Air conditioning system load prediction method, device, medium and equipment

Abstract

The present invention discloses a method, device, medium, and equipment for predicting the load of an air-conditioning system, and relates to the technical field of load prediction. The method first obtains the historical load data of the air-conditioning system and the load influencing factors of the same period as the historical load data. A preliminary load prediction model is then constructed based on the historical load data using a seasonal difference autoregressive sliding average model, and the prediction residuals of the preliminary load prediction model for the historical load data are determined. A generalized regression neural network is then trained based on the load influencing factors and the prediction residuals of the preliminary load prediction model for the historical load data to obtain a residual prediction model. Finally, the load data to be predicted can be input into the preliminary load prediction model for preliminary load prediction, and the residual prediction model is used to correct the load data, thereby determining the predicted load of the air-conditioning system at the target time based on the preliminary load and the corrections. The present invention improves convergence speed, prediction efficiency, and prediction accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of load forecasting, and in particular to a method, device, medium and equipment for forecasting load of an air-conditioning system. Background Art

[0002] Currently, building air conditioning systems account for approximately 40% to 50% of total energy consumption, presenting significant energy-saving potential. Accurately predicting cooling loads in air conditioning systems not only helps reduce energy consumption and improve system efficiency, but also provides theoretical and practical support for air conditioning system control.

[0003] In the prior art, air conditioning load forecasting methods are generally divided into physical modeling methods and data-driven methods. The physical modeling method calculates the air conditioning load through mechanism modeling, using detailed building parameters, equipment operation data and personnel flow. However, due to the characteristics of air conditioning systems such as nonlinearity, strong coupling, and large hysteresis, it is difficult to establish a universal and accurate air conditioning load model. In recent years, with the development of the computer industry, especially the advancement of artificial intelligence technology, data-driven methods, including machine learning algorithms such as support vector machines and neural network technology, have been widely used in air conditioning load forecasting. Starting from the characteristics of the data itself and considering its changing trends, the data-driven method obtains the predicted value by training the model with a large amount of historical data and related variable data. It has the advantages of low cost, high flexibility, high accuracy and strong generalization ability.

[0004] However, when applied to air conditioning load forecasting, traditional machine learning algorithms often have low accuracy when using simple network structures. Furthermore, when seeking to improve air conditioning load forecasting accuracy, complex network structures are often employed, resulting in slower convergence and lower prediction efficiency. In other words, traditional air conditioning load forecasting methods cannot achieve both efficiency and accuracy. Summary of the Invention

[0005] Based on this, it is necessary to provide an air conditioning system load prediction method, device, medium and equipment to address the above technical problems.

[0006] The present invention adopts the following technical solutions:

[0007] The present invention provides a load forecasting method for an air-conditioning system. The method first obtains historical load data of the air-conditioning system and load influencing factors of the same period as the historical load data. Then, a preliminary load forecasting model is constructed based on a seasonal difference autoregressive sliding average model according to the historical load data, and the prediction residual of the preliminary load forecasting model for the historical load data is determined. Then, a generalized regression neural network is trained according to the load influencing factors and the prediction residual of the preliminary load forecasting model for the historical load data to obtain a residual forecasting model. Finally, the load data to be predicted can be input into the preliminary load forecasting model for preliminary load forecasting, and the residual prediction model is used to determine the residual corresponding to the preliminary forecast according to the load influencing factors to be predicted so as to correct it, thereby determining the predicted load of the air-conditioning system at a target time according to the preliminary load and the correction.

[0008] The present invention provides an air conditioning system load prediction device, comprising:

[0009] An acquisition module is used to obtain historical load data of the air-conditioning system and load influencing factors during the same period of the historical load data;

[0010] A preliminary training module is used to train the seasonal difference autoregressive moving average model based on historical load data to obtain a preliminary load forecasting model; and to determine the prediction residual of the preliminary load forecasting model for the historical load data;

[0011] The residual training module is used to train the generalized regression neural network based on the load influencing factors and the prediction residuals of the preliminary load forecasting model for historical load data to obtain a residual prediction model;

[0012] A preliminary prediction module is used to input the load data to be predicted into the preliminary load prediction model, extract the time series characteristics of the load data to be predicted through the preliminary load prediction model, and determine the preliminary load of the air-conditioning system at the target time according to the time series characteristics;

[0013] The residual prediction module inputs the load influencing factors to be predicted into the residual prediction model, extracts the relationship characteristics between the load influencing factors and the air-conditioning load through the residual prediction model, and determines the correction of the preliminary load based on the relationship characteristics; the predicted load of the air-conditioning system at the target time is determined based on the sum of the preliminary load and the correction to the preliminary load.

[0014] The present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned air-conditioning system load prediction method is implemented.

[0015] The present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned air conditioning system load prediction method when executing the program.

[0016] At least one of the above technical solutions adopted by the present invention can achieve the following beneficial effects:

[0017] The present invention splits and processes the relevant data of the air-conditioning system load forecast. On the one hand, the seasonal difference autoregressive sliding average model is used to capture the periodic characteristics of the air-conditioning system load data, thereby fitting the change law of the air-conditioning system load data, making a preliminary forecast of the load data of the air-conditioning system to be predicted, and determining the preliminary load forecast result of the air-conditioning system at the target time under the change law; on the other hand, the generalized regression neural network is used to capture the nonlinear relationship between the load influencing factors and the load that is ignored in the previous aspect, thereby further correcting the preliminary load forecast result by utilizing the nonlinear approximation ability of the generalized regression neural network. By decoupling the entire air-conditioning system load forecasting process, the complexity of the network structure is reduced, the convergence speed and prediction efficiency are improved, and the prediction accuracy is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0019] Figure 1 A flow chart of a method for predicting load of an air-conditioning system provided by the present invention;

[0020] Figure 2 A SARIMA model prediction process diagram provided by the present invention;

[0021] Figure 3 A schematic diagram of the GRNN model structure provided by the present invention;

[0022] Figure 4 A schematic diagram of the NRBO-GRNN model optimization process provided by the present invention;

[0023] Figure 5 A schematic diagram of a load prediction device for an air-conditioning system provided by the present invention;

[0024] Figure 6 A schematic diagram of a computer device for implementing a method for predicting air-conditioning system load provided by the present invention. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention and corresponding drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] In order to solve the problems existing in the existing methods, this patent proposes a prediction model that combines the Seasonal Autoregressive Integrated Moving Average (SARIMA) model, the Generalized Regression Neural Network (GRNN), and the Newton-Raphson-based optimizer (NRBO). It uses the SARIMA model for preliminary prediction and the GRNN network for secondary learning to further improve the prediction accuracy and handle complex nonlinear problems. It simplifies the input parameters and parameter adjustment process required for the prediction model, has better time series prediction performance, and has significant advantages in optimization accuracy, convergence speed, and stability.

[0027] The technical solutions provided by various embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0028] Figure 1 The following is a flow chart of a method for predicting load of an air conditioning system according to the present invention, which specifically includes the following steps:

[0029] S101: Obtain historical load data of the air-conditioning system and load influencing factors during the same period as the historical load data.

[0030] S102: Training a seasonal difference autoregressive moving average model based on historical load data to obtain a preliminary load forecasting model; and determining a prediction residual of the preliminary load forecasting model for the historical load data.

[0031] S103: Based on the load influencing factors and the prediction residuals of the preliminary load forecasting model for the historical load data, a generalized regression neural network is trained to obtain a residual prediction model.

[0032] S104: Input the load data to be predicted into the preliminary load prediction model, extract the time series features in the load data to be predicted through the preliminary load prediction model, and determine the preliminary load of the air-conditioning system at the target time according to the time series features.

[0033] S105: Input the load influencing factors to be predicted into the residual prediction model, extract the relationship characteristics between the load influencing factors and the air-conditioning load through the residual prediction model, and determine the corrected residual of the preliminary load based on the relationship characteristics; and determine the predicted load of the air-conditioning system at the target time based on the sum of the preliminary load and the corrected residual.

[0034] For the sake of convenience, the following description will only be based on the server as the execution subject. The server mentioned in the present invention can be a server set up on a business platform, or a device such as a desktop computer or a laptop computer that can execute the solution of the present invention.

[0035] Generally, data-driven methods for predicting the load of air-conditioning systems mostly use historical air-conditioning load data, which has obvious periodicity on a time scale of years or days. Therefore, in one or more embodiments of the present invention, the server of the business platform can obtain historical load data of the air-conditioning system. At the same time, the present invention uses a seasonal difference autoregressive moving average model for load prediction of the air-conditioning system. The SARIMA model is a time series model that comprehensively considers the dependence, seasonality and linear trend of the time series but does not consider the nonlinear trend. If this model is used to fit the data, the information contained in the nonlinear trend in the time series data will be omitted. The GRNN model has a strong nonlinear approximation ability and can extract the information contained in the nonlinear trend. Combining the SARIMA model and the GRNN model to establish a SARIMA-GRNN combined model, comprehensively utilizing the characteristics of the information provided by the two prediction models, can not only make up for the defect that the SARIMA model cannot fit the nonlinear part, but also improve the fitting accuracy of the overall model to make the prediction more accurate, thereby improving the stability of the air-conditioning system.

[0036] The SARIMA model is used to make preliminary forecasts using historical load data. SARIMA can describe time series that exhibit periodic characteristics due to seasonal variations (annual, monthly, weekly, and daily). When dealing with time series problems, it can simultaneously consider correlations between data and interference from random factors, resulting in high forecast accuracy. It is commonly used to fit time series problems. In one or more embodiments of the present invention, historical load data for the air conditioning system is used as input to the SARIMA model to predict the air conditioning system load at a historical moment. The predicted residual of the predicted air conditioning system load, i.e., the difference between the actual load value and the predicted value, is calculated based on the historical load data at that moment.

[0037] The establishment of the SARIMA model includes the following three steps: (1) Using the unit root test (Augmented Dickey-Fuller, ADF) test to stabilize the time series of the original load history data and determine the difference order (d, D); (2) Using the autocorrelation function (ACF) graph and the partial autocorrelation coefficient (PACF) graph to determine the possible model parameters (p: number of non-seasonal autoregressive terms; q: number of non-seasonal moving average terms; P: number of seasonal autoregressive terms; Q: number of seasonal moving average terms; s: length of the seasonal cycle); (3) Using the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC) to screen the optimal model, the optimal model is obtained. Figure 2 As shown, Figure 2 This is a schematic diagram of the SARIMA model prediction process in the present invention.

[0038] Specifically, the server can use a unit root test to determine the stationarity of the historical load data. When the historical load data has a trend, the historical load data is differentiated. When the historical load data has seasonality, the historical load data is seasonally differentiated until the historical load data is stable. The non-seasonal difference order d and seasonal difference order D are determined when the seasonal difference autoregressive sliding average model is used to predict the load of the air-conditioning system.

[0039] According to the autocorrelation function graph and partial autocorrelation coefficient graph corresponding to the historical load data, the number of non-seasonal autoregressive items to be selected when using the seasonal difference autoregressive moving average model for air conditioning system load forecasting is determined. p , non-seasonal moving average items q , seasonal autoregressive terms P , seasonal moving average items Q and the length of the seasonal cycle s .

[0040] According to the number of candidate non-seasonal autoregressive items, the number of non-seasonal moving average items, the number of seasonal autoregressive items, the number of seasonal moving average items and the length of the seasonal cycle, multiple candidate seasonal difference autoregressive moving average models are formed, and the candidate seasonal difference autoregressive moving average models are screened by Akaike information criterion and Bayesian information criterion, and the optimal seasonal difference autoregressive moving average model is used as the preliminary load forecasting model.

[0041] The formula for the SARIMA model is as follows: ,in, , , , , .

[0042] Where, x ( t ) is the air conditioning system load time series, is the stable historical load data after difference, B is the lag operator, is the difference operator, F ( B s ) f ( B ) is a seasonal autoregressive model, f ( B )for p order autoregressive polynomial, f 1. f 2. ... f p is the non-seasonal autoregressive parameter, F ( B s ) is the seasonal autoregressive polynomial, F 1. F 2. ... F P for P Order seasonal autoregressive parameter, I ( B s ) i ( B ) is the seasonal moving average model, i ( B )for q order moving average polynomial, i 1. i 2. ... i q is the seasonal moving average polynomial, I ( B s ) is the non-seasonal moving average polynomial, I 1. I 2. ... I Q for Q The seasonal moving average parameter, e ( t ) is Gaussian noise.

[0043] Furthermore, when forecasting air conditioning load, the selection of prediction model input data significantly impacts the model's prediction speed and the accuracy of the final output prediction results. In one or more embodiments of the present invention, in addition to obtaining historical load data for the air conditioning system, the server may also obtain load influencing factors for the same period as the historical load data. These load influencing factors may include one or more combinations of outdoor temperature, indoor temperature, solar radiation, relative humidity, holiday attributes, and occupancy density.

[0044] Since the load influencing factors are diverse and their influence on the air-conditioning load varies, the factors with greater influence can be found among the many load influencing factors and determined as input variables.

[0045] Therefore, within a set historical data collection cycle and at set time intervals, the server collects various load-influencing factors from the historical load data of the air-conditioning system during the same period. Using Pearson correlation analysis, it identifies the load-influencing factors that have the greatest impact on the air-conditioning system load and uses these as sample data to train the GRNN model. Furthermore, the prediction residuals corresponding to the SARIMA model's predictions of the air-conditioning system's historical load data serve as the GRNN model's annotations. The sample data is then input into a generalized regression neural network to obtain the predicted residuals. The generalized regression neural network is trained multiple times with the optimization objective of minimizing the deviation between the predicted residuals and the annotations. The GRNN model's output can be denormalized to obtain the GRNN model's predicted value for the prediction residuals. To avoid neuron saturation and eliminate dimensional differences between variables, the sample data needs to be normalized to accelerate the optimization process and improve training accuracy. Furthermore, the collected sample data can be divided into training and test sets in a 3:1 ratio to ensure the accuracy of the GRNN model during training and better generalization in application.

[0046] The GRNN neural network model uses the SARIMA model to perform secondary learning on the prediction residuals of historical load data. By learning the relationship between the SARIMA model's prediction residuals and various load-influencing factors, it can further correct the SARIMA model's prediction results. In other words, the GRNN model uses the residual error to compensate for the SARIMA model, capturing nonlinear relationships that the SARIMA model fails to accurately predict. The GRNN model outputs the corrected residual of the predicted load. The final prediction value is the sum of the initial load predicted by the SARIMA model and the corrected residual of the GRNN model. In this way, using the GRNN model to compensate for the SARIMA model's residual error can effectively improve the accuracy of load forecasting.

[0047] The GRNN model is a neural network model based on nonlinear regression theory and is a type of radial basis function network (RBF). The GRNN consists of four layers: input layer, pattern layer, summation layer, and output layer. Figure 3 As shown, Figure 3 This is a schematic diagram of the GRNN model structure in the present invention.

[0048] Figure 3 In the example, the input sample is , the output sample is The number of neurons in the input layer is equal to the dimension of the input variable, which can transmit the input directly to the pattern layer; each neuron in the pattern layer corresponds to a different sample, and the number of neurons corresponds to the number of training samples. n The transfer function of a neuron , i = 1, 2, …, I .

[0049] Where, X is the input sample of the model, X i For the i The observation value corresponding to each neuron is s is the smoothing factor.

[0050] The summation layer includes two types of neurons, one of which performs arithmetic summation on the outputs of neurons in all pattern layers, and its transfer function is .

[0051] Another type of neuron performs weighted summation of the outputs of all pattern layers, with the weight being n The dependent variable (output vector) of the training samples (input samples) Y n No. j elements, and its transfer function is: .

[0052] Where, y nj For the model layer n neurons and the summation layer j The summed neuron connection weights.

[0053] Output layer, the number of neurons is equal to the dimension of the output vector J , each neuron divides the output of the summation layer, j The output of the neuron corresponds to the predicted result j Elements: ,j =1, 2, ..., J .

[0054] Where, y i The output layer j The output of a neuron.

[0055] GRNN neural network depends on training samples, and only one parameter, the smoothing factor, needs to be adjusted in model construction. s When it is very large, the prediction results are close to the dependent variable (output vector) of all training samples (input samples) Y The network has a strong generalization ability; when s When it approaches 0, the prediction result is close to the dependent variable (output vector) of the training sample (input sample) closest to the prediction point. Y , the network approximation effect is good, but if it encounters a prediction point that is not included in the training sample, the prediction effect will be very poor and overfitting will occur. In order to obtain a suitable smoothing factor s In one or more embodiments of the present invention, the Newton-Raphson optimization algorithm is used to optimize parameters. The NRBO algorithm is an optimization algorithm that combines the Newton-Raphson method with heuristic search techniques. This algorithm aims to solve complex optimization problems through efficient local and global search capabilities.

[0056] The NRBO algorithm uses the Newton-Raphson method to find the search area to define the search path, and uses the Newton-Raphson Search Rule (NRSR) and the Trap Avoidance Operator (TAO) to explore the search domain. Figure 4 As shown, Figure 4 This is a schematic diagram of the NRBO-GRNN model optimization process in the present invention.

[0057] Specifically, in one or more embodiments of the present invention, the server may construct a generalized regression neural network corresponding to each individual in each iteration, and determine the fitness value corresponding to the individual based on the prediction accuracy of the constructed generalized regression neural network's prediction residuals for a preset test sample. The worst and best population positions of the population are determined based on the individual fitness values. Based on the worst and best population positions, the Newton-Raphson optimization algorithm is used to update the individuals in the population. After multiple iterations, the global optimal solution in the population after the iterations is used as the optimal smoothing factor.

[0058] As the iteration proceeds, the adaptive parameters dBalance exploration and development, focusing more on exploration in the early stages and more on development in the later stages. Repeat the search and update process to gradually optimize the smoothing factor until the maximum number of iterations is reached. The final global optimal solution, Xb, is the optimized smoothing factor, which is used to improve the GRNN's predictive performance.

[0059] Specifically, first, a random population can be generated by the following formula: .

[0060] in, xnj Indicates the n The individual's j The parameters to be optimized, lb 、 ub are the upper and lower bounds of the parameters to be optimized, rand is a random number between (0,1); N p is the number of individuals in the population; dim is the dimension of the parameter to be optimized. In the present invention, the parameter to be optimized is the smoothing factor. dim is 1.

[0061] The population matrix is as follows: .

[0062] Where, For populations, Each row corresponds to an individual, and each column corresponds to a dimension of the parameter to be optimized.

[0063] The Newton-Raphson search rule is as follows: , , , .

[0064] Where, is the vector generated in the Newton-Raphson search rule update step, The current iteration n The solution corresponding to each individual, xnj middle j When 1 is taken, it is , randn is a normally distributed random number with mean 0 and variance 1, X w is the worst population position of the current iteration, X b is the optimal population position of the current iteration, is the process vector generated when generating a new individual, which means exploring the worse area in the search space based on the worse individuals in the population. is the process vector generated when generating new individuals, which represents the search for further developing better areas based on better individuals in the population, is the amount of change when generating a new individual, is a random number between (0,1), Search parameters for Newton-Raphson.

[0065] Calculating NRSR can enhance the current solution by helping it update its position. This formula increases the search capability of NRBO through random parameters and better balances the exploration and exploitation capabilities. In order to find the optimal solution in the search space and eventually converge to the global solution, an adaptive coefficient can be applied. d To enhance the algorithm. d The expression is:

[0066] Where, IT Indicates the current iteration number, Max_IT Indicates the maximum number of iterations.

[0067] In order to maintain a balance between the exploration and exploitation phases, the adaptive coefficient d Adaptation during the iteration process significantly reduces the number of iterations while taking into account the random behavior of the optimization process, increasing diversity and avoiding local optimality, thereby improving the NRBO algorithm. r To improve the development of the proposed NRBO, the optimization algorithm further refines the search near the already found high-quality solution to obtain a better local solution, and focuses the search in a local area of the search space to maximize the use of the information of the currently obtained best solution. This parameter guides the population in the right direction. r The expression is: .

[0068] Where, a and b is a random number between (0,1), r 1 and r 2 are unequal, distinct integers chosen randomly from the population.

[0069] The search method proposed by the following formula is benign when searching locally, but has limitations when searching globally: .

[0070] Where, To update The new vector position obtained is is the individual position at the IT-th iteration, indicating the smoothing factor value of the current individual, is the set of smoothing factor values of all individuals in the entire population in the IT-th iteration, and are two individual positions randomly selected from the population.

[0071] The search strategy proposed by the following formula is benign in global search, but has limitations in local search: .

[0072] Where, For consideration X b 、 、 The new vector position is used to further improve the search effect.

[0073] NRBO uses both of the above equations to improve both the exploration and exploitation phases. The new position vector at the next iteration is as follows: , .

[0074] Where, is the solution vector at the IT+1th iteration, For consideration 、 and The generated new position vector is used for local exploration to balance global search and local search.

[0075] Using Trap Avoidance Operation (TAO) can significantly change The position of. By the following formula, when rand The value is less than DF When : , , .

[0076] Where, β is a binary number 1 or 0, is a uniform random number between (-1,1), is a uniform random number between (-0.5, 0.5), is the average value of the smoothing factors of all individuals in the IT-th iteration, It is a local optimal solution, a better smoothing factor value generated during the local exploration process.

[0077] Due to the parameters m 1 and m 2 The randomness of the selection makes the population more diverse, thus breaking away from the constraints of local optimal solutions.

[0078] The pseudo code of the NRBO optimization algorithm is as follows:

[0079] initialization:

[0080] 1. Choose the population size ( N p ), maximum number of iterations ( Max_IT ) and the determinant ( DF ) is an appropriate value.

[0081] 2. Initialize the random ensemble position.

[0082] 3. Evaluate initial fitness and specify X b (optimal population position) and X w (Worst population position).

[0083] Main loop:

[0084] while ( IT < Max_IT );

[0085] oven =1: N p ;

[0086] forge =1: dim ;

[0087] In the interval [1, N p ] Pick unequal random integers r 1 、 r 2 ;

[0088] Determine the solution ;

[0089] end for ;

[0090] ifrand < DF ;

[0091] Finding a solution ;

[0092] ;

[0093] else ;

[0094] Determine the solution ;

[0095] end if ;

[0096] renew X b and X w ;

[0097] end for ;

[0098] IT = IT +1;

[0099] end while ;

[0100] Termination: If the termination condition is met, return the best solution X b .

[0101] The implementation steps of SARIMA model construction and NRBO algorithm optimization of GRNN neural network are as follows Figure 5 As shown, Figure 5 The following is a schematic diagram of a SARIMA-NRBO-GRNN model prediction process in the present invention, including:

[0102] 1. Data preparation and preprocessing: Collect and clean the historical load data of the air conditioning system and the time series data corresponding to the load influencing factors during the same period of the historical load data. Process missing values and outliers, normalize the data, and further divide the sample data set.

[0103] For example, first collect and pre-process the data. Within a set historical data collection period (e.g., no less than one year), collect the historical load data of the air-conditioning system and various load influencing factors of the same period at set time intervals (e.g., 1 hour), and use Pearson correlation analysis to determine the load influencing factors that have a greater impact on the air-conditioning system load. I The total sample data collected can be divided into training set and test set in a ratio of 3:1 to ensure the accuracy of the model during training and better generalization during testing.

[0104] Here we can use the linear function normalization method: .

[0105] Where, is the normalized data, is the data to be normalized, is the minimum value of the data type to be normalized, The maximum value of the data type to be normalized.

[0106] At the same time, in order to make the obtained data reflect the true value of the original dimension, the output prediction results need to be denormalized.

[0107] 2. Use ADF test to make the original time series stationary and determine the difference order ( d , D ).

[0108] 3. Use the autocorrelation function ACF diagram and partial autocorrelation coefficient PACF diagram to determine the possible SARIMA model parameters ( p , q , P , Q , s ).

[0109] 4. The optimal SARIMA model was obtained by using Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) to screen the optimal model.

[0110] 5. Input the historical air conditioning system load data into the SARIMA model to predict the air conditioning system load at the historical target time and calculate the prediction residual. Prediction residual = actual air conditioning system load at the historical target time - SARIMA predicted value.

[0111] 6. Initialize the GRNN model parameters, including determining the input and output variables of the GRNN model and initializing the smoothing factor. Input variables may include: outdoor temperature at the historical load data moment, outdoor temperature at the moment before the historical load data moment, indoor temperature at the historical load data moment, load forecast residuals, solar radiation at the historical load data moment, relative humidity at the historical load data moment, holiday attributes at the historical load data moment, and building occupancy density at the historical load data moment.

[0112] 7. Initialize the NRBO algorithm parameters, including population size, maximum number of iterations, and determining factors.

[0113] 8. For each GRNN model corresponding to each population individual, use the GRNN to make predictions and calculate the root mean square error RMSE As the fitness value of the individual: .

[0114] in, y i is the prediction residual of the GRNN model, is the annotation during GRNN model training, that is, the actual prediction residual, M is the number of iterations.

[0115] 9. Start iteration and apply the Newton-Raphson search rule to each individual in the population so that the fitness value gradually decreases.

[0116] 10. Trap Avoidance Operation (TAO) is introduced to adjust the search path of individuals in the population to avoid falling into local optimality and update the parameters of GRNN.

[0117] 11. Select individuals with lower fitness to form a new population, re-evaluate the fitness values of the updated population individuals, and determine the global optimal position and global optimal fitness value.

[0118] 12. Determine whether to terminate the optimization process based on the preset termination conditions: maximum number of iterations or fitness threshold. The smoothing factor corresponding to the lowest fitness value generated during the iteration is taken as the optimal smoothing factor.

[0119] 13. The SARIMA-NRBO-GRNN prediction model is constructed using the optimal smoothing factor. The test samples are predicted and the predicted revised value is output. The final predicted value is obtained by summing it with the initial predicted value of the SARIMA model.

[0120] Through the above process, the SARIMA model and the GRNN model are successively constructed and trained to obtain a preliminary load forecasting model and a residual forecasting model, so that the load data to be predicted are input into the preliminary load forecasting model, the time series characteristics in the load data to be predicted are extracted through the preliminary load forecasting model, and the preliminary load of the air-conditioning system at the target time is determined according to the time series characteristics, and the load influencing factors to be predicted are input into the residual prediction model, and the relationship characteristics between the load influencing factors and the air-conditioning load are extracted through the residual prediction model, and the corrected residual of the preliminary load is determined according to the relationship characteristics, and the predicted load of the air-conditioning system at the target time is determined according to the sum of the preliminary load and the corrected residual.

[0121] based on Figure 1 The air-conditioning system load forecasting method shown in the figure first obtains the historical load data of the air-conditioning system and the load influencing factors of the same period as the historical load data, then constructs a preliminary load forecasting model based on the seasonal difference autoregressive sliding average model according to the historical load data, and determines the prediction residual of the preliminary load forecasting model for the historical load data, and then trains the generalized regression neural network according to the load influencing factors and the prediction residual of the preliminary load forecasting model for the historical load data to obtain a residual prediction model, and finally the load data to be predicted can be input into the preliminary load forecasting model for preliminary load prediction, and the residual prediction model is used to determine the residual corresponding to the preliminary prediction according to the load influencing factors to be predicted so as to correct it, thereby determining the predicted load of the air-conditioning system at the target time according to the preliminary load and the correction.

[0122] The present invention splits and processes the relevant data of the air-conditioning system load forecast. On the one hand, the seasonal difference autoregressive sliding average model is used to capture the periodic characteristics of the air-conditioning system load data, thereby fitting the change law of the air-conditioning system load data, making a preliminary forecast of the load data of the air-conditioning system to be predicted, and determining the preliminary load forecast result of the air-conditioning system at the target time under the change law; on the other hand, the generalized regression neural network is used to capture the nonlinear relationship between the load influencing factors and the load that is ignored in the previous aspect, thereby further correcting the preliminary load forecast result by utilizing the nonlinear approximation ability of the generalized regression neural network. By decoupling the entire air-conditioning system load forecasting process, the complexity of the network structure is reduced, the convergence speed and prediction efficiency are improved, and the prediction accuracy is improved.

[0123] In building energy consumption, air conditioning systems are one of the main energy-consuming devices. Using the historical load of the air conditioning system to predict the air conditioning load is a commonly used data-driven method. Since the air conditioning load has obvious periodicity on a time scale of years or days, the present invention considers using the SARIMA model for load prediction of the air conditioning system. And combining the NRBO algorithm to optimize the GRNN neural network for air conditioning system load prediction can achieve accurate energy consumption management. Combined with real-time data, the model can predict short-term and long-term air conditioning loads. More accurate load predictions can help optimize the operating strategy of the air conditioning system, reduce unnecessary energy consumption, and achieve energy-saving effects. In a home environment, using the optimized GRNN model for air conditioning load prediction can adjust the air conditioning operation according to the activity patterns of family members and weather changes. Accurate load prediction enables the air conditioning system to respond to load changes more quickly, improving user experience and comfort.

[0124] Air conditioning system loads are cyclical, and their prediction involves a variety of complex nonlinear relationships and random fluctuations. The SARIMA model can capture and handle cyclical fluctuations in time series, but may not accurately predict complex nonlinear relationships. GRNN excels at handling complex nonlinear relationships and random fluctuations, and the NRBO algorithm can further optimize its performance. The NRBO algorithm leverages the rapid convergence of the Newton-Raphson method to quickly find an accurate solution in a local search, improving its predictive performance and generalization capabilities. It can find optimized GRNN parameters within a small number of iterations, thereby improving training efficiency. By combining heuristic search algorithms, NRBO can conduct an effective global search and avoid being trapped in local optima. The introduction of a trap avoidance operation adjusts the search path to increase the diversity of solutions, thereby improving the robustness and stability of the prediction model.

[0125] After a preliminary forecast using the SARIMA model, the forecast residuals are calculated. The GRNN neural network model can use these residuals for secondary learning, correcting and improving the preliminary forecast. This error correction mechanism can significantly improve forecast accuracy. The GRNN neural network model learns the relationship between the residual errors in the SARIMA model's forecast and other influencing factors to compensate for the SARIMA model's forecast results. This model structure, combining preliminary forecasts with secondary learning, can significantly improve the accuracy and reliability of air conditioning load forecasts. The combined model is more stable in the face of different types of data changes. When the data exhibits significant seasonal and trend variations, the SARIMA model provides stable forecasts; when the data exhibits complex nonlinear variations, the GRNN model effectively compensates. For example, air conditioning load exhibits significant cyclical variations between summer and winter, and the SARIMA model can provide a good baseline forecast. The GRNN model, through secondary learning and compensation, provides more accurate corrections for nonlinear effects on air conditioning load caused by weather changes, user behavior, and other factors. This complementary mechanism enables the combined model to maintain high prediction accuracy in various scenarios, reduces the model's dependence on single data characteristics, and improves the robustness and stability of the prediction.

[0126] When applying the air conditioning system load prediction method provided by the present invention, it is not necessary to Figure 1 The steps are executed in the order shown. The specific execution order of the steps can be determined according to needs, and the present invention does not limit this.

[0127] The above is an air conditioning system load prediction method provided by one or more embodiments of the present invention. Based on the same idea, the present invention also provides a corresponding air conditioning system load prediction device, such as Figure 6 shown.

[0128] Figure 6 A schematic diagram of an air conditioning system load prediction device provided by the present invention includes:

[0129] An acquisition module 201 is used to acquire historical load data of the air conditioning system and load influencing factors during the same period of the historical load data;

[0130] The preliminary training module 202 is used to train the seasonal difference autoregressive moving average model based on historical load data to obtain a preliminary load forecasting model; and determine the prediction residual of the preliminary load forecasting model for the historical load data;

[0131] The residual training module 203 is used to train the generalized regression neural network based on the load influencing factors and the prediction residuals of the preliminary load forecasting model for historical load data to obtain a residual prediction model;

[0132] The preliminary prediction module 204 is used to input the load data to be predicted into the preliminary load prediction model, extract the time series characteristics of the load data to be predicted through the preliminary load prediction model, and determine the preliminary load of the air conditioning system at the target time based on the time series characteristics;

[0133] The residual prediction module 205 inputs the load influencing factors to be predicted into the residual prediction model, extracts the relationship characteristics between the load influencing factors and the air-conditioning load through the residual prediction model, and determines the correction of the preliminary load based on the relationship characteristics; and determines the predicted load of the air-conditioning system at the target time based on the sum of the preliminary load and the correction to the preliminary load.

[0134] The specific definitions of the air conditioning system load prediction device can be found in the definitions of the air conditioning system load prediction method described above and will not be repeated here. Each module in the aforementioned air conditioning system load prediction device can be implemented in whole or in part via software, hardware, or a combination thereof. Each of the aforementioned modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each of the aforementioned modules.

[0135] The present invention also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 Provided is a load forecasting method for air conditioning systems.

[0136] The present invention also provides a computer device. At the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 Provided is a load forecasting method for air conditioning systems.

[0137] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes in the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0138] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present invention.

Claims

1. A method for predicting load of an air conditioning system, characterized in that: include: Obtain historical load data of the air conditioning system and load influencing factors during the same period of the historical load data; The load influencing factors include: one or more combinations of outdoor temperature, indoor temperature, solar radiation, relative humidity, holiday attributes and population density; The seasonal difference autoregressive moving average model is trained based on historical load data to obtain a preliminary load forecasting model; the prediction residual of the preliminary load forecasting model for the historical load data is determined; The load influencing factors of the same period as the historical load data are used as sample data, and the prediction residuals are used as labels. The sample data are input into the generalized regression neural network to obtain the predicted prediction residuals. The generalized regression neural network is trained multiple times with the minimum deviation between the predicted prediction residuals and the labels as the optimization goal. In each round of training, the Newton-Raphson optimization algorithm is used to optimize the smoothing factor of the generalized regression neural network to obtain a residual prediction model. Inputting the load data of the air-conditioning system to be predicted into the preliminary load forecasting model, extracting the periodic time series features in the load data to be predicted through the preliminary load forecasting model, and determining the preliminary load of the air-conditioning system at the target time according to the time series features; The load influencing factors to be predicted are input into the residual prediction model. The nonlinear relationship characteristics between the load influencing factors and the air conditioning load are extracted through the residual prediction model to determine the corrected residual of the preliminary load. The predicted load of the air conditioning system at the target time is determined based on the sum of the preliminary load and the corrected residual. The load influencing factors during the period of obtaining historical load data specifically include: During the same period of historical load data, obtain data corresponding to various load influencing factors at preset time intervals; Based on the historical load data of the air-conditioning system and the corresponding data of each load influencing factor, the correlation between each load influencing factor and the historical load data of the air-conditioning system is determined through Pearson correlation analysis; Based on the preset correlation threshold, multiple load influencing factors are screened.

2. The air conditioning system load prediction method according to claim 1, wherein: The seasonal difference autoregressive moving average model is trained based on historical load data to obtain a preliminary load forecasting model, which specifically includes: The unit root test is used to determine the stationarity of the historical load data. When the historical load data has a trend, the historical load data is differentiated. When the historical load data has seasonality, the historical load data is seasonally differentiated until the historical load data is stable. The non-seasonal and seasonal difference orders are determined when the seasonal difference autoregressive sliding average model is used for air conditioning system load forecasting. Based on the autocorrelation function graph and partial autocorrelation coefficient graph corresponding to the historical load data, the number of non-seasonal autoregressive items, non-seasonal moving average items, seasonal autoregressive items, seasonal moving average items and seasonal cycle length to be selected when using the seasonal difference autoregressive moving average model for air conditioning system load forecasting; According to the number of candidate non-seasonal autoregressive items, the number of non-seasonal moving average items, the number of seasonal autoregressive items, the number of seasonal moving average items and the length of the seasonal cycle, multiple candidate seasonal difference autoregressive moving average models are formed, and the candidate seasonal difference autoregressive moving average models are screened by Akaike information criterion and Bayesian information criterion, and the optimal seasonal difference autoregressive moving average model is used as the preliminary load forecasting model.

3. The air conditioning system load prediction method according to claim 1, wherein: The Newton-Raphson optimization algorithm is used to optimize the smoothing factor of the generalized regression neural network, specifically including: The smoothing factors of the generalized regression neural network are generated by random algorithms to form a population, and each individual in the population is a generated smoothing factor; Constructing a generalized regression neural network corresponding to each individual, and determining the fitness value corresponding to the individual based on the prediction accuracy of the prediction residual of the constructed generalized regression neural network for a preset test sample; determining the worst population position and the best population position of the population based on the individual fitness value; According to the worst population position and the best population position, the Newton-Raphson optimization algorithm is used to update the individuals in the population. After multiple rounds of iteration, the global optimal solution in the population after iteration is used as the optimal smoothing factor.

4. An air conditioning system load prediction device, characterized in that: include: An acquisition module is used to obtain historical load data of the air-conditioning system; During the same period of historical load data, obtain data corresponding to various load influencing factors at preset time intervals; Based on the historical load data of the air-conditioning system and the corresponding data of each load influencing factor, the correlation between each load influencing factor and the historical load data of the air-conditioning system is determined through Pearson correlation analysis; Screen multiple load influencing factors based on preset correlation thresholds; The load influencing factors include: one or more combinations of outdoor temperature, indoor temperature, solar radiation, relative humidity, holiday attributes and population density; A preliminary training module is used to train the seasonal difference autoregressive moving average model based on historical load data to obtain a preliminary load forecasting model; and to determine the prediction residual of the preliminary load forecasting model for the historical load data; The residual training module is used to use the load influencing factors of the same period as the historical load data as sample data and the predicted residuals as labels; the sample data is input into the generalized regression neural network to obtain the predicted residuals, and the generalized regression neural network is trained multiple times with the minimum deviation between the predicted residuals and the labels as the optimization goal. In each round of training, the Newton-Raphson optimization algorithm is used to optimize the smoothing factor of the generalized regression neural network to obtain the residual prediction model; A preliminary prediction module is used to input the load data to be predicted into the preliminary load prediction model, extract the time series characteristics of the load data to be predicted through the preliminary load prediction model, and determine the preliminary load of the air-conditioning system at the target time according to the time series characteristics; The residual prediction module inputs the load influencing factors to be predicted into the residual prediction model, extracts the relationship characteristics between the load influencing factors and the air-conditioning load through the residual prediction model, and determines the correction of the preliminary load based on the relationship characteristics; the predicted load of the air-conditioning system at the target time is determined based on the sum of the preliminary load and the correction to the preliminary load.

5. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

6. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 3 is implemented.

Images