A method for intelligent prediction of power load based on big data

Abstract

The present application relates to the field of power forecasting technology and provides a method for intelligent power load forecasting based on big data, characterized by comprising the following steps: S10: obtaining historical power load records and historical power behavior records of each power user in a region; S20: establishing a power probability model based on the historical power behavior records; S30: establishing a power load forecasting model based on the power probability model; S40: identifying parameters of the power probability model and the power load forecasting model based on the historical power behavior records; S50: inputting the historical power load records into the power load forecasting model to output a power load forecast value. The present application achieves intelligent power load forecasting by establishing a power probability model and a load forecasting model and identifying their respective parameters.

Description

Technical Field

[0001] The present invention belongs to the technical field of power forecasting, and in particular relates to an intelligent power load forecasting method based on big data. Background Art

[0002] In modern power systems, power load forecasting is a crucial task. Accurate load forecasting can help power companies optimize resource allocation, improve power supply reliability, and reduce operating costs. Traditional power load forecasting methods are mostly based on empirical rules or simple statistical analysis, and usually rely on linear regression or time series models of historical data. These methods are inadequate when dealing with complex nonlinear relationships, seasonal changes, and emergencies.

[0003] In addition, as the complexity of power load forecasting models increases, parameter selection and optimization become more difficult, which can easily lead to overfitting. In particular, traditional methods do not consider the impact of different types of days due to parameter selection and optimization, and are unable to better capture the changes in electricity consumption behavior in different time periods, resulting in low accuracy of the forecasting model. Summary of the Invention

[0004] In view of the above-mentioned defects of the prior art, the present invention proposes a method for intelligent power load prediction based on big data. The technical solution designed by the present invention includes the following steps:

[0005] S10: Obtain historical power load records and historical power behavior records of each power user in the region;

[0006] S20: Establish a power probability model based on historical power behavior records;

[0007] S30: establishing a power load forecasting model based on the power probability model;

[0008] S40: Identifying parameters of a power probability model and parameters of a power load forecasting model based on historical power behavior records;

[0009] S50: Input historical power load records into the power load forecasting model to output a power load forecast value.

[0010] Preferably, the S20 includes:

[0011] The component functions of the power probability model are defined based on historical power behavior records, including weekday component functions and holiday component functions. The formula is as follows:

[0012]

[0013] Where, f WD，n (x k |d n , en ) is the working day component function, f HD，n (c|d n , e n ) is the holiday component function, d n is the logarithmic expectation of the nth component function, e n is the standard deviation of the nth component function, x k is the observed value of power consumption.

[0014] Preferably, the S30 includes:

[0015] The power load of each power user in the region is weighted and summed, based on the dependent parameter a represented by the distribution. n d n and e n The power probability model is used to construct the overall power load forecasting model. The formula is as follows:

[0016]

[0017] t g，m ∈T=[t g，1 , t g，2 ,…,t g，M ]~f A (a n , d n , e n )

[0018] Where, f B (x k ) is the power load forecasting model, P m (x k ) is the power load of the electricity user, M is the number of electricity users, is the average total power of the electricity consumption unit, is the total electricity consumption time average of the electricity consumption units, f is the electricity consumption time sequence of each electricity consumption unit in the region, and ~f A (a n , d n , e n ) is the dependent parameter a of the distribution representation n d n and e n The power probability model.

[0019] Preferably, the parameters for identifying the power probability model in S40 include:

[0020] The expectation and maximization processing of the holiday component function, and then the expectation and maximization processing of the weekday component function are used as a calculation process. By repeating the iterative calculation process until convergence, the parameter a of the power probability model of the local optimal solution is obtained. n dn and e n .

[0021] Preferably, the holiday component function is subjected to expectation processing and maximization processing, and the formula is as follows:

[0022]

[0023] Where, Expect k，n is the expectation of the holiday component function, Maximize is the maximization of the holiday component function, and K is the total amount of data to obtain the optimal solution parameters.

[0024] Preferably, the working day component function is subjected to expectation processing and maximization processing, and the formula is as follows:

[0025]

[0026] Where, Expect k,n ′ is the expectation of the workday composition function, and Maximize′ is the maximization of the workday composition function.

[0027] Preferably, the parameters of the power load forecasting model identified in S40 include:

[0028] Build the iterative parameter matrix and output f B (x k ) function, establish the position search of the scout, follower and predator, continuously update the position of the iterative parameter matrix and output the corresponding f B (x k ) function, find the best iterative parameter combination and determine the parameters of the power load forecasting model and M;

[0029] The iterative parameter matrix is ​​established and output f B (x k ) functions include:

[0030]

[0031] Where Matrix(v) is the iteration parameter matrix, f B (x k ), Parameters for the first set of iterations and M, V are the maximum number of iterations.

[0032] Preferably, the scout's position search formula is as follows:

[0033]

[0034] Where, is the scout's position after the search, is the position of the scout before the search, β is a uniform random number in [0, 1], γ represents the predator as a random number in [0, 1], δ is a standard normal random number, and Warn is the warning value of the scout when it finds a predator.

[0035] Preferably, the follower's position search formula is as follows:

[0036]

[0037] Where, is the follower position after searching, is the follower's position before the search, The iterative parameter position with the worst optimization effect in the current search, It is the iterative parameter position with the best optimization effect in the current search, and ε is a random number in [0, 1].

[0038] Preferably, the predator's position search formula is as follows:

[0039]

[0040] Where, is the predator's position after searching, is the predator's position before searching, f is the current search B (x k ) function, f best is the optimal f B (x k ) function, f worst The worst f B (x k ) function, θ is the standard normal distribution number, and σ is |-1, 1|.

[0041] Beneficial effects:

[0042] 1. By processing weekday and holiday components separately, the model can better capture changes in electricity consumption patterns and significantly improve the accuracy of power load forecasting;

[0043] 2. This application adopts the method of expectation maximization processing and iterative calculation to better estimate the parameters of the power probability model, thereby improving the stability and robustness of the model;

[0044] 3. By establishing a parameter matrix and dynamically updating it, the model can quickly adapt to real-time data changes, ensuring the prediction effect in different seasons, holidays and emergencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0046] The embodiments of the present invention are described in detail below. The following embodiments are implemented based on the technical solutions of the present invention, and provide detailed implementation methods and specific operating procedures. However, the protection scope of the present invention is not limited to the following embodiments.

[0047] This paper designs a method for intelligent prediction of power load based on big data, such as Figure 1 As shown, the technical solution includes the following steps, specifically including:

[0048] S10: Obtain historical power load records and historical power behavior records of each power user in the region;

[0049] S20: Establish a power probability model based on historical power behavior records;

[0050] S30: establishing a power load forecasting model based on the power probability model;

[0051] S40: Identifying parameters of a power probability model and parameters of a power load forecasting model based on historical power behavior records;

[0052] S50: Input historical power load records into the power load forecasting model to output a power load forecast value.

[0053] Specifically, historical power load records are data on actual power consumption by power users during a certain period of time;

[0054] Historical electricity behavior records are users' electricity usage behavior pattern data, including but not limited to electricity usage habits during peak hours, the impact of specific events (such as holidays and weather changes) on electricity usage, and the types of users' electrical equipment and usage frequency.

[0055] Preferably, S20 includes:

[0056] The component functions of the power probability model are defined based on historical power behavior records, including weekday component functions and holiday component functions. The formula is as follows:

[0057]

[0058] Where, f WD，n (x k |d n , e n ) is the working day component function, f HD，n (c|d n , e n ) is the holiday component function, d nis the logarithmic expectation of the nth component function, e n is the standard deviation of the nth component function, x k is the observed value of power consumption.

[0059] Specifically, the formula of the power probability model is as follows:

[0060]

[0061]

[0062] Where, f A (x k ) is the power probability model, N is f A The number of component functions in (x), a n f A (x k ) is the weight of the nth component function, f n (x|b n ) is f A The nth component function in (c), b n f A (x k ) in the component functions.

[0063] In addition, d n is the logarithmic expectation of the nth component function, reflecting the central tendency of electricity consumption (logarithmic form), e n is the standard deviation of the nth component function, reflecting the dispersion of power consumption data, x k is the observed value of electricity consumption. Note that when it is in the weekday component function, it represents weekday electricity usage; when it is in the holiday component function, it represents holiday electricity usage. Without restrictions on weekday and holiday electricity behavior, the observed value represents total electricity usage. By leveraging the differences in electricity behavior between weekdays and holidays, a power probability model is established to predict electricity demand.

[0064] Preferably, S30 includes:

[0065] The power load of each power user in the region is weighted and summed, based on the dependent parameter a represented by the distribution. n d n and e n The power probability model is used to construct the overall power load forecasting model. The formula is as follows:

[0066]

[0067] Where, f B (x k ) is the power load forecasting model, P m (xk ) is the power load of the electricity user, M is the number of electricity users, is the average total power of the electricity consumption unit, is the total electricity consumption time average of the electricity consumption units, T is the electricity consumption time sequence of each electricity consumption unit in the region, and ~f A (a n , d n , e n ) is the dependent parameter a of the distribution representation n d n and e n The power probability model.

[0068] Specifically, according to the power load forecasting model formula, the parameters that need to be determined are M、a n d n and e n As training progresses, the parameters of the power probability model and the power load forecasting model change accordingly. Due to the rapid growth of data and the real-time interactive nature of the model, this solution enables online updates of the parameters of the power load forecasting model and the power probability model by accessing the data interface. Given the significant differences in usage patterns between the weekday component function and the holiday component function, two independent models are used to determine their respective update frequencies, allowing for independent and alternating adjustment of the corresponding parameters.

[0069] Preferably, the parameters for identifying the power probability model in S40 include:

[0070] The expectation and maximization processing of the holiday component function, and then the expectation and maximization processing of the weekday component function are used as a calculation process. By repeating the iterative calculation process until convergence, the parameter a of the power probability model of the local optimal solution is obtained. n d n and e n .

[0071] Preferably, the holiday component function is subjected to expectation processing and maximization processing, and the formula is as follows:

[0072]

[0073] Where, Expect k，n is the expectation of the holiday component function, Maximize is the maximization of the holiday component function, and K is the total amount of data to obtain the optimal solution parameters.

[0074] Preferably, the working day component function is subjected to expectation processing and maximization processing, and the formula is as follows:

[0075]

[0076] Where, Expect k，n ′ is the expectation of the workday composition function, and Maximize′ is the maximization of the workday composition function.

[0077] Specifically, the expected value of the holiday component function for power load is calculated, which helps to assess the expected level of power demand in a specific time period. The optimization algorithm is then used to find the parameters that maximize the expected value. This process helps determine the model parameters that best explain the load behavior under given data. This process is repeated, and the parameters are updated multiple times to gradually approach the optimal solution until convergence, resulting in the optimal power probability model parameters a. n d n and e n , which in disguise determines the parameters of the final power load forecasting model, and for the other parameters of the power load forecasting model and M, according to the following step S40, by establishing an iterative parameter matrix, output f B (x k ) function, searches according to the positions of the scout, follower, and predator, iteratively updates the position of the parameter matrix and outputs the corresponding f B (x k ) function, find the best combination of iterative parameters, that is, to determine the parameters and M.

[0078] Preferably, the parameters of the power load forecasting model identified in S40 include:

[0079] Build the iterative parameter matrix and output f B (x k ) function, establish the position search of the scout, follower and predator, continuously update the position of the iterative parameter matrix and output the corresponding f B (x k ) function, find the best iterative parameter combination and determine the parameters of the power load forecasting model and M;

[0080] Build the iterative parameter matrix and output f B (x k ) functions include:

[0081]

[0082] Where Matrix(v) is the iteration parameter matrix, f B (x k ), Parameters for the first set of iterations and M, V are the maximum number of iterations.

[0083] Preferably, the scout's position search formula is as follows:

[0084]

[0085] Where, is the scout's position after the search, is the position of the scout before the search, β is a uniform random number in [0, 1], γ represents the predator as a random number in [0, 1], δ is a standard normal random number, and Warn is the warning value of the scout when it finds a predator.

[0086] Preferably, the follower's position search formula is as follows:

[0087]

[0088] Where, is the follower position after searching, is the follower's position before the search, The iterative parameter position with the worst optimization effect in the current search, It is the iterative parameter position with the best optimization effect in the current search, and ε is a random number in [0, 1].

[0089] Preferably, the predator's position search formula is as follows:

[0090]

[0091] Where, is the predator's position after searching, is the predator's position before searching, f is the current search B (x k ) function, f best is the optimal f B (x k ) function, f worst The worst f B (x k ) function, θ is the standard normal distribution number, and σ is |-1, 1|.

[0092] Specifically, due to f B (x k ) is the power load forecasting model, so the goal is to minimize f B (x k ) Optimize the search on the Matrix so that the model's prediction of power load is closer to the actual value. The optimization search on the Matrix includes: establishing a scout, a follower, and a predator. The scout records the current search f B (xk ), the follower records the f following the scout B (x k ) and assign the predator Predator. In addition, μ is used in the formula to affect the predator's search position update, and the optimization avoids falling into the local optimum.

[0093] The above describes in detail the preferred embodiments of the present invention. It should be understood that numerous modifications and variations based on the concepts of the present invention are possible by those skilled in the art without inventive effort. Therefore, any technical solution that can be derived by those skilled in the art through logical analysis, reasoning, or limited experimentation based on the concepts of the present invention and the prior art should be within the scope of protection defined by the claims.

Claims

1. A method for intelligent prediction of power load based on big data, characterized in that: The following steps are involved: S10: Obtain historical power load records and historical power behavior records of each power user in the region; S20: Establish a power probability model based on historical power behavior records; S30: establishing a power load forecasting model based on the power probability model; S40: Identifying parameters of a power probability model and parameters of a power load forecasting model based on historical power behavior records; S50: Inputting historical power load records into the power load forecasting model to output a power load forecast value; The S20 includes: The component functions of the power probability model are defined based on historical power behavior records, including weekday component functions and holiday component functions. The formula is as follows: Where, is the weekday component function, is the holiday component function, is the logarithmic expectation of the nth component function, is the standard deviation of the nth component function, is the observed value of electricity consumption; The S30 includes: The power load of each power unit in the region is weighted and summed, based on the dependent parameters of the distribution representation 、 and The power probability model is used to construct the overall power load forecasting model. The formula is as follows: Where, is the power load forecasting model, is the power load of the electricity user, is the number of electricity consuming units, is the average total power of the electricity consumption unit, is the average total electricity consumption time of the electricity user, The power consumption sequence of each power user in the region, is the dependent parameter of the distribution 、 and Electric power probability model; The parameters for identifying the power probability model in S40 include: The expectation and maximization processing of the holiday component function, and then the expectation and maximization processing of the weekday component function are used as a calculation process. By repeating the iterative calculation process until convergence, the parameters of the power probability model of the local optimal solution are obtained. 、 and ; The parameters of the power load forecasting model identified in S40 include: Create an iterative parameter matrix and output Function, establish the position search of scouts, followers and predators, continuously update the position of the iterative parameter matrix and output the corresponding Function, find the best iterative parameter combination and determine the parameters of the power load forecasting model 、 and ; The iterative parameter matrix is ​​established and output Functions include: Where, is the iteration parameter matrix, for A collection of Parameters for the first set of iterations 、 and , is the maximum number of iterations.

2. The method for intelligent power load prediction based on big data according to claim 1, characterized in that: The holiday component function is subjected to expectation processing and maximization processing, and the formula is as follows: Where, is the expectation of the holiday component function, is the maximization of the holiday component function, The total amount of data to obtain the optimal solution parameters.

3. The method for intelligent power load prediction based on big data according to claim 2, characterized in that: The expectation processing and maximization processing of the working day component function are as follows: Where, is the expectation of the weekday component function, is the maximization of the workday composition function.

4. The method for intelligent power load prediction based on big data according to claim 3 is characterized in that: The scout's position search formula is as follows: Where, is the scout's position after the search, is the scout's position before the search, for A uniform random number, Indicates that the predator is A random number, is a standard normal random number, A warning value for scouts that have spotted a predator.

5. The method for intelligent power load prediction based on big data according to claim 4 is characterized in that: The follower's position search formula is as follows: Where, is the follower position after searching, is the follower's position before the search, The iterative parameter position with the worst optimization effect in the current search, It is the iterative parameter position with the best optimization effect in the current search. for A random number.

6. The method for intelligent power load prediction based on big data according to claim 5, characterized in that: The predator's position search formula is as follows: Where, is the predator's position after searching, is the predator's position before searching, For the current search function, For the best function, The worst function, is the standard normal distribution number, The value is .

Images