A Grid Planning Method Considering the Energy Consumption Characteristics of Emerging Industries

Abstract

The present invention discloses a grid planning method considering the energy consumption characteristics of emerging industries, which relates to the technical field of grid planning, and includes: identifying the energy consumption characteristics of emerging industries and constructing an energy consumption fluctuation prediction model; solving the energy consumption fluctuation prediction model through a load prediction algorithm to divide the power grid area; configuring an energy storage system based on the power grid area division result; and connecting renewable energy based on the configuration result of the energy storage system. The grid planning method considering the energy consumption characteristics of emerging industries provided by the present invention can accurately capture the law of power grid load fluctuation by constructing a fluctuation prediction model considering the energy consumption characteristics of emerging industries. The present invention overcomes the defect of being unable to adapt to dynamic changes in the traditional method and improves the accuracy and reliability of prediction. The use of a clustering algorithm to optimize the power grid area division can fully consider the differences in energy consumption fluctuation degree and load distribution, ensure that the power grid area division is more scientific and reasonable, and thus improve the regulation ability and stability of the power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of grid planning, and specifically provides a grid planning method considering the energy consumption characteristics of emerging industries. Background Art

[0002] In existing power grid planning, due to the rapid development of emerging industries, the power grid load fluctuations have become increasingly complex. Traditional power grid planning methods usually rely on historical load data and traditional prediction models. Although they can reflect the power grid load change trend to a certain extent, due to the failure to fully consider the characteristics of emerging industries and the energy consumption fluctuations they bring, these methods have certain limitations in dealing with the accuracy of load fluctuations and the power grid regulation ability. The power grid regional division methods in the prior art rely too much on static data, such as geographical information and load distribution, while ignoring the dynamically changing energy consumption fluctuation characteristics, resulting in the regional division unable to accurately reflect the actual load fluctuation situation.

[0003] In addition, the current energy storage system configuration methods often lack precise optimization for the energy consumption demand fluctuations in specific power grid regions, resulting in the unreasonable configuration of energy storage resources and the inability to effectively cope with the impact of peak load fluctuations and renewable energy fluctuations. The renewable energy access ratio optimization methods are usually too simplified and unable to consider the complex interaction between the energy storage system and load fluctuations, resulting in the failure to maximize the use efficiency of renewable energy.

[0004] Therefore, the prior art has certain defects in coping with the energy consumption fluctuations of emerging industries and power grid load regulation, especially in the comprehensive consideration of power grid regional division, energy storage system configuration, and renewable energy access optimization, and is unable to make full use of the energy consumption fluctuation characteristics of emerging industries to improve the power grid regulation ability and stability. Summary of the Invention

[0005] In view of the above problems, the present invention is proposed.

[0006] Therefore, the technical problems solved by the present invention are: the existing power grid planning methods cannot effectively cope with the energy consumption fluctuation problems brought by emerging industries, the unreasonable configuration of energy storage systems, and the low efficiency of renewable energy access.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a grid planning method considering the energy consumption characteristics of emerging industries, including:

[0008] Identifying the energy consumption characteristics of emerging industries and constructing an energy consumption fluctuation prediction model;

[0009] Solving the energy consumption fluctuation prediction model through a load prediction algorithm to divide power grid regions;

[0010] Configuring an energy storage system based on the power grid regional division result;

[0011] Connect renewable energy based on the configuration result of the energy storage system.

[0012] As a preferred solution of the grid planning method considering the energy consumption characteristics of emerging industries according to the present invention, wherein: the building of the energy consumption fluctuation prediction model includes determining the new energy industry categories;

[0013] Define energy consumption characteristic parameters for each industry category at different life cycle stages;

[0014] Collect the energy consumption data of the new energy industry according to the energy consumption characteristic parameters;

[0015] Perform data preprocessing on the collected energy consumption data by using the Z-score normalization method;

[0016] Build an energy consumption fluctuation prediction model by using the preprocessed energy consumption data.

[0017] As a preferred solution of the grid planning method considering the energy consumption characteristics of emerging industries according to the present invention, wherein: the building of the energy consumption fluctuation prediction model includes decomposing the energy consumption data into three parts: trend, seasonality and random fluctuation by using the time series decomposition method, and establishing a dynamic energy consumption fluctuation prediction model by applying the VARMA multivariate autoregressive moving average model.

[0018] As a preferred solution of the grid planning method considering the energy consumption characteristics of emerging industries according to the present invention, wherein: the time series decomposition method is expressed as

[0019]

[0020] wherein, represents the original energy consumption data, the actual value at time t, represents the trend component, which is the long-term change trend of the data, represents the seasonal component, which is the periodic fluctuation that repeats over time in the data, represents the random fluctuation component, that is, the residual part, which is the random fluctuation in the data that cannot be explained by the trend and seasonal patterns;

[0021] The VARMA multivariate autoregressive moving average model is expressed as

[0022]

[0023] wherein, represents the random fluctuation component at the current time t, represents the autoregressive coefficient, represents the moving average coefficient, represents the error term, denotes the autoregressive order, denotes the moving average order.

[0024] As a preferred solution of the grid planning method considering the energy consumption characteristics of emerging industries according to the present invention, wherein: the construction of the energy consumption fluctuation prediction model further includes using the maximum likelihood estimation method for parameter optimization, and by calculating the log-likelihood function and maximizing this function, determining the optimal autoregressive coefficient and moving average coefficient, expressed as,

[0025]

[0026] wherein, denotes the log-likelihood function, denotes the variance of the noise term of the model, denotes the stochastic fluctuation component obtained from the time series decomposition, at the time point value at, denotes the total length of the time series, denoting the total number of data samples;

[0027] Use the quasi-Newton method to optimize the parameters in the maximum likelihood estimation to minimize the log-likelihood function, initialize the parameters, calculate the gradient and Hessian matrix, and use the update rule of the BFGS algorithm for parameter adjustment;

[0028] Use the AIC information criterion to select the optimal autoregressive order and moving average order, expressed as,

[0029] wherein, denotes the maximum value of the log-likelihood function, denotes the number of parameters in the model, parameters including autoregressive coefficients, moving average coefficients, and the variance of the noise term.

[0030] As a preferred solution of the grid planning method considering the energy consumption characteristics of emerging industries according to the present invention, wherein: the division of the power grid area includes calculating the energy consumption demand fluctuation degree of different power grid areas based on the energy consumption data generated by the energy consumption fluctuation prediction model;

[0031] According to the difference in the energy consumption demand fluctuation degree, combined with the geographical information and load distribution of the power grid, adopt the K-means clustering algorithm, and by minimizing the variance of the load fluctuation degree within each area, to determine the division result of the power grid area.

[0032] As a preferred solution of the grid planning method considering the energy consumption characteristics of emerging industries according to the present invention, wherein: the configuration of the energy storage system includes using the particle swarm optimization algorithm to optimize the capacity and distribution of the energy storage system according to the energy consumption demand fluctuation degree of each power grid area and the result of the energy consumption fluctuation prediction model;

[0033] Optimize the energy storage system configuration for each grid area by minimizing the difference between the energy storage demand and the grid load fluctuation.

[0034] As a preferred solution of the grid framework planning method considering the energy consumption characteristics of emerging industries according to the present invention, wherein: the access of renewable energy includes adopting a genetic algorithm to optimize the timing and proportion of renewable energy access based on the energy storage system configuration parameters and the results of the energy consumption fluctuation prediction model;

[0035] Optimize the utilization efficiency of renewable energy by minimizing the grid load fluctuation and maximizing the access proportion of renewable energy.

[0036] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the grid framework planning method considering the energy consumption characteristics of emerging industries as described above are implemented.

[0037] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, the steps of the grid framework planning method considering the energy consumption characteristics of emerging industries as described above are implemented.

[0038] Advantages of the present invention: The grid framework planning method considering the energy consumption characteristics of emerging industries provided by the present invention can accurately capture the law of grid load fluctuation by constructing a fluctuation prediction model considering the energy consumption characteristics of emerging industries, overcomes the defect of being unable to adapt to dynamic changes in the traditional method, and improves the accuracy and reliability of prediction. Using the K-means clustering algorithm to optimize the grid area division can fully consider the differences in energy consumption fluctuation degree and load distribution, ensure that the grid area division is more scientific and reasonable, and thus improve the regulation ability and stability of the grid. Optimize the energy storage system configuration through the particle swarm optimization algorithm, which can achieve the best match between the grid load fluctuation and the energy storage demand, improve the utilization efficiency of the energy storage system, and reduce the waste of energy storage resources. Optimize the access timing and proportion of renewable energy through the genetic algorithm, which can maximize the access proportion of renewable energy while ensuring the minimization of grid load fluctuation, improve the utilization efficiency of renewable energy and the proportion of green energy in the grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1The overall flowchart of a grid planning method considering the energy consumption characteristics of emerging industries provided by an embodiment of the present invention. Detailed implementation manners

[0041] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following will describe the detailed implementation manners of the present invention with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0042] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below. Embodiment

[0043] Refer to Figure 1 , an embodiment of the present invention provides a grid planning method considering the energy consumption characteristics of emerging industries, including:

[0044] Identify the energy consumption characteristics of emerging industries and construct an energy consumption fluctuation prediction model.

[0045] Solve the energy consumption fluctuation prediction model through a load forecasting algorithm and divide the power grid area.

[0046] Configure an energy storage system based on the power grid area division result.

[0047] Connect renewable energy based on the configuration result of the energy storage system.

[0048] Identify key new energy industry categories including solar power generation, wind power generation, electric vehicle manufacturing, energy storage systems, etc.

[0049] Define specific energy consumption characteristic parameters for each industry category at different life cycle stages (start-up period, expansion period, maturity period), including electricity load patterns, fluctuation amplitudes, and time period distributions, to guide subsequent data collection and model construction.

[0050] Real-time collect the energy consumption data of the new energy industries through installed smart meters and data collection devices, including load demand, energy consumption fluctuations, and peak electricity consumption time periods, to ensure that the collected data conforms to the energy consumption characteristic parameters.

[0051] Use the Z-score standardization method to clean and standardize the collected data, remove outliers and noise, and ensure data quality and consistency.

[0052] The energy consumption data is decomposed into three parts: trend, seasonality, and random fluctuations using the time series decomposition method, and a dynamic energy consumption fluctuation prediction model is established by applying the vector autoregressive moving average (VARMA) model to capture the changing trends and fluctuation patterns of energy consumption demand.

[0053] The construction of the energy consumption fluctuation prediction model includes decomposing the energy consumption data into three parts: trend, seasonality, and random fluctuations using the time series decomposition method, and establishing a dynamic energy consumption fluctuation prediction model by applying the VARMA model.

[0054] The time series decomposition method is expressed as

[0055]

[0056] where represents the original energy consumption data, the actual value at time t, represents the trend component, which is the long-term change trend in the data, represents the seasonal component, which is the periodic fluctuation that repeats over time in the data (such as annual cycle, weekly cycle, etc.), represents the random fluctuation component, that is, the residual part, which is the random fluctuation in the data that cannot be explained by the trend and seasonal patterns;

[0057] The VARMA model is expressed as

[0058] where represents the random fluctuation component at the current time t, represents the autoregressive coefficient, represents the moving average coefficient, represents the error term, represents the autoregressive order, represents the moving average order.

[0059] The construction of the energy consumption fluctuation prediction model also includes parameter optimization using the maximum likelihood estimation method. By calculating the log-likelihood function and maximizing this function, the optimal autoregressive coefficients and moving average coefficients are determined, which is expressed as

[0060] where represents the log-likelihood function, represents the variance of the noise term of the model, represents the random fluctuation component obtained from the time series decomposition, the value at the time point t, represents the total length of the time series and the total number of data samples;

[0061] The quasi - Newton method is used to optimize the parameters in the maximum likelihood estimation to minimize the log - likelihood function. Initialize the parameters, calculate the gradient and Hessian matrix, and adjust the parameters using the update rule of the BFGS algorithm;

[0062] The Akaike Information Criterion (AIC) is used to select the optimal autoregressive order and moving average order, denoted as

[0063] where represents the maximum value of the log - likelihood function, represents the number of parameters in the model, , including the parameters of autoregressive coefficients, moving average coefficients, and the variance of the noise term.

[0064] The grid - frame planning method for energy consumption characteristics considering emerging industries proposed by the method of this embodiment, especially aiming at the characteristics of the new - energy industry, adopts the Akaike Information Criterion (AIC) and the quasi - Newton method (BFGS algorithm) to optimize the VARMA (Vector AutoRegressive Moving Average) model, so as to achieve accurate prediction of power demand fluctuations in the new - energy industry and optimization of power - grid planning.

[0065] The energy - consumption data of the new - energy industry has significant seasonality, long - term growth trends, and irregular fluctuations. Traditional linear regression or time - series models often cannot accurately capture these complex characteristics. Therefore, the present invention decomposes the energy - consumption data into three parts: trend, seasonality, and random fluctuations through the time - series decomposition method, and then processes different components respectively. The trend component after time - series decomposition reflects the energy - consumption growth pattern of the new - energy industry on a relatively long time scale, the seasonal component reveals the energy - consumption fluctuations changing with seasons, and the random - fluctuation component reflects unpredictable sudden factors, such as climate change or equipment failures.

[0066] The introduction of the VARMA model is to be able to model the interactions between multiple factors while capturing historical dependencies and random fluctuations. In the new - energy industry, energy - consumption fluctuations are not only affected by a single factor, but are the result of the interaction of multiple factors. These factors include climate conditions, changes in market demand, policy regulation, etc. The multi - variable processing ability of the VARMA model enables it to effectively model these interactions, thereby improving the accuracy of prediction.

[0067] To select the optimal order of the VARMA model, the present invention adopts the Akaike Information Criterion (AIC). AIC can find a balance between model complexity and prediction ability, and avoid overfitting through a penalty term. In the prediction of the new energy power grid, the application of AIC helps to determine the optimal autoregressive order and moving average order of the VARMA model, so that the model can more accurately reflect the changing trend of energy consumption demand.

[0068] Once the order of the model is determined, the present invention uses the quasi-Newton method (BFGS algorithm) to optimize the coefficients in the VARMA model. The BFGS algorithm can quickly find the optimal solution in the multi-dimensional parameter space through an efficient iterative update process. This is crucial for the large-scale energy consumption data in the new energy industry, because these data are often high-dimensional and change rapidly. Through the efficient optimization of the BFGS algorithm, the parameters of the model can converge quickly, thus ensuring the real-time performance and accuracy of the prediction.

[0069] In the maximum likelihood estimation process, the Akaike Information Criterion (AIC) not only is used to select the order of the VARMA model, but also plays an important role in the maximum likelihood estimation. By introducing AIC, it can ensure that the best balance is achieved between the complexity and the goodness of fit of the model when estimating parameters. Specifically, AIC helps to avoid the errors caused by overfitting of the model in the maximum likelihood estimation process through the penalty on the model complexity, thereby improving the prediction ability of the model.

[0070] A significant advantage of this method is its ability to adapt to the characteristics of energy consumption fluctuations in the new energy power grid. The volatility of new energy power generation is relatively strong, and traditional load forecasting methods often cannot effectively handle this kind of volatility. However, through multi-stage modeling, the present invention can not only capture the long-term growth trend, but also accurately simulate short-term seasonal fluctuations and random fluctuations, thus providing a scientific basis for the load dispatching and resource allocation of the power grid.

[0071] In addition, the application of the BFGS algorithm can greatly improve the computational efficiency of optimization. Compared with the traditional gradient descent method, the BFGS algorithm can make more effective use of gradient information in the calculation process, avoid computational bottlenecks, and can quickly obtain the optimal solution when facing large-scale data. This enables the present invention to maintain high real-time performance and accuracy when facing the high-frequency and dynamically changing energy consumption data in the new energy power grid.

[0072] In summary, by combining the Akaike Information Criterion (AIC) and the quasi - Newton method (BFGS algorithm), the present invention optimizes the VARMA model and can effectively address the challenges of predicting energy consumption fluctuations in the new energy industry. Through the combination of time - series decomposition and the VARMA model, the present invention can capture various components of energy consumption fluctuations in the new energy industry and consider the interaction of various factors during the optimization process, thereby providing accurate energy consumption predictions and reasonable load dispatching suggestions for power grid planning. This method not only has high theoretical value but also has strong practical application prospects and can provide strong support for load management, resource allocation, and stability of the new energy power grid.

[0073] Specifically, for the collected energy consumption data, the Z - score standardization method is used to convert the data into standardized values to eliminate the deviation between different dimensions and ensure the unity of the data. The Z - score standardization formula is as follows:

[0074]

[0075] where, represents the standardized energy consumption data, represents the original energy consumption data, the value at time point . represents the sample mean, indicating the central position of the data, represents the sample standard deviation, measuring the degree of data fluctuation. Specifically, the maximum likelihood estimation (MLE) method is used to estimate the model parameters and Then, optimization is carried out through the quasi - Newton method (BFGS algorithm) to minimize the log - likelihood function. The specific steps are as follows:

[0076] Initialize the model parameters

[0077] Calculate the initial log - likelihood function

[0078] Calculate the gradient and the Hessian matrix:

[0079] where, represents the gradient of the log - likelihood function, the partial derivative of the log - likelihood function with respect to the model parameters, represents the autoregressive coefficient, indicating the relationship with the historical values (autoregressive terms). In the model, is used to describe the impact of the energy consumption data at the previous time points on the current time point, represents the moving average coefficient, indicating the relationship with the error term (noise term). is used to capture the past The impact of the error at a moment on the current moment, represents the partial derivative of the log-likelihood function with respect to the autoregressive coefficient , indicating the degree of influence of the autoregressive coefficient on the value of the log-likelihood function, represents the partial derivative of the log-likelihood function with respect to the moving average coefficient , indicating the degree of influence of the moving average coefficient on the value of the log-likelihood function, represents the Hessian matrix, which is the second derivative matrix of the log-likelihood function and describes the mutual influence between each pair of parameters (e.g., and ), represents the second partial derivative of the log-likelihood function with respect to and , indicating the second-order influence of the autoregressive coefficients and on the log-likelihood function, represents the autoregressive coefficients, which are two parameters in the autoregressive part of the model.

[0080] Gradient is the partial derivative of the log-likelihood function with respect to each parameter, while the Hessian matrix represents the second derivative and is used to capture the curvature of the curve.

[0081] In each iteration, the update rule of the BFGS algorithm is used to adjust the parameters:

[0082] where, represents the parameter vector in the th iteration, representing all the parameters of the model at the current iteration step, including and parameters such as the variance of the noise term, represents the step size, which is the size of the update in each iteration and is usually calculated by a line search algorithm to minimize the log-likelihood function for each step, represents the Hessian matrix, which is the second derivative matrix at the current iteration step and is used to adjust the direction and step size of the gradient, represents the gradient at the current iteration, which is the partial derivative of the current parameters with respect to the log-likelihood function, represents the updated parameter in the th iteration.

[0083] Repeat the above steps until the log-likelihood function converges to the maximum value, that is, find the optimal parameters and In maximum likelihood estimation, optimize the autoregressive coefficients and the moving average coefficients And update the model parameters by the quasi - Newton method, and finally use AIC to select the optimal order.

[0084] Initialize parameters: In the initial iteration, set the autoregressive order and the moving average order and initialize all coefficients and

[0085] Calculate the gradient and Hessian matrix: According to the log - likelihood function and the current parameter values, calculate the gradient and Hessian matrix, which represent the influence on the parameters.

[0086] Parameter update: Use the BFGS algorithm to update the parameters and continue the iteration until the log - likelihood function converges.

[0087] AIC selects the optimal model: By minimizing the AIC value, select the optimal order and Finally determine the model parameters.

[0088] The divided power grid regions include calculating the energy demand volatility of different power grid regions based on the energy consumption data generated by the energy consumption fluctuation prediction model; according to the differences in the energy demand volatility, combined with the geographical information and load distribution of the power grid, using the K - means clustering algorithm, and determining the division result of the power grid regions by minimizing the variance of the load volatility within each region.

[0089] Specifically, the goal of power grid region division is to identify the load fluctuation patterns in different regions based on the energy consumption data generated by the energy consumption fluctuation prediction model, and then reasonably divide the power grid regions to ensure that the subsequent energy storage system configuration and renewable energy access can be optimized more effectively. In this process, first calculate the load volatility of each region through the energy consumption fluctuation prediction model, and this index reflects the amplitude of the power grid load changing over time. To describe the load volatility, define this index as the fluctuation amplitude of the load in each region within a certain time window, and the calculation formula is as follows:

[0090] Among them, is the load volatility of region , is the actual load value of region at time point , is the load prediction value, is the time window size, representing the calculation period of the load fluctuation.

[0091] Using these fluctuation data, by combining the geographical information and load distribution of the power grid, the K-means clustering algorithm is adopted for regional division. The K-means algorithm is a distance-based clustering algorithm, aiming to divide the power grid into several regions with similar load fluctuation characteristics by minimizing the variance of the load fluctuation degree within each cluster. The steps are as follows:

[0092] Initialize cluster centers: Randomly select initial cluster centers, and each cluster corresponds to a preliminary division of a power grid region.

[0093] Calculate the load fluctuation degree: Based on the historical load data of each region, calculate the load fluctuation degree ( ).

[0094] Assign regions to clusters: Assign each power grid region to the nearest cluster center, and calculate the variance of the load fluctuation degree within the cluster.

[0095] Update cluster centers: Calculate the mean value of the load fluctuation degree of all regions within each cluster, and update this mean value as the new cluster center.

[0096] Iterative update: Repeat steps 3 and 4 until the variance of the load fluctuation degree converges.

[0097] The configured energy storage system includes adopting the particle swarm optimization algorithm to optimize the capacity and distribution of the energy storage system according to the energy consumption demand fluctuation degree of each power grid region and the result of the energy consumption fluctuation prediction model; by minimizing the difference between the energy storage demand and the power grid load fluctuation, the energy storage system configuration of each power grid region is optimized, thereby enhancing the load regulation ability and reducing the power grid load fluctuation.

[0098] Specifically, after completing the power grid regional division, the next step is to optimize the energy storage system configuration according to the energy consumption demand fluctuation degree of each power grid region and the result of the energy consumption fluctuation prediction model. This step is crucial because a reasonable energy storage configuration can effectively enhance the power grid load regulation ability and reduce the impact of load fluctuation on the power grid stability.

[0099] The particle swarm optimization algorithm is the core algorithm for optimizing the energy storage system capacity and distribution. PSO simulates the foraging behavior of bird flocks and relies on the position and velocity of particles to search the solution space. Using the PSO algorithm to minimize the difference between the energy storage demand and the power grid load fluctuation, its optimization goal is to reduce the fluctuation amplitude of the power grid by configuring an appropriate energy storage capacity. The optimization process includes the following steps:

[0100] Initialize the particle swarm: Initialize multiple particles for each power grid region. The position of the particle represents the capacity of the energy storage system, while the velocity controls the adjustment direction and amplitude of the energy storage capacity.

[0101] Fitness evaluation: For each particle, calculate its fitness value, which is determined by the change in the grid load fluctuation degree. The fitness function is expressed as:

[0102]

[0103] where, is the load fluctuation degree of region , is the load fluctuation degree after the optimization of the energy storage system. The goal is to minimize this difference. is the number of grid regions.

[0104] Particle update: Update the velocity and position of the particle according to the fitness value. The position of the particle represents the optimized configuration of the energy storage system.

[0105] Termination condition: When the fitness of the particle reaches the preset optimal level or after multiple iterations, the algorithm ends and returns the final optimized result.

[0106] The access to renewable energy includes optimizing the timing and proportion of renewable energy access by using a genetic algorithm based on the configuration parameters of the energy storage system and the results of the energy consumption fluctuation prediction model; by minimizing the grid load fluctuation and maximizing the proportion of renewable energy access, the utilization efficiency of renewable energy is optimized, and the stability and sustainability of the grid are further improved.

[0107] Specifically, after the energy storage system is configured, the next task is to optimize the timing and proportion of renewable energy access. The access to renewable energy can not only improve the sustainability of the grid but also reduce the dependence on traditional energy. However, excessive access to renewable energy may exacerbate the load fluctuation, so scientific optimization is needed.

[0108] The genetic algorithm is an optimization algorithm that mimics the biological evolution process and is used to optimize the timing and proportion of renewable energy access. The genetic algorithm is based on operations such as selection, crossover, and mutation, and gradually approaches the optimal solution. The specific steps are as follows:

[0109] Initialize the population: Randomly generate a set of combinations of the timing and proportion of renewable energy access. Each individual in the population represents an access scheme.

[0110] Fitness evaluation: Calculate the fitness of each scheme. The goal of the fitness function is to minimize the grid load fluctuation and maximize the proportion of renewable energy access. The fitness function is expressed as:

[0111] where, is the proportion of renewable energy access in region , is a weight coefficient used to balance the relationship between minimizing load fluctuations and maximizing renewable energy.

[0112] Selection, crossover, and mutation: Through the selection operation, individuals with better fitness are selected from the population. The crossover operation generates new individuals, and the mutation operation increases the diversity of the population.

[0113] Termination condition: When the fitness reaches the predetermined optimal value or after a sufficient number of generations, the algorithm ends and returns the optimal renewable energy access plan.

[0114] In the aspect of optimizing grid load regulation and renewable energy access, the method of this embodiment provides a more accurate and efficient grid planning method by innovatively combining the energy consumption fluctuation prediction model and various intelligent optimization algorithms. Compared with traditional methods, the present invention can fully consider the load fluctuation characteristics of the grid area, reasonably divide the grid area, optimize the configuration of the energy storage system, and improve the access efficiency of renewable energy, thereby enhancing the stability of the grid while reducing the operating cost and environmental impact of the grid.

[0115] Traditional grid area division methods often only rely on the geographical information of the grid or static analysis of the load, ignoring the dynamic characteristics of energy consumption fluctuations. This division method cannot reflect the actual situation of grid load fluctuations, resulting in insufficient grid load regulation ability and inability to maintain system stability under large load fluctuations. In contrast, the present invention calculates the volatility of the grid area through the load volatility data generated by the energy consumption fluctuation prediction model and uses the K-means clustering algorithm to divide the grid into regions. The advantage of this method is that it can dynamically divide the grid area through accurate load volatility data, minimize the load fluctuations within the region to the greatest extent, and thus achieve more precise load regulation and grid optimization. This method not only ensures the smoothness of the load in each grid area but also provides a more reasonable basis for the subsequent configuration of the energy storage system.

[0116] In terms of the configuration of the energy storage system, traditional methods usually determine the energy storage capacity and layout based on the peak and valley values of the load or simple empirical rules, often resulting in over-configuration or under-configuration problems. This method lacks a detailed analysis of the load fluctuation characteristics of the grid, leading to the inability to maximize the efficiency of the energy storage system and even possible waste of resources. The present invention precisely optimizes the capacity and layout of the energy storage system through the particle swarm optimization algorithm, combined with the load volatility of each grid area and the results of the energy consumption fluctuation prediction model. The introduction of the particle swarm optimization algorithm enables the configuration of the energy storage system to be optimized globally, effectively enhancing the load regulation ability of the energy storage system, reducing the fluctuations of the grid, and lowering the investment and operating costs.

[0117] For the access of renewable energy, traditional methods usually only consider the impact of load fluctuations to a certain extent and often rely on static load balancing models. In the case of large grid load fluctuations, this method cannot fully utilize the power generation capacity of renewable energy and may even lead to excessive waste of renewable energy. The present invention dynamically optimizes the access timing and proportion of renewable energy through a genetic algorithm based on the results of an energy storage system configuration and an energy consumption fluctuation prediction model. The genetic algorithm can comprehensively consider grid load fluctuations and the access benefits of renewable energy to ensure that the access proportion of renewable energy is increased without increasing grid load fluctuations. This optimization process effectively improves the utilization efficiency of renewable energy, reduces the potential risks brought by grid fluctuations, and ensures the stable operation of the grid.

[0118] Embodiment 2

[0119] An embodiment of the present invention, which is different from the previous embodiment in that:

[0120] If the described function 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 such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0121] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0122] More specific examples (nonexhaustive list) of computer-readable media include the following: electrical connections (electronic devices) having one or more wirings, portable computer diskettes (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber devices, and portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0123] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0124] Embodiment 3

[0125] For an embodiment of the present invention, a grid planning method considering the energy consumption characteristics of emerging industries is provided. To verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0126] This experiment was conducted in a simulated medium-sized urban power grid environment. The power grid was divided into 10 regions, and each region represented the energy consumption characteristics of a typical emerging industry, such as electric vehicle charging, intelligent manufacturing, photovoltaic power generation, etc. The energy consumption data for each region was from actual collected load fluctuation data, covering multiple time periods, and the specific data sources included the electricity load data for the past year. To ensure the authenticity and operability of the experiment, the experiment used the MATLAB and Python platforms for simulation. The experimental environment simulated the operating conditions of the power grid under high load seasons, low load seasons, and large load fluctuations.

[0127] Traditional methods mainly rely on grid geographical information, load density, and historical load data to conduct grid area division, energy storage system configuration, and renewable energy access. The experiment first divides the grid areas through the grid's geographical information and the historical load data of each grid area. Traditional methods use a fixed load density threshold to partition the grid according to the level of load. Each divided area does not fully consider the differences in energy consumption fluctuations, resulting in areas with relatively large fluctuations possibly being divided into the same area, leading to low scheduling efficiency. Next, traditional methods configure energy storage systems for each grid area. The energy storage capacity configuration is usually allocated according to a certain proportion (10%) of the total grid capacity, ignoring the differences in energy consumption fluctuation characteristics between regions. Finally, at the stage of renewable energy access, traditional methods usually set a fixed renewable energy access ratio (each area is fixed to access 30% of renewable energy), without optimizing according to grid load fluctuations and energy storage system configuration, which may result in low utilization rate of renewable energy in some areas and increased grid fluctuations.

[0128] The method of the present invention first divides the grid areas and analyzes and predicts the energy consumption fluctuation characteristics of each area by constructing an energy consumption fluctuation prediction model. Specifically, the VARMA (Vector Auto-Regressive Moving Average) multi-variable autoregressive moving average model is used to analyze the energy consumption data of the grid areas, decompose the trend, seasonal, and random fluctuation components, and optimize the model parameters through maximum likelihood estimation and the quasi-Newton method (BFGS) to ensure the accuracy of the model. On this basis, the K-means clustering algorithm is combined with the load fluctuation degree, geographical information, and load distribution to accurately divide the grid areas. The load fluctuation degree of each area is obtained from the output results of the energy consumption fluctuation prediction model. After division, the load fluctuation characteristics of each area are ensured to be consistent, minimizing the risk brought by grid load fluctuations.

[0129] At the stage of energy storage system configuration, based on the load fluctuation degree and energy consumption fluctuation prediction results of each area, the particle swarm optimization algorithm (PSO) is used to dynamically adjust the capacity and distribution of the energy storage system, and the configuration of the energy storage system in each area is optimized by minimizing the difference between the energy storage demand and grid load fluctuations. Finally, at the stage of renewable energy access, based on the configuration of the energy storage system and the output of the energy consumption fluctuation prediction model, the genetic algorithm (GA) is used to optimize the timing and proportion of renewable energy access, ensuring the stability and sustainable operation of the grid by maximizing the utilization efficiency of renewable energy and minimizing grid load fluctuations. The experimental results are shown in Table 1.

[0130] Table 1 Comparison Table of Experimental Results

[0131] Index The method of the present invention Traditional method Standard deviation of load fluctuation degree of regional division 0.12 0.23 Configuration efficiency of energy storage system 85% 65% Renewable energy access ratio 40% 30% Grid load balance error 3% 8% Renewable energy utilization efficiency 90% 70% Configuration accuracy of energy storage system capacity High Low

[0132] By comparing the data in the table, first, when dividing the power grid area, the method of the present invention accurately calculates the load fluctuation degree through the energy consumption fluctuation prediction model, thereby obtaining a more accurate area division result. Compared with the traditional method, the method of the present invention can significantly reduce the difference in load fluctuation degree between regions and improve the efficiency of power grid dispatching.

[0133] Secondly, in terms of the configuration of the energy storage system, the traditional method configures the energy storage capacity at a fixed ratio and fails to fully consider the load fluctuation characteristics of each region, resulting in low energy storage efficiency. In contrast, the method of the present invention dynamically adjusts according to the specific needs of each region through the particle swarm optimization algorithm, making the capacity and distribution of the energy storage system more in line with the actual load fluctuation requirements of the power grid, and the energy storage efficiency is increased by 20%.

[0134] In terms of the access of renewable energy, the traditional method adopts a fixed ratio access method and fails to optimize according to the power grid load fluctuation, resulting in low utilization rate of renewable energy in some regions. After optimizing the access time and ratio through the genetic algorithm, the method of the present invention successfully increases the access ratio of renewable energy in the power grid, effectively reduces the load fluctuation, and improves the utilization efficiency of renewable energy.

[0135] Finally, through the comparison of the power grid load balance error in the experiment, the load regulation error of the method of the present invention is only 3%, while that of the traditional method is 8%. The method of the present invention can adjust the power grid load more accurately, reduce the power grid fluctuation, and thus improve the stability and reliability of the power grid.

[0136] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0137] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0138] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A grid planning method considering the energy consumption characteristics of emerging industries, characterized in that: include: Identify the energy consumption characteristics of emerging industries and build energy consumption fluctuation prediction models; Solve the energy fluctuation prediction model through the load prediction algorithm, and divide the power grid area based on the model prediction results of the energy fluctuation prediction model; Based on the grid area division result, configure an energy storage system; Based on the configuration result of the energy storage system, access to renewable energy; The construction of the energy consumption fluctuation prediction model also includes using a time series decomposition method to decompose the energy consumption data into three parts: trend, seasonality and random fluctuation, and applying a VARMA multivariate autoregressive moving average model to establish a dynamic energy consumption fluctuation prediction model; The time series decomposition method is expressed as, ； in, Represents the original energy consumption data, at time The actual value of the moment, Represents the trend component, which is the medium- and long-term trend of data. represents the seasonal component, which is the periodic fluctuation in the data that repeats over time. Represents the random fluctuation component, i.e., the residual part, which is the random fluctuation in the data that cannot be explained by the trend and seasonal patterns; The VARMA multivariate autoregressive moving average model is expressed as, ； in, represents the autoregressive coefficient, represents the moving average coefficient, represents the error term, represents the autoregressive order, represents the moving average order; The energy consumption fluctuation prediction model is constructed by using the maximum likelihood estimation method to optimize parameters, and the optimal autoregressive coefficient and moving average coefficient are determined by calculating the log-likelihood function and maximizing the function, which is expressed as: ； in, represents the log-likelihood function, The variance of the noise term of the model Indicates the total length of the time series, indicating the total number of samples of the data; Use the quasi-Newton method to optimize the parameters in the maximum likelihood estimation to minimize the log-likelihood function, initialize the parameters, calculate the gradient and Hessian matrix, and use the quasi-Newton method's update rule to adjust the parameters; The AIC information criterion is used to select the optimal autoregressive order and moving average order, expressed as, ； in, represents the maximum value of the log-likelihood function, represents the number of parameters in the model, , where 1 represents the variance of the noise term.

2. The grid planning method considering the energy consumption characteristics of emerging industries as claimed in claim 1 is characterized by: The construction of the energy consumption fluctuation prediction model includes defining energy consumption characteristic parameters for each industry category at different life cycle stages; Collecting energy consumption data of the new energy industry based on the energy consumption characteristic parameters; The Z-score standardization method is used to preprocess the collected energy consumption data; The energy consumption fluctuation prediction model is constructed using the preprocessed energy consumption data.

3. The grid planning method considering the energy consumption characteristics of emerging industries as claimed in claim 2 is characterized by: The dividing of the power grid regions includes calculating the energy demand fluctuation of different power grid regions based on the energy consumption data generated by the energy consumption fluctuation prediction model; According to the difference in energy demand fluctuation, combined with the geographical information and load distribution of the power grid, the K-means clustering algorithm is used to determine the division result of the power grid area by minimizing the variance of the load fluctuation in each area.

4. The grid planning method considering the energy consumption characteristics of emerging industries as claimed in claim 3 is characterized by: The configuring of the energy storage system includes optimizing the capacity and distribution of the energy storage system using a particle swarm optimization algorithm according to the energy demand fluctuation of each power grid area and the result of the energy fluctuation prediction model; The energy storage system configuration for each grid area is optimized by minimizing the difference between energy storage demand and grid load fluctuations.

5. The grid planning method considering the energy consumption characteristics of emerging industries as claimed in claim 4 is characterized by: The access to renewable energy includes optimizing the timing and proportion of renewable energy access using a genetic algorithm based on the configuration parameters of the energy storage system and the results of the energy fluctuation prediction model; Optimize the efficiency of renewable energy use by minimizing grid load fluctuations and maximizing the proportion of renewable energy access.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the grid planning method considering the energy consumption characteristics of emerging industries described in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the grid planning method considering the energy consumption characteristics of emerging industries described in any one of claims 1 to 5 are implemented.

Images