Public building cold load prediction method, system, equipment and medium

Abstract

The invention provides a public building cold load prediction method, system, equipment and medium, and the method comprises the following steps: collecting cold load related data, carrying out the preprocessing, employing a random forest method to process the processed related data, and obtaining a model input data set; optimizing the SSA model by adopting the good point set, and optimizing the LSTM grid parameters based on the optimized SSA model to obtain an RF-I SSA-LSTM mixed cold model; based on the RF-I SSA-LSTM mixed cold model and a model input data set, obtaining a cold load prediction result; according to the method, evaluation index model establishment and characteristic value extraction of the data set are carried out on the related influence variables of the large building cold load based on the random forest method, the variables with high correlation degree are selected as the model input data set, the RF-ISSA-LSTM mixed cold model has better global search ability, the optimization result is more accurate, and the optimization efficiency is improved. The technical problem that the cold load of the public building cannot be accurately predicted in the prior art is solved.

Description

Technical Field

[0001] The invention belongs to the technical field of cold load prediction of air-conditioning systems, and in particular to a method, system, equipment and medium for predicting cold load of public buildings. Background Art

[0002] Global warming, environmental degradation and energy shortage crisis are severe challenges facing the world. The growing building energy consumption is an important part of the energy consumption structure. The area scale and unit area energy consumption of large public buildings have also increased significantly. Public buildings have huge energy-saving potential. In large public buildings, the energy consumption of HVAC systems accounts for 40%-60% of the total building energy consumption. Therefore, energy saving of air-conditioning systems has become a key issue in building energy-saving design and an important direction for improving the energy efficiency of the whole society. Many large public buildings use ice storage air-conditioning systems to achieve energy saving and consumption reduction. The ice storage air-conditioning system makes full use of energy storage technology to achieve peak shifting and valley filling. The cold storage device is used to store cold energy during the low electricity consumption stage at night, and the cold energy is released during the peak electricity consumption stage during the day to meet the building load demand, reducing the electricity consumption burden during peak hours, which can achieve the purpose of building energy saving to a large extent. Accurate prediction of building cooling load can optimize resource allocation and improve comprehensive energy efficiency. At the same time, reasonable planning of air-conditioning equipment operation strategy is conducive to further developing the energy-saving potential of ice storage air-conditioning systems.

[0003] When using mainstream neural networks to predict the short-term cooling load of buildings, in addition to the historical cooling load data set, various types of influencing factor data are still needed, such as the building's own energy consumption characteristics, building characteristics, meteorological factors, social factors, economic development factors, etc. Therefore, the change of building cooling load is affected by multiple influencing factors, the number of data sets is large, and the accuracy of the cooling load prediction model is reduced. Therefore, when predicting the cooling load of a building, how to effectively process and select a large amount of data becomes the premise and basis of load prediction, and it is also a key factor in determining the accuracy of cooling load prediction. The historical data set of influencing factors used in the cooling load prediction uses a suitable neural network method to form a cooling load prediction model with strong applicability and good prediction effect for specific buildings to explore the correlation between the influencing factors, which is of great significance for the analysis of the cooling load characteristics and performance of buildings and the improvement of the corresponding load prediction method.

[0004] However, there is a technical problem in the existing related technologies that the cooling load of public buildings cannot be accurately predicted. Summary of the invention

[0005] In order to solve the problems existing in the prior art, the present invention provides a method, system, device and medium for predicting the cooling load of a public building, which are used to solve the technical problem that the cooling load of a public building cannot be accurately predicted in the prior related technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for predicting cooling load of a public building comprises the following steps:

[0008] Collect cooling load related data, perform preprocessing, and use random forest method to process the preprocessed related data to obtain the model input data set;

[0009] The SSA model is optimized using the good point set, and the LSTM grid parameters are optimized based on the optimized SSA model to obtain the RF-ISSA-LSTM hybrid cold model;

[0010] Based on the RF-ISSA-LSTM hybrid cooling model and the model input data set, a cooling load prediction result is obtained.

[0011] Further, the cooling load related data includes input data and output data, and the input data includes: cooling load at the previous moment, dry bulb temperature, carbon dioxide, air temperature, dew point temperature, wind speed, solar radiation value at the previous moment, time, solar radiation value at the current moment, relative humidity and wind direction;

[0012] The output data is the air conditioning cooling load at the current moment.

[0013] Furthermore, the process of using the random forest method to process the processed related data is as follows:

[0014] Based on the coupling phenomenon of the cooling load related data in the input data and the output data, features with an influence coefficient greater than 0.2 are preset, and the random forest method is used for feature selection.

[0015] Furthermore, when the good point set is used to optimize the SSA model, the formula for updating the search space phase of the SSA model is optimized as follows:

[0016]

[0017] Among them, ub j and lb j represent the upper and lower boundaries of the j-th dimension, respectively, and X i (j) is the value of the i-th best point in the j-th dimension, represents the value of the i-th point in the j-th dimension, and k is the number of iterations.

[0018] Furthermore, the process of optimizing the LSTM grid parameters based on the optimized SSA model is as follows:

[0019] The SSA model introduces an adaptive inertia weight to the producer position update:

[0020]

[0021] In the formula, iter max Indicates the maximum number of iterations, iter min represents the maximum number of iterations, t represents the current number of iterations, ω represents the adaptive inertia weight, and exp represents the natural exponential function.

[0022] Furthermore, the RF-ISSA-LSTM hybrid cold model has a three-layer structure, which includes an input layer, an output layer and a hidden layer.

[0023] Furthermore, the input layer is 10 layers, the output layer is 1 layer, and the hidden layer is 18 layers.

[0024] A system for predicting cooling load of public buildings, comprising:

[0025] Initialization unit, configured as:

[0026] It is used to collect cooling load related data, pre-process them, and use the random forest method to process the processed related data to obtain the model input data set;

[0027] The model optimization unit is configured as follows:

[0028] It is used to optimize the SSA model with a good point set, and optimize the LSTM grid parameters based on the optimized SSA model to obtain the RF-ISSA-LSTM hybrid cold model;

[0029] Output unit, configured as:

[0030] Used to obtain cooling load prediction results based on the RF-ISSA-LSTM hybrid cooling model and the model input data set.

[0031] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for predicting cooling load of a public building are implemented.

[0032] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for predicting cooling load of a public building.

[0033] Compared with the prior art, the present invention has the following beneficial technical effects:

[0034] The present invention provides a method, system, device and medium for predicting the cooling load of a public building, comprising the following steps: collecting cooling load related data, and preprocessing the data, and using a random forest method to process the processed related data to obtain a model input data set; using a good point set to optimize an SSA model, and optimizing LSTM grid parameters based on the optimized SSA model to obtain an RF-ISSA-LSTM hybrid cooling model; based on the RF-ISSA-LSTM hybrid cooling model and the model input data set, a cooling load prediction result is obtained; the present application establishes an evaluation index model and extracts characteristic values ​​of a data set for related influencing variables of the cooling load of a large building based on the random forest method, and selects variables with high correlation as the model input data set. The RF-ISSA-LSTM hybrid cooling model has better global search capability, more accurate optimization results, and improved algorithm operation speed and accuracy. It has been experimentally verified that the RF-ISSA-LSTM hybrid cooling model can more accurately reflect the energy consumption of large buildings in actual applications, plays a positive role in the cooling load prediction of buildings, and solves the technical problem that the cooling load of public buildings cannot be accurately predicted in the existing related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flow chart of a method for predicting cooling load of a public building according to an embodiment of the present disclosure is shown;

[0036] Figure 2 The fitting effect of the RF-ISSA-LSTM hybrid cold model of the embodiment of the present disclosure is shown.

[0037] Figure 3 A relative error comparison diagram of the RF-ISSA-LSTM hybrid cold model of the embodiment of the present disclosure and the model in the prior art is shown;

[0038] Figure 4 A comparison chart of the running time of the RF-ISSA-LSTM hybrid cold model of the embodiment of the present disclosure and the model in the prior art is shown. DETAILED DESCRIPTION

[0039] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0040] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0041] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0042] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0043] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0044] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0045] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0046] The present disclosure provides a method for predicting cooling load of a public building. Figure 1 As shown, the following steps are included:

[0047] Step S1: Collect cooling load related data, perform preprocessing, and use random forest method to process the processed related data to obtain a model input data set;

[0048] It should be noted that since the change of building cooling load is affected by multiple types of input variables, and there is a certain coupling relationship between the multiple types of input variables, low-correlation input variables will not only increase the difficulty of the model establishment process, but also lead to a decrease in the model running speed and lower prediction accuracy. Therefore, it is necessary to evaluate the data set indicators of the input variables, extract eigenvalues ​​and eliminate input variables with low correlation.

[0049] Preferably, in some embodiments, the cooling load related data includes input data and output data, the input data includes: cooling load at the previous moment, dry bulb temperature, carbon dioxide, air temperature, dew point temperature, wind speed, solar radiation value at the previous moment, time, solar radiation value at the current moment, relative humidity and wind direction; the output data is the air conditioning cooling load at the current moment.

[0050] Next, in some embodiments, the process of using the random forest method to process the processed related data is:

[0051] Based on the coupling phenomenon between the input data and the output data of the cooling load related data, the features with an influence coefficient greater than 0.2 are preset, and the random forest method is used for feature selection. The influence coefficients of the various feature parameters after random forest analysis are shown in Table 1:

[0052] Table 1 Correlation weight results of each input factor

[0053]

[0054] As shown in Table 1, the weight values ​​of outdoor wind speed and outdoor wind direction in the table are less than 0.2, that is, less than the preset influence coefficient. Therefore, they are not used as the model input data set, thereby reducing the output parameter interference of the model.

[0055] Step S2: Use the good point set to optimize the SSA model, and optimize the LSTM grid parameters based on the optimized SSA model to obtain the RF-ISSA-LSTM hybrid cold model;

[0056] It should be noted that since the initialization of the individual positions of the population is the basis of the search of the swarm intelligence algorithm, the diversity of the population distribution will affect the optimization ability of the swarm intelligence algorithm. The more uniform the initial population distribution, the easier it is for the algorithm to globally search for the optimal solution in a shorter time. This embodiment uses the good point set optimization to improve the SSA model and optimize the initial population. That is to say, the good point set optimization to improve the SSA (sparrow search algorithm) model is a strategy to improve the performance of the SSA algorithm by introducing the good point set method. The good point set method optimizes the initialization process of the population to enhance the diversity and uniformity of the population, thereby improving the search efficiency and global optimization ability of the algorithm.

[0057] It should be further explained that the good point set is a set of points evenly distributed in a multidimensional space, with good uniformity and low variance. In the swarm intelligence algorithm, using the good point set to initialize the population can make the individuals evenly distributed in the search space, thereby increasing the algorithm's chances of exploring different areas in the early stages and improving the possibility of finding the global optimal solution.

[0058] Preferably, in some embodiments, when the SSA model is optimized using the good point set, the formula for updating the search space phase of the SSA model is optimized as follows:

[0059]

[0060] Among them, ub j and lb j represent the upper and lower boundaries of the j-th dimension, respectively, and X i (j) is the value of the i-th best point in the j-th dimension, represents the value of the i-th point in the j-th dimension, and k is the number of iterations.

[0061] Step S3: obtaining a cooling load prediction result based on the RF-ISSA-LSTM hybrid cooling model and the model input data set;

[0062] Preferably, in some embodiments, the process of optimizing the LSTM grid parameters based on the optimized SSA model is:

[0063] The SSA model introduces an adaptive inertia weight to the producer position update:

[0064]

[0065] In the formula, iter max Indicates the maximum number of iterations, iter min represents the maximum number of iterations, t represents the current number of iterations, ω represents the adaptive inertia weight, and exp represents the natural exponential function;

[0066] Furthermore, the RF-ISSA-LSTM hybrid cold model is a three-layer structure, which includes an input layer, an output layer and a hidden layer; the input layer has 10 layers, the output layer has 1 layer, and the hidden layer has 18 layers; it should be noted that the input layer is the starting layer of the model, responsible for receiving input data, in which the data is preprocessed and passed to the next layer, the number of nodes in the input layer usually matches the number of features of the input data, the hidden layer is the core part of the model, responsible for learning the complex patterns and features of the input data, the hidden layer can contain multiple nodes, also called neurons or units, which are connected to the input layer and the output layer through weights and activation functions, the hidden layer can have one or more layers, depending on the complexity of the model and the requirements of the learning task, in the hidden layer, the data undergoes a series of nonlinear transformations to extract useful information and features; the output layer is the last layer of the model, responsible for generating the prediction results of the model, the number of nodes in the output layer usually matches the target number of the task, for example, in a classification task, the number of nodes in the output layer may be equal to the number of categories, and the output layer uses an activation function such as softmax to generate the final prediction results.

[0067] This application discloses an embodiment as follows:

[0068] The air conditioning cooling load data set from the energy monitoring center of two large public buildings with different uses in a certain place was collected for experimental verification. The results show that this method can accurately predict the changes in the cooling load of large public buildings in practical applications, which is helpful to realize the online optimization control of the building air-conditioning system, thereby providing effective data support and theoretical reference for building energy-saving management and operation.

[0069] In order to verify the prediction effect of the RF-ISSA-LSTM model described in this application, the mean absolute percentage error MAPE (Mean Absolute Percentage Error) and the root mean square error (RMSE) are selected as the main evaluation indicators of the model prediction accuracy. MAPE has a strong sensitivity to time series prediction and can well reflect the quality of the model. RMSE measures the deviation between the predicted value and the true value and can accurately reflect the prediction accuracy. The formula is as follows:

[0070]

[0071]

[0072] in, is the predicted value of the i-th sample in the test set, y i is the true value of the i-th sample in the test set, and n is the total number of samples.

[0073] Compared with other algorithm models and the improved LSTM model, the relevant evaluation indicators are shown in Table 2.

[0074] Table 2 Comparison of prediction accuracy of different models

[0075]

[0076] The trained ISSA-LSTM model is used to analyze the test data set. The fitting effect of the test data is as follows: Figure 2 As shown in the figure, the horizontal axis is the hourly sampling point, the vertical axis is the building air conditioning cooling load value, the continuous line segment is the actual building cooling load value, the dotted line segment is the building cooling load value predicted by the LSTM model, and the dot-dash line segment is the building cooling load value predicted by the improved LSTM model.

[0077] The building cooling load prediction method based on improved LSTM described in the present invention predicts a specific load value that has a certain gap with the actual value, but the overall rising and falling trend of the predicted value curve of the model can accurately reflect the actual load curve.

[0078] It is compared with other algorithm models, such as Figure 3 As shown in the figure, the solid line segment is the error of the improved model, and the dotted line segment is the error of the model before improvement. It can be seen that the prediction error of the RF-ISSA-LSTM model is much smaller than that of the other three models, the overall prediction accuracy is better, and the error fluctuation range is smaller. The prediction model has good stability and robustness. Therefore, the RF-ISSA-LSTM model still has a high prediction accuracy when reducing the number of prediction data samples for large public buildings. Experiments show that the hybrid model has good model generalization ability.

[0079] It is compared with other algorithm models, such as Figure 4 As shown in the figure, compared with GA-LSTM, PSO-LSTM, GWO-LSTM and SSA-LSTM, ISSA-LSTM has a shorter running time and has a significant advantage in time complexity. The comprehensive results show that ISSA has better optimization performance in the optimization of hyperparameters of LSTM model.

[0080] The building cooling load prediction method based on the improved LSTM in the present invention has high prediction accuracy and good generalization ability, is more suitable for cooling load prediction of large public buildings, and helps to realize online optimization control of building air-conditioning systems, thereby providing effective data support and theoretical reference for building energy-saving management and operation.

[0081] This embodiment also discloses a system for predicting cooling load of a public building, including:

[0082] Initialization unit, configured as:

[0083] It is used to collect cooling load related data, pre-process them, and use the random forest method to process the processed related data to obtain the model input data set;

[0084] The model optimization unit is configured as follows:

[0085] It is used to optimize the SSA model with a good point set, and optimize the LSTM grid parameters based on the optimized SSA model to obtain the RF-ISSA-LSTM hybrid cold model;

[0086] Output unit, configured as:

[0087] Used to obtain cooling load prediction results based on the RF-ISSA-LSTM hybrid cooling model and the model input data set.

[0088] In another embodiment of the present invention, a computer device is provided, the computer device comprising a processor and a memory, the memory being used to store a computer program, the computer program comprising program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in a computer storage medium to implement a corresponding method flow or a corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the method for predicting the cooling load of a public building.

[0089] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for predicting the cooling load of public buildings described in the above embodiment.

[0090] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0092] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0094] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0095] In addition, it should be understood that although this specification is described in accordance with the implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation modes that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of ​​the present invention, and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for predicting cooling load of a public building, characterized in that: The following steps are involved: Collect cooling load related data, pre-process them, and use random forest method to process the pre-processed related data to obtain the model input data set; The SSA model is optimized using the good point set, and the LSTM grid parameters are optimized based on the optimized SSA model to obtain the RF-ISSA-LSTM hybrid cold model; Based on the RF-ISSA-LSTM hybrid cooling model and the model input data set, a cooling load prediction result is obtained.

2. The method for predicting cooling load of a public building according to claim 1, characterized in that: The cooling load related data includes input data and output data, wherein the input data includes: cooling load at the previous moment, dry bulb temperature, carbon dioxide, air temperature, dew point temperature, wind speed, solar radiation value at the previous moment, time, solar radiation value at the current moment, relative humidity and wind direction; The output data is the air conditioning cooling load at the current moment.

3. The method for predicting cooling load of a public building according to claim 1, characterized in that: The process of using the random forest method to process the processed related data is as follows: Based on the coupling phenomenon of the cooling load related data in the input data and the output data, features with an influence coefficient greater than 0.2 are preset, and the random forest method is used for feature selection.

4. The method for predicting cooling load of a public building according to claim 1, characterized in that: When the SSA model is optimized using the good point set, the formula for updating the search space phase of the SSA model is optimized as follows: Among them, ub j and lb j represent the upper and lower boundaries of the j-th dimension, respectively, and X i (j) is the value of the i-th best point in the j-th dimension, represents the value of the i-th point in the j-th dimension, and k is the number of iterations.

5. The method for predicting cooling load of a public building according to claim 1, characterized in that: The process of optimizing the LSTM grid parameters based on the optimized SSA model is as follows: The SSA model introduces an adaptive inertia weight to the producer position update: In the formula, iter max Indicates the maximum number of iterations, iter min represents the maximum number of iterations, t represents the current number of iterations, ω represents the adaptive inertia weight, and exp represents the natural exponential function.

6. The method for predicting cooling load of a public building according to claim 1, characterized in that: The RF-ISSA-LSTM hybrid cold model has a three-layer structure, which includes an input layer, an output layer and a hidden layer.

7. The method for predicting cooling load of a public building according to claim 6, characterized in that: The input layer is 10 layers, the output layer is 1 layer, and the hidden layer is 18 layers.

8. A system for predicting cooling load of public buildings, characterized in that: The method for predicting cooling load of a public building according to any one of claims 1 to 7 comprises: Initialization unit, configured as: It is used to collect cooling load related data, pre-process them, and use the random forest method to process the processed related data to obtain the model input data set; The model optimization unit is configured as follows: It is used to optimize the SSA model with a good point set, and optimize the LSTM grid parameters based on the optimized SSA model to obtain the RF-ISSA-LSTM hybrid cold model; Output unit, configured as: Used to obtain cooling load prediction results based on the RF-ISSA-LSTM hybrid cooling model and the model input data set.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for predicting cooling load of a public building as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting cooling load of a public building as described in any one of claims 1 to 7 are implemented.

Images