reactive power of the target power grid at time t, and I represents the total number of nodes. This indicates the output cost of adjustable load. This represents the first output power of the adjustable load at the i-th node at time t. This represents the operating cost of charging and discharging the energy storage unit of the target power grid at time t. Let represent the active power output by the energy storage unit at the i-th node at time t. This represents the reactive power output cost of the adjustable load-energy storage aggregation unit of the target power grid at time t. This represents the reactive power aggregation output of the adjustable load-energy storage aggregation unit of the target power grid at time t. P represents the active power output cost of the adjustable load-energy storage aggregation unit of the target power grid at time t. t LES This represents the active power aggregated output of the adjustable load-energy storage aggregation unit of the target power grid at time t;

[0033] The power balance constraint is:

[0034]

[0035] Among them, P d (i,t) represents the active power aggregated output of the adjustable load-energy storage aggregation unit at node i at time t, P L (i,t) represents the active load of the adjustable load-energy storage aggregation unit at node i at time t, U(i,t) represents the voltage amplitude at node i at time t, U(j,t) represents the voltage amplitude at node j at time t, and G ij Let θ(ij,t) represent the conductance of line ij consisting of nodes i and j, and let B represent the phase angle difference of line ij. ij Q represents the susceptance of line ij. d (i,t) represents the reactive power aggregation output of the adjustable load-energy storage aggregation unit at node i at time t, Q L (i,t) represents the reactive load of the adjustable load-energy storage aggregation unit at node i at time t, and n represents the number of nodes;

[0036] The node power constraint is:

[0037]

[0038] Among them, P imin and P imax Let Q represent the upper and lower limits of the active power at node i, respectively. imin and Q imax Let P represent the upper and lower limits of the reactive power at node i, respectively. i (t) and Q i (t) represent the active power and reactive power injected at node i at time t, respectively;

[0039] The node voltage constraint is:

[0040] U imin ≤U i (t)≤U imax

[0041] Among them, U imin and U imax U represents the upper and lower voltage limits of node i, respectively. i (t) represents the voltage value at node i at time t;

[0042] The branch transmission power constraint is:

[0043] P lij ≤P lijmax

[0044] Among them, P lij P represents the transmission power of line ij. lijmax This represents the upper limit of the transmission power of line ij.

[0045] The objective function of the target optimization scheduling model is understood to minimize the operating cost of the target power grid. The constraints of the target optimization scheduling model include power balance constraints, node power constraints, node voltage constraints, and branch transmission power constraints. Specifically, the power balance constraint ensures that the total power generation of the target power grid equals the total power consumption; the node power constraint limits the power input and output of each node to prevent exceeding its power handling capacity; the node voltage constraint ensures that the voltage of each node is within a safe range, avoiding excessively high or low voltage that could affect equipment operation and power quality; and the branch transmission power constraint sets an upper limit on the transmission power of each branch in the power grid to avoid line overload and ensure the stability and security of power transmission. By comprehensively considering the operating cost, security, scheduling flexibility, and optimal resource utilization of the power grid, the target optimization scheduling model effectively improves the prediction accuracy of the target output power of adjustable loads, thereby improving the accuracy of the target output power determination results.

[0046] Step S106: Based on the load data of the adjustable load and the first output power in the power data, determine the second output power of the adjustable load;

[0047] It is understandable that the second output power of the adjustable load is determined based on the load data of the adjustable load included in the power data, and the first output power of the adjustable load output by the aforementioned target optimization scheduling model. By adjusting the first output power of the adjustable load in conjunction with the load data of the adjustable load, the accuracy and rationality of the output power prediction results of the adjustable load can be further improved, ultimately improving the accuracy of the target output power determination results.

[0048] In one optional embodiment, determining the second output power of the adjustable load based on the load data of the adjustable load in the power data and the first output power includes: using a load forecasting model based on the load data and the first output power to obtain the second output power, wherein the load forecasting model includes an input layer, an association layer, a hidden layer and an output layer, the input layer is used to input the load data and the first output power, the association layer is used to capture the time series characteristics of the data input to the input layer, the hidden layer is used to extract information of the load data and the first output power through nonlinear transformation, and the output layer is used to output the second output power.

[0049] It can be understood that by inputting the load data and the first output power of the adjustable load into the load forecasting model, the second output power of the adjustable load is obtained. The aforementioned load forecasting model can employ a dynamic BP neural network (Backpropagation Neural Network) model, which includes an input layer, a correlation layer, a hidden layer, and an output layer. The input layer is used to input the load data and the first output power; the correlation layer is used to capture the time-series characteristics of the data input to the input layer; the hidden layer is used to extract deep features of the load data and the first output power through nonlinear transformation; and the output layer is used to output the second output power of the adjustable load. Accurate prediction of the second output power provides more reliable information for the optimized prediction of the target output power of the adjustable load, enabling the predicted target output power to better adapt to real-time changes in the power grid and improving the rationality and accuracy of the target output power.

[0050] Optionally, based on intraday rolling load data and the first output power of the adjustable load, a load forecasting model based on a dynamic BP neural network can be used to perform ultra-short-term forecasting of the adjustable load power to obtain the second output power of the adjustable load. To address the uncertainty of the first output power of the intraday adjustable load, more refined intraday rolling adjustable load forecasting is needed to improve the accuracy of the second output power forecast. When performing ultra-short-term forecasting of the adjustable load, a method capable of achieving fast and accurate short-term forecasting needs to be selected. Therefore, a dynamic BP neural network is used as the load forecasting model to perform rolling forecasting of the second output power of the intraday adjustable load.

[0051] Optionally, compared to traditional BP neural networks, dynamic BP neural networks incorporate an additional correlation layer for constructing local feedback. In the structure of dynamic BP neural networks, the correlation layer plays a crucial role. Unlike traditional linear functions, the correlation layer introduces a delay unit, enabling it to remember historical states. This design allows the neural network to re-input the output from previous moments as input values, thus achieving dynamic memorization of past information. This memory mechanism allows dynamic BP neural networks to capture and learn patterns and trends in time-series data, which is particularly important for handling time-dependent problems. Specifically, the presence of hidden layers greatly enhances the neural network's ability to process complex data. In tasks such as time series forecasting, there are often inherent temporal correlations between data points, and hidden layers can provide temporal continuity to the network by remembering past calculation results. This continuity allows dynamic BP neural networks to identify long-term dependencies in the data, thus taking these dependencies into account when predicting future values. Furthermore, the introduction of hidden layers also provides the neural network with the ability to perform nonlinear fitting. Without hidden layers, neural networks can only perform linear transformations, limiting their ability to solve nonlinear problems. By introducing nonlinear activation functions, the hidden layer enables the dynamic BP neural network to learn and simulate complex nonlinear relationships, thereby improving the expressive power and prediction accuracy of the load forecasting model.

[0052] Optionally, the second output power of the adjustable load can be obtained using a dynamic BP neural network as follows: First, the load data of the adjustable load of the target power grid and the first output power are input into a load forecasting model based on a dynamic BP neural network. Second, in the load forecasting model based on the dynamic BP neural network, a hidden layer is obtained through the input layer. Next, in the load forecasting model based on the dynamic BP neural network, an association layer is obtained through the hidden layer. Finally, in the load forecasting model based on the dynamic BP neural network, the output layer is obtained through the interaction between the association layer and the hidden layer, outputting the predicted result of the adjustable load, i.e., the second output power of the adjustable load.

[0053] Step S108: Based on purchased electricity, aggregated output power, and second output power, determine the target output power of the adjustable load.

[0054] It is understandable that the target output power of the target power grid is determined based on the purchased electricity, the aggregated output of the adjustable load-energy storage aggregation unit, and the second output power of the adjustable load. By comprehensively considering the interaction between purchased electricity, aggregated output, and second output power, the rationality and accuracy of the target output power can be improved, optimal resource allocation can be achieved, and power grid operating costs can be reduced.

[0055] In one alternative embodiment, determining the target output power of the adjustable load based on purchased electricity, aggregated output power, and a second output power includes:

[0056] Based on purchased electricity and aggregated output, an improved particle swarm optimization algorithm is used to optimize the second output power to obtain the target output power. The fitness function of the improved particle swarm optimization algorithm is used to maximize the target output power of the adjustable load.

[0057]

[0058] Where f2 represents the fitness function and PF represents the penalty function. Let represent the target output power of the adjustable load at the i-th node at time t.

[0059] It is understandable that, based on purchased electricity and aggregated power output, an improved particle swarm optimization (PSO) algorithm is used to optimize the second output power of the adjustable load, thereby obtaining the target output power of the adjustable load. Specifically, the fitness function of the improved PSO algorithm is used to maximize the target output power of the adjustable load. Optimizing the second output power of the adjustable load using the improved PSO algorithm not only improves the accuracy of the target output power but also enhances the flexibility and stability of the power grid, ensuring the safe and stable operation of the power system.

[0060] Optionally, an improved particle swarm optimization (PSO) algorithm can be used to achieve short-term intraday optimal scheduling, obtaining the target output power of the adjustable load. PSO is a widely used intelligent optimization technique suitable for solving various complex nonlinear problems. This algorithm generates or pre-sets a series of initial solutions, then performs optimization searches according to specific iterative rules, aiming to make the quality of the solutions as close to the optimum as possible. In PSO, each potential solution is considered a particle, each with a unique velocity and position, and their fitness value is evaluated by a defined fitness function. The fitness score of a particle determines its optimal individual solution (i.e., a local optimum) and global optimum in the swarm. However, traditional PSO algorithms suffer from slow convergence speed and susceptibility to local optima. To address this, a fast and adaptive improved PSO algorithm can be proposed to accelerate convergence and, to some extent, overcome the disadvantage of obtaining locally optimal results.

[0061] Optionally, short-term intraday optimal scheduling can be achieved using an improved particle swarm optimization (PSO) algorithm, with the objective of maximizing the target output power of the adjustable load. This optimizes the second output power of the adjustable load, yielding its target output power. This short-term intraday optimal scheduling, aiming to maximize the target output power of the adjustable load, aims to achieve efficient utilization of adjustable load resources in the local power grid through an improved PSO algorithm. This maximizes the utilization of flexibility resources in the local power grid to respond to intraday fluctuations in electricity demand and the uncertainty of renewable energy. By optimizing the second output power of the adjustable load, reliance on expensive and inefficient frequency regulation services can be reduced, lowering the operating costs of the local power grid while improving its operational stability and reliability. The improved PSO algorithm finds the optimal solution by simulating the social behavior of bird flocks. Compared to the traditional PSO algorithm, the improved PSO algorithm improves the convergence speed and global search capability by adjusting parameters and introducing new strategies, thus finding the optimal target output power of the adjustable load more effectively.

[0062] Optionally, an improved particle swarm optimization algorithm with the objective of maximizing the output of adjustable load is constructed. The intraday short-term optimization scheduling takes the purchased electricity from the upstream grid and the aggregated output of the adjustable load-energy storage aggregation unit determined by the day-ahead optimization scheduling as references. Based on this, the second output power is optimized with the objective of maximizing the target output power of the adjustable load.

[0063] Optionally, consistency between the day-ahead optimal scheduling and intraday short-term optimal scheduling results can be ensured by constructing a penalty function characterizing the difference between day-ahead optimal scheduling and intraday short-term optimal scheduling. In intraday short-term optimal scheduling, the purchased electricity from the local grid to the upper-level grid and the aggregated output of the adjustable load-energy storage aggregation unit should be consistent with the day-ahead optimal scheduling results. Therefore, a penalty function PF is introduced. The penalty function PF can be determined as follows:

[0064]

[0065] in, and These represent the purchased active power from the upper-level power grid during the day-ahead optimized scheduling and intraday short-term optimized scheduling at time t, respectively. and These represent the reactive power purchased from the upper-level power grid during the day-ahead optimized scheduling and intraday short-term optimized scheduling at time t, respectively. and These represent the active power aggregated output of the adjustable load-energy storage aggregation unit in the day-ahead optimized scheduling and intraday short-term optimized scheduling at time t, respectively. and ε1 and ε2 represent the reactive power aggregation output of the adjustable load-energy storage aggregation unit in the day-ahead optimized scheduling and intraday short-term optimized scheduling at time t, respectively. ε1 and ε2 represent the penalty term coefficients for the deviation value of purchased electricity and the deviation value of the aggregation output of the adjustable load-energy storage aggregation unit, respectively.

[0066] In an optional embodiment, the method further includes: improving the particle swarm optimization algorithm to update the particle velocities in the following manner:

[0067]

[0068] in, This represents the position of particle a in the (f+1)th iteration. This represents the position of particle a in the f-th iteration. Let represent the local optimal position of particle a in the f-th iteration, and β represent the convergence rate. Let f represent the global optimal position in the f-th iteration, α represent the random decay factor of the particle, R represent a random value that follows a standard normal distribution, and S represent the boundary of the particle.

[0069] It is understandable that updating the particle velocity of the improved particle swarm optimization algorithm in the above manner can effectively improve the algorithm's optimization ability and convergence speed, and improve the accuracy and real-time performance of the target output power determination result.

[0070] Optionally, the second output power of the adjustable load of the local power grid is used as the initial solution, and an improved particle swarm optimization (PSO) algorithm is used for optimization to finally obtain the optimal target output power of the adjustable load. The improved PSO algorithm introduces a dynamically adjusted convergence rate β in its particle velocity update method to achieve a balance between fast convergence and fine-grained search. In the early stages of the search, β is assigned a large value to accelerate the convergence process. As iterations progress, the value of β gradually decreases to achieve a more refined search. Simultaneously, α*R*S is used to expand the search range of the particles, helping them escape local optima and find the global optimum. For infeasible solutions, a penalty function strategy is used to adjust the fitness value of the solution instead of directly eliminating them. These solutions will obtain higher fitness values ​​after fitness evaluation and will be retained for the next iteration. Furthermore, when updating the optimal position of particles, the improved PSO algorithm uses a standard normal distribution and particle boundaries to guide the update process, rather than a completely random approach, which helps maintain the fitness of feasible solutions and improves the overall efficiency of the algorithm. These adjustments improve the particle swarm optimization algorithm, allowing it to maintain search efficiency while enhancing solution quality and algorithm robustness.

[0071] Through the above steps S102 to S108, the goal of determining the output power and purchased electricity of the adjustable load-energy storage aggregation unit of the target power grid by acquiring the power data of the target power grid, and then determining the target output power of the adjustable load of the target power grid, can be achieved. This improves the accuracy of the determination result of the adjustable load output power in the power grid and solves the technical problem of inaccurate determination result of the adjustable load output power in the power grid in related technologies.

[0072] Based on the above embodiments and optional embodiments, this application proposes an implementation method for determining the output power of an optional adjustable load. This implementation method can be understood as an adjustable load optimization scheduling method based on a dynamic BP neural network-improved particle swarm algorithm, used to accurately determine the target output power of the adjustable loads included in the target power grid.

[0073] The participation of adjustable loads in dispatching new power systems faces several challenges. First, the priority given to adjustable loads in dispatching is insufficient, typically ranking them after resources such as energy storage units. This priority setting limits the potential and role of adjustable loads in power system dispatching, preventing them from fully utilizing their regulatory capacity. Second, because the responsiveness of adjustable loads cannot be rigidly scheduled and deployed like traditional generating units, their non-rigid dispatching characteristics present new challenges for the target grid's dispatching of adjustable loads. Furthermore, existing dispatching methods do not adequately consider load management optimization mechanisms on the load side and ignore the individual willingness of dispatched users, potentially affecting user participation and dispatching effectiveness.

[0074] In summary, a method for optimizing and scheduling adjustable loads based on dynamic BP neural network and improved particle swarm optimization algorithm is proposed. This method addresses the problem of low accuracy in determining the target output power of adjustable loads due to their low priority in grid scheduling, slow convergence speed in the optimization process, and susceptibility to local optima. This approach effectively reduces grid operating costs and improves the flexibility and reliability of the power system.

[0075] Figure 2 This is a flowchart of an optional method for determining the output power of an adjustable load according to an embodiment of this application. Figure 2 The flowchart of the adjustable load optimization scheduling method based on dynamic BP neural network-improved particle swarm optimization algorithm is described. Figure 2 The steps of this method include:

[0076] Step S1: Aggregate the adjustable loads in the local power grid (i.e., the target power grid) with the energy storage units for day-ahead optimization scheduling, and determine the purchased electricity (including purchased active power and purchased reactive power) from the upper-level power grid and the aggregated output of the adjustable load-energy storage aggregation unit (including active power aggregation output and reactive power aggregation output).

[0077] Aggregating adjustable loads and energy storage units in local power grids for day-ahead optimal dispatch is crucial for the efficient operation of power systems. First, due to the vast scale of power systems, unified dispatch of all adjustable loads is impractical; therefore, optimizing the dispatch of adjustable loads within local power grids becomes a feasible and necessary choice. The main objective of day-ahead optimal dispatch is to determine the amount of electricity the local power grid will purchase from the upper-level grid the following day, reducing unnecessary energy waste and lowering grid operating costs. Second, aggregating adjustable loads and energy storage units for optimal dispatch fully leverages their synergistic effects. Adjustable loads have a strong capacity to participate in dispatch, but given their high volatility, grid dispatch may prioritize energy storage units, thus limiting the regulatory role of adjustable loads. By aggregating them, a larger dispatch margin can be reserved for adjustable loads in day-ahead dispatch where forecast data accuracy is low, allowing them to fully realize their potential in short-term dispatch. This method not only reduces dependence on traditional energy sources but also ensures the operational reliability of local power grids, providing a more efficient and accurate solution for the optimal dispatch of local power grids. This local grid distributed energy storage optimization scheduling based on adjustable load-energy storage aggregation units can better handle integer and continuous variables in the local grid, making the local grid scheduling results more accurate, thereby improving the efficiency of tapping and utilizing the power system's resource regulation potential.

[0078] Step S11: Establish the constraints of the local power grid.

[0079] The current optimization scheduling model (i.e., the objective optimization scheduling model) aims to minimize the operating cost of the local power grid and satisfies a series of constraints, including power balance constraints, node power constraints, node voltage constraints, and branch transmission power constraints, to ensure the safe and stable operation of the local power grid. The construction methods of the aforementioned power balance constraints, node power constraints, node voltage constraints, and branch transmission power constraints are the same as those in the above embodiments, and will not be repeated here.

[0080] Step S15: Establish the objective function of the day-ahead optimization scheduling model. This objective function is used to minimize the operating cost of the local power grid. The construction method of the objective function is the same as in the above embodiment, and will not be repeated here.

[0081] Step S2: Based on the daily rolling update of load data and the first output power of the adjustable load obtained in step S1, the load forecasting model based on dynamic BP neural network is used to perform ultra-short-term forecasting of the adjustable load power to obtain the second output power of the adjustable load.

[0082] To address the uncertainty of the initial output power of adjustable loads within a day, more refined intraday rolling forecasts of adjustable loads are needed to improve the accuracy of the second output power forecast. When performing ultra-short-term forecasts of adjustable loads, a method capable of achieving rapid and accurate short-term forecasts is required. Therefore, a dynamic BP neural network is employed as the load forecasting model to perform rolling forecasts of the second output power of intraday adjustable loads. Figure 3 This is a structural diagram of an optional dynamic BP neural network provided according to an embodiment of this application, such as... Figure 3 As shown, the load prediction model based on the dynamic BP neural network includes an input layer, a correlation layer, a hidden layer, and an output layer. The input layer is used to input load data and a first output power. The correlation layer is used to capture the time series characteristics of the data input to the above input layer. The hidden layer is used to extract information about the load data and the first output power through nonlinear transformation. The output layer is used to output a second output power for the adjustable load.

[0083] Compared to traditional backpropagation (BP) neural networks, dynamic BP neural networks incorporate an additional correlation layer for local feedback. This correlation layer plays a crucial role in the structure of dynamic BP neural networks. Unlike traditional linear functions, the correlation layer introduces a delay unit, enabling it to remember historical states. This design allows the neural network to re-input the output from previous time steps as input, thus achieving dynamic memorization of past information. This memory mechanism allows dynamic BP neural networks to capture and learn patterns and trends in time-series data, which is particularly important for handling time-dependent problems. Specifically, the presence of hidden layers greatly enhances the neural network's ability to process complex data. In tasks such as time series forecasting, there are often inherent temporal correlations between data points, and hidden layers can provide temporal continuity to the network by remembering past calculation results. This continuity allows dynamic BP neural networks to identify long-term dependencies in the data, thus taking these dependencies into account when predicting future values. Furthermore, the introduction of hidden layers also provides the neural network with the ability to perform nonlinear fitting. Without hidden layers, neural networks can only perform linear transformations, limiting their ability to solve nonlinear problems. By introducing nonlinear activation functions, the hidden layer enables the dynamic BP neural network to learn and simulate complex nonlinear relationships, thereby improving the expressive power and prediction accuracy of the load forecasting model.

[0084] Figure 4 This is a schematic diagram of an optional second output power prediction result based on a dynamic BP neural network, according to an embodiment of this application. Figure 4The differences between the predicted second output power of the adjustable load obtained using a dynamic BP neural network and a BP neural network, and the actual value of the second output power of the adjustable load are shown respectively. The blue solid line represents the actual value of the second output power, the red dashed line represents the second output power obtained using the dynamic BP neural network, and the black solid line represents the second output power obtained using the BP neural network. The horizontal axis represents time in hours (h), and the vertical axis represents the second output power in kilowatts (kW). Figure 4 As can be seen from the magnified area, compared with the BP neural network, the error between the second output power obtained by the dynamic BP neural network and the true value of the second output power is smaller. That is, the second output power result obtained by the dynamic BP neural network is more accurate, which shows the superiority of the dynamic BP neural network.

[0085] Step S21: Input the load data of the adjustable load of the local power grid and the first output power into the load prediction model based on the dynamic BP neural network.

[0086] Step S22: In the load prediction model based on dynamic BP neural network, the hidden layer is obtained through the input layer.

[0087] Step S23: In the load prediction model based on dynamic BP neural network, the correlation layer is obtained through the hidden layer.

[0088] Step S24: In the load prediction model based on dynamic BP neural network, the output layer is obtained through the interaction of the correlation layer and the hidden layer, and the prediction result of the adjustable load is output, which is the second output power of the adjustable load.

[0089] Step S3: With the goal of maximizing the target output power of the adjustable load, the improved particle swarm optimization algorithm is used to achieve short-term intraday optimization scheduling, thereby optimizing the second output power of the adjustable load and obtaining the target output power of the adjustable load.

[0090] Intraday short-term optimal scheduling, aiming to maximize the target output power of adjustable loads, aims to achieve efficient utilization of adjustable load resources in a local power grid through an improved particle swarm optimization (PSO) algorithm. This maximizes the utilization of flexibility resources within the local power grid to respond to intraday electricity demand fluctuations and the uncertainty of renewable energy. By optimizing the secondary output power of adjustable loads, reliance on expensive and inefficient frequency regulation services can be reduced, lowering the operating costs of the local power grid while improving its operational stability and reliability. The improved PSO algorithm finds the optimal solution by simulating the social behavior of bird flocks. Compared to the traditional PSO algorithm, the improved algorithm improves convergence speed and global search capability by adjusting parameters and introducing new strategies, thus finding the optimal target output power of adjustable loads more effectively.

[0091] Step S31: Construct a penalty function to characterize the difference between day-ahead optimal scheduling and intraday short-term optimal scheduling.

[0092] In intraday short-term optimal dispatching, the purchased electricity from the upstream grid and the aggregated output of the adjustable load-energy storage aggregation unit should be consistent with the results of day-ahead optimal dispatching. Therefore, a penalty function PF is introduced to ensure consistency between the day-ahead optimal dispatching results (including purchased electricity and aggregated output) and the intraday short-term optimal dispatching results. The determination method of the penalty function PF is the same as in the above embodiment and will not be repeated here.

[0093] Step S32: Construct the fitness function of the improved particle swarm algorithm with the goal of maximizing the output of the adjustable load.

[0094] Intraday short-term optimized dispatch uses the purchased electricity from the upper-level grid and the aggregated output of the adjustable load-energy storage aggregation unit as references, as determined by the day-ahead optimized dispatch. Based on this, the second output power is optimized with the goal of maximizing the target output power of the adjustable load. The determination method of the fitness function f2 of the improved particle swarm algorithm is the same as that in the above embodiment, and will not be repeated here.

[0095] Step S33: Use the improved particle swarm optimization algorithm to achieve intraday short-term optimization scheduling and obtain the target output power of the adjustable load.

[0096] Particle swarm optimization (PSO) is a widely used intelligent optimization technique suitable for solving various complex nonlinear problems. This algorithm generates or pre-sets a series of initial solutions, then performs optimization searches according to specific iterative rules, aiming to make the quality of the solutions as close to the optimum as possible. In PSO, each potential solution is considered a particle, each with a unique velocity and position, and their fitness value is evaluated by a defined fitness function. The fitness score of a particle determines its optimal individual solution (i.e., a local optimum) and the global optimum within the swarm. However, traditional PSO algorithms suffer from slow convergence speed and a tendency to get trapped in local optima. To address these issues, a fast and adaptive improved PSO algorithm is proposed to accelerate convergence and, to some extent, overcome the drawback of obtaining locally optimal results.

[0097] Using the second output power of the adjustable load in the local power grid as the initial solution, an improved particle swarm optimization algorithm is used for optimization to finally obtain the optimal target output power of the adjustable load. The particle velocity update method of the improved particle swarm optimization algorithm is the same as that in the above embodiment, and will not be repeated here.

[0098] In the improved particle swarm optimization (PSO) algorithm, a dynamically adjusted convergence rate β is introduced to achieve a balance between fast convergence and fine-grained search. In the early stages of the search, β is assigned a large value to accelerate the convergence process. As iterations progress, the value of β gradually decreases to achieve a more refined search. Simultaneously, α*R*S is used to expand the search range of the particles, helping them escape local optima and find the global optimum. For infeasible solutions, a penalty function strategy is used to adjust the fitness value of the solution instead of directly eliminating it. These solutions receive higher fitness values ​​after fitness evaluation and are retained for the next iteration. Furthermore, when updating the optimal position of particles, the improved PSO algorithm uses a standard normal distribution and particle bounds to guide the update process, rather than a completely random approach. This helps maintain the fitness of feasible solutions and improves the overall efficiency of the algorithm. Through these adjustments, the improved PSO algorithm can improve the quality of solutions and the robustness of the algorithm while maintaining search efficiency.

[0099] The above-mentioned optional implementation methods achieve at least the following effects: by aggregating adjustable loads and energy storage units into local grid dispatch, the operating cost and complexity of local grid optimization can be reduced; by adopting a dynamic BP neural network-improved particle swarm optimization algorithm, the accuracy of the adjustable load target output power determination result can be improved, resource allocation can be optimized, energy waste can be reduced, and the problem of low local grid operating efficiency caused by improper resource allocation can be avoided; by combining the predictive ability of the dynamic BP neural network with the global search ability of the improved particle swarm optimization algorithm, the dynamics and uncertainties in the local grid can be better handled, the accuracy of the adjustable load target output power determination result can be improved, thereby improving the efficiency of the power system in tapping and utilizing the resource regulation potential of the local grid.

[0100] It should be noted that the steps shown in the flowchart in 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 may be executed in a different order than that shown here.

[0101] This embodiment also provides an adjustable load output power determination device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0102] According to an embodiment of this application, an apparatus embodiment for implementing the method for determining the output power of an adjustable load is also provided. Figure 5This is a schematic diagram of an adjustable load output power determination device according to an embodiment of this application, such as... Figure 5 As shown, the above-mentioned adjustable load output power determination device includes a data acquisition module 502, a first determination module 504, a second determination module 506, and a third determination module 508. The device will be described below.

[0103] The data acquisition module 502 is used to acquire power data of the target power grid;

[0104] The first determining module 504, connected to the data acquisition module 502, is used to determine the purchased electricity, aggregated output, and first output power of the adjustable load of the target power grid based on power data. The aggregated output refers to the output power of the adjustable load-energy storage aggregation unit of the target power grid.

[0105] The second determining module 506, connected to the first determining module 504, is used to determine the second output power of the adjustable load based on the load data of the adjustable load and the first output power in the power data;

[0106] The third determining module 508, connected to the second determining module 506, is used to determine the target output power of the adjustable load based on the purchased electricity, aggregated output power, and the second output power.

[0107] In an embodiment of this application, an adjustable load output power determination device is provided, which includes a data acquisition module 502 for acquiring power data of the target power grid; a first determination module 504, connected to the data acquisition module 502, for determining the purchased electricity, aggregated output, and first output power of the adjustable load of the target power grid based on the power data, wherein the aggregated output refers to the output power of the adjustable load-energy storage aggregation unit of the target power grid; a second determination module 506, connected to the first determination module 504, for determining the second output power of the adjustable load based on the load data and first output power of the adjustable load in the power data; and a third determination module 508, connected to the second determination module 506, for determining the target output power of the adjustable load based on the purchased electricity, aggregated output, and second output power. The goal is to determine the output power and purchased electricity of the adjustable load-energy storage aggregation unit of the target power grid by acquiring the power data of the target power grid, and then determine the target output power of the adjustable load of the target power grid. This achieves the technical effect of improving the accuracy of the determination result of the adjustable load output power in the power grid, and thus solves the technical problem of inaccurate determination result of the adjustable load output power in the power grid in related technologies.

[0108] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0109] It should be noted that the data acquisition module 502, the first determining module 504, the second determining module 506, and the third determining module 508 mentioned above correspond to steps S102 to S108 in the embodiments. The instances and application scenarios implemented by the above modules and their corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in a computer terminal.

[0110] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0111] The aforementioned adjustable load output power determination device may further include a processor and a memory. The data acquisition module 502, the first determination module 504, the second determination module 506, the third determination module 508, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0112] The processor contains a core that retrieves the corresponding program unit from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0113] This application provides a non-volatile storage medium storing a program that, when executed by a processor, implements a method for determining the output power of an adjustable load.

[0114] This application provides an electronic device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring power data of a target power grid; determining, based on the power data, the purchased electricity volume, aggregated output, and a first output power of the adjustable load of the target power grid, wherein the aggregated output refers to the output power of the adjustable load-energy storage aggregation unit of the target power grid; determining, based on the load data of the adjustable load and the first output power in the power data, a second output power of the adjustable load; and determining, based on the purchased electricity volume, aggregated output, and the second output power, a target output power of the adjustable load. The device described herein may be a server, PC, etc.

[0115] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: acquiring power data of a target power grid; determining, based on the power data, the purchased electricity, aggregated output, and a first output power of the adjustable load of the target power grid, wherein the aggregated output refers to the output power of the adjustable load-energy storage aggregation unit of the target power grid; determining, based on the load data of the adjustable load and the first output power in the power data, a second output power of the adjustable load; and determining, based on the purchased electricity, aggregated output, and the second output power, a target output power of the adjustable load.

[0116] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0118] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0119] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxesFigure 1 The steps of the function specified in one or more boxes.

[0120] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0121] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0122] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0123] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0124] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for determining the output power of an adjustable load, characterized in that, include: Acquire power data from the target power grid; Based on the power data, the purchased electricity, aggregated output, and first output power of the adjustable load of the target power grid are determined, wherein the aggregated output refers to the output power of the adjustable load-energy storage aggregation unit of the target power grid; Based on the load data of the adjustable load in the power data and the first output power, the second output power of the adjustable load is determined; Based on the purchased electricity, the aggregated output, and the second output power, the target output power of the adjustable load is determined.

2. The method according to claim 1, characterized in that, The step of determining the purchased electricity, aggregated power output, and first output power of the adjustable load of the target power grid based on the power data includes: Based on the power data, a target optimization scheduling model is used to obtain the purchased power, the aggregated output, and the first output power. The target optimization scheduling model includes an objective function and constraints. The objective function is used to minimize the operating cost of the target power grid. The constraints include the power balance constraints of the target power grid, the node power constraints of the target power grid, the node voltage constraints of the target power grid, and the branch transmission power constraints of the target power grid. A node refers to a specific location in the target power grid that needs to exhibit electrical attributes.

3. The method according to claim 2, characterized in that, The target optimization scheduling model includes: When the purchased electricity includes purchased active power and purchased reactive power, and the aggregated output includes active aggregated output and reactive aggregated output, the objective function is: Where f1 represents the objective function, and T represents the scheduling period. P represents the active power purchase cost of the target power grid at time t. t s This represents the purchased active power of the target power grid at time t. This represents the reactive power purchase cost of the target power grid at time t. This represents the purchased reactive power of the target power grid at time t, where I indicates that there are I nodes. This indicates the output cost of the adjustable load. Let represent the first output power of the adjustable load at the i-th node at time t. This represents the operating cost of charging and discharging the energy storage unit of the target power grid at time t. Let represent the active power output by the energy storage unit at the i-th node at time t. This represents the reactive power output cost of the adjustable load-energy storage aggregation unit of the target power grid at time t. This represents the reactive power aggregation output of the adjustable load-energy storage aggregation unit of the target power grid at time t. P represents the active power output cost of the adjustable load-energy storage aggregation unit of the target power grid at time t. t LES This represents the active power aggregated output of the adjustable load-energy storage aggregation unit of the target power grid at time t; The power balance constraint is: Among them, P d (i,t) represents the active power aggregated by the adjustable load-energy storage aggregation unit at node i at time t, P L (i,t) represents the active load of the adjustable load-energy storage aggregation unit at node i at time t, U(i,t) represents the voltage amplitude at node i at time t, U(j,t) represents the voltage amplitude at node j at time t, and G ij Let θ(ij,t) represent the conductance of line ij consisting of nodes i and j, and let B represent the phase angle difference of line ij. ij Q represents the susceptance of line ij. d (i,t) represents the reactive power aggregation output of the adjustable load-energy storage aggregation unit at node i at time t, Q L (i,t) represents the reactive load of the adjustable load-energy storage aggregation unit at node i at time t, and n represents the number of nodes; The node power constraint is: Among them, P i min and P i max Let Q represent the upper and lower limits of the active power at node i, respectively. i min and Q i max P represents the upper and lower limits of reactive power at node i, respectively. i (t) and Q i (t) represent the active power and reactive power injected at node i at time t, respectively; The node voltage constraint is: U i min ≤U i (t)≤U i max Among them, U i min and U i max U represents the upper and lower voltage limits of node i, respectively. i (t) represents the voltage value at node i at time t; The branch transmission power constraint is: P l ij ≤P l ij max Among them, P l ij P represents the transmission power of line ij. l ij max This represents the upper limit of the transmission power of line ij.

4. The method according to claim 1, characterized in that, The step of determining the second output power of the adjustable load based on the load data of the adjustable load in the power data and the first output power includes: Based on the load data and the first output power, a load prediction model is used to obtain the second output power. The load prediction model includes an input layer, a correlation layer, a hidden layer, and an output layer. The input layer is used to input the load data and the first output power. The correlation layer is used to capture the time series characteristics of the data input to the input layer. The hidden layer is used to extract information about the load data and the first output power through nonlinear transformation. The output layer is used to output the second output power.

5. The method according to any one of claims 1 to 4, characterized in that, Determining the target output power of the adjustable load based on the purchased electricity, the aggregated output power, and the second output power includes: Based on the purchased electricity and the aggregated output, the second output power is optimized using an improved particle swarm optimization algorithm to obtain the target output power, wherein the fitness function of the improved particle swarm optimization algorithm is used to maximize the target output power of the adjustable load; Where f2 represents the fitness function, and PF represents the penalty function. Let represent the target output power of the adjustable load at the i-th node at time t.

6. The method according to claim 5, characterized in that, The method further includes: The improved particle swarm optimization algorithm updates the particle velocity in the following way: in, This represents the position of particle a in the (f+1)th iteration. This represents the position of particle a in the f-th iteration. Let represent the local optimal position of particle a in the f-th iteration, and β represent the convergence rate. Let f represent the global optimal position in the f-th iteration, α represent the random decay factor of the particle, R represent a random value that follows a standard normal distribution, and S represent the boundary of the particle.

7. An adjustable load output power determination device, characterized in that, include: The data acquisition module is used to acquire power data from the target power grid. The first determining module is used to determine the purchased electricity, aggregated output, and first output power of the adjustable load of the target power grid based on the power data, wherein the aggregated output refers to the output power of the adjustable load-energy storage aggregation unit of the target power grid; The second determining module is used to determine the second output power of the adjustable load based on the load data of the adjustable load in the power data and the first output power; The third determining module is used to determine the target output power of the adjustable load based on the purchased electricity, the aggregated output power, and the second output power.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores multiple instructions adapted for loading by a processor and executing the adjustable load output power determination method according to any one of claims 1 to 6.

9. An electronic device, characterized in that, include: One or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the adjustable load output power determination method according to any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the method for determining the output power of an adjustable load as described in any one of claims 1 to 6.

Images