Building energy consumption prediction method and device

Abstract

The invention relates to the technical field of building energy, in particular to a building energy consumption prediction method and device.The method comprises the steps that a building energy consumption data set is obtained, and the building energy consumption data set comprises the electricity consumption, the water consumption, the heat consumption, the temperature, the humidity and the illumination intensity; preprocessing the building energy consumption data set to obtain a preprocessed building energy consumption data set; determining key features based on the preprocessed building energy consumption data set; based on the key features, determining a trained building energy consumption prediction model; and inputting the new building energy consumption data into the trained building energy consumption prediction model to obtain a predicted energy consumption result. According to the invention, accurate prediction and real-time monitoring of building energy consumption can be realized, the management efficiency is improved, and energy waste is reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of building energy technology, and in particular to a method and device for predicting building energy consumption. Background Art

[0002] Traditional building energy consumption management methods mainly rely on manual data collection and empirical analysis. These methods have many problems and limitations in practical applications. First, data collection is difficult. Traditional methods require manual regular collection of energy consumption data, which is time-consuming and prone to missing key information. Secondly, the analysis accuracy is low. Energy consumption management based on manual analysis is subjective and relies on experience, which makes it difficult to accurately reflect the actual situation of building energy consumption. Thirdly, real-time monitoring is difficult. Traditional methods cannot achieve real-time monitoring of building energy consumption, making it difficult to discover and solve energy waste problems in a timely manner. Finally, there is a lack of personalized solutions. Traditional methods cannot provide targeted energy-saving suggestions based on the characteristics of different buildings.

[0003] In view of this, this application is filed. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a method and device for predicting building energy consumption, which can achieve accurate prediction and real-time monitoring of building energy consumption, improve management efficiency, and reduce energy waste.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for predicting building energy consumption, the method comprising:

[0006] Acquire a building energy consumption data set, wherein the building energy consumption data set includes electricity usage, water usage, heat usage, temperature, humidity, and light intensity;

[0007] Preprocessing the building energy consumption data set to obtain a preprocessed building energy consumption data set;

[0008] Based on the preprocessed building energy consumption dataset, determining key features;

[0009] Based on the key features, determining a trained building energy consumption prediction model;

[0010] The new building energy consumption data is input into the trained building energy consumption prediction model to obtain the predicted energy consumption result.

[0011] In a second aspect, the present disclosure also provides a device for predicting building energy consumption, the device comprising:

[0012] A first acquisition module is used to acquire a building energy consumption data set, wherein the building energy consumption data set includes electricity usage, water usage, heat usage, temperature, humidity and light intensity;

[0013] A second acquisition module is used to preprocess the building energy consumption data set to obtain a preprocessed building energy consumption data set;

[0014] A first determination module, configured to determine key features based on the preprocessed building energy consumption data set;

[0015] A second determination module is used to determine a trained building energy consumption prediction model based on the key features;

[0016] The third acquisition module inputs the new building energy consumption data into the trained building energy consumption prediction model to obtain the predicted energy consumption result.

[0017] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the building energy consumption prediction method as described above.

[0018] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the building energy consumption prediction method as described above.

[0019] The disclosed embodiment provides a method for predicting building energy consumption, which obtains a building energy consumption data set, and preprocesses the building energy consumption data set to obtain a preprocessed building energy consumption data set; the building energy consumption data can be cleaned by preprocessing, reducing the sensitivity of random fluctuations in the data and the influence of outliers, improving the data quality for constructing a building energy consumption model, and improving the robustness of the building energy consumption model; then based on the preprocessed building energy consumption data set, key features are determined; based on the key features, a trained building energy consumption prediction model is determined; through the processing of key features, the data quality and the correlation between data can be further improved, and the robustness of the building energy consumption prediction model can be improved; finally, the new building energy consumption data is input into the trained building energy consumption prediction model to obtain the predicted energy consumption result. The disclosed method can realize accurate prediction and real-time monitoring of building energy consumption through a trained building energy consumption prediction model, improve management efficiency, and reduce energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0021] Figure 1 The present invention is a flowchart of a method for predicting building energy consumption in an embodiment of the present invention.

[0022] Figure 2 It is a structural schematic diagram of a building energy consumption prediction device in an embodiment of the present disclosure;

[0023] Figure 3 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0025] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0026] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0027] With the rapid development of artificial intelligence and machine learning technologies, new opportunities have emerged in the field of building energy consumption prediction and management. Machine learning algorithms can process large-scale building energy consumption data and achieve fast and accurate data analysis through pattern recognition and data mining techniques. These algorithms can not only learn the laws of building energy consumption from historical data, but also predict future energy consumption trends, providing scientific decision-making support for building managers. Machine learning models can sense changes in building energy consumption in real time and help managers to promptly discover and solve energy waste problems through intelligent monitoring systems. For example, by collecting real-time data through sensors installed inside the building, machine learning models can analyze this data, identify energy consumption anomalies, and automatically adjust the energy system to reduce energy consumption. Energy consumption prediction models based on machine learning algorithms can automatically identify energy efficiency issues and make corresponding suggestions, reducing interference from human factors. These models can provide building managers with more accurate energy consumption predictions and optimization suggestions by learning factors such as building usage patterns, environmental conditions, and user behavior. In addition, machine learning algorithms can provide personalized energy-saving suggestions based on different building types and environmental conditions. Since each building has different structures, usage functions, and geographical locations, its energy consumption characteristics are also different. Based on these differences, machine learning models can customize energy-saving solutions for different types of buildings, helping building managers develop more effective energy efficiency improvement plans. It not only solves the problems of traditional building energy consumption management methods, but also provides new ideas and approaches for energy conservation in the construction field. By combining big data analysis and machine learning algorithms, this method can achieve accurate prediction and real-time monitoring of building energy consumption, providing building managers with more effective energy efficiency optimization solutions.

[0028] In response to the above problems, the embodiments of the present disclosure provide a building energy consumption prediction method that can process a large amount of data and achieve accurate prediction and real-time monitoring of building energy consumption, reduce interference from human factors, and improve resource utilization.

[0029] Figure 1 : is a flow chart of a building energy consumption prediction method in an embodiment of the present disclosure. The method can be executed by a building energy consumption prediction device, which can be implemented in software and / or hardware, and can be configured in an electronic device. Figure 1 As shown, the method may specifically include the following steps:

[0030] S110. Obtain a building energy consumption data set, wherein the building energy consumption data set includes electricity consumption, water consumption, heat consumption, temperature, humidity, and light intensity.

[0031] Among them, the building energy consumption data set can be collected through smart metering equipment, sensor networks or building management systems. The building energy consumption data set includes parameters such as electricity consumption, water consumption, heat consumption, indoor temperature, outdoor temperature, humidity and light intensity.

[0032] S120: preprocess the building energy consumption dataset to obtain a preprocessed building energy consumption dataset.

[0033] In one embodiment, the preprocessing of the building energy consumption dataset to obtain the preprocessed building energy consumption dataset includes:

[0034] Standardizing and normalizing the building energy consumption data set to obtain a first processed data set;

[0035] Noise and outlier filtering is performed on the first processed data set to obtain a second processed data set.

[0036] Specifically, the parameters such as electricity consumption, water consumption, heat consumption, indoor temperature, outdoor temperature, humidity and light intensity in the building energy consumption data set have different dimensions and magnitudes, and need to be converted into a unified format to facilitate subsequent data processing. Therefore, each data in the building energy consumption data set is standardized and normalized to obtain the first processed data set. Specifically, all data are scaled to between 0 and 1, and formula (1) can be used for normalization, and then the normalized data are converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, and formula (2) can be used for normalization.

[0037]

[0038] Among them, x′ represents the normalized data, x″ represents the standardized data, x1 represents the building energy consumption data, σ represents the standard deviation of x′, and μ represents the mean of x′.

[0039] Then, the first processed data set is cleaned to remove noise and outliers that may affect the model performance, so as to improve data quality and ensure the effectiveness of model training and the reliability of prediction results.

[0040] In one embodiment, filtering the first processed data set for noise and outliers to obtain the second processed data set includes:

[0041] determining a standard deviation and a first mean of the first processed data set;

[0042] Determine a denoised data set using a denoising formula based on the first processed data set, the standard deviation and the first mean;

[0043] Determining a variance and a second mean of the denoised data set;

[0044] The denoised data set is filtered using an abnormality factor based on the denoised data set, the variance and the second mean to obtain a second processed data set.

[0045] Specifically, the first processed data set obtained in the above manner is used to calculate the variance and the first mean of the first processed data set, and the following denoising formula is used to perform noise filtering to obtain a denoised data set, and then the variance and the second mean of the denoised data set are calculated, and the following abnormal factor is used to perform abnormal value filtering to obtain a second processed data set, wherein,

[0046] The expression of the noise reduction formula is:

[0047]

[0048] Wherein, X represents the denoised data set, C1 represents the first processed data set, k1 represents the standard deviation, M1 represents the first mean of C1, and a1 represents the adjustable filtering weight factor;

[0049] The expression of the abnormal factor is:

[0050]

[0051] Where D represents the anomaly factor, X represents the denoised dataset, ρ represents the variance of X, μ represents the second mean of X, and V -1 represents the inverse of the covariance and T represents the transposed matrix.

[0052] By filtering noise, this embodiment can more clearly obtain useful signals in building energy consumption data, reduce overfitting caused by noise, and reduce the sensitivity of random fluctuations in the data; by filtering abnormal factors, the negative impact of abnormal values ​​on building energy consumption data can be reduced, thereby improving the accuracy of the data.

[0053] S130. Determine key features based on the preprocessed building energy consumption data set.

[0054] Specifically, the key features include statistical features, aggregation features, descriptive features and relationship features, and the key features are determined by using statistical features, aggregation features, descriptive features and relationship features.

[0055] In one embodiment, determining key features based on the pre-processed building energy consumption dataset includes:

[0056] Determining a column data set based on the preprocessed building energy consumption data set;

[0057] Based on the column data set, statistical features, aggregation features, descriptive features and relationship features are determined respectively.

[0058] It can be understood that the data in the preprocessed building energy consumption data set obtained by the above embodiment is stored in columns, and the columns can be stored according to parameters such as electricity consumption, water consumption, heat consumption, temperature, humidity and light intensity. For example, water consumption is stored in one column of data and electricity consumption is stored in one column of data. Depending on the amount of data, water consumption can also be stored in two columns of data, or at least three columns of data. Then, based on each column of data, the mean, median, variance, standard deviation, maximum value and minimum value of each column of data are calculated, and then the set of the mean, median, variance, standard deviation, maximum value and minimum value corresponding to all columns constitutes a statistical feature; wherein, the statistical feature can be represented by the symbol F0.

[0059] Aggregate Features:

[0060]

[0061] Describing features:

[0062]

[0063] Relationship characteristics:

[0064]

[0065] Among them, F1 represents the aggregation feature, f2 represents the description feature, F3 represents the relationship feature, N represents the number of data in the preprocessed building energy consumption dataset, and X i represents the i-th column data in the preprocessed building energy consumption dataset, X j represents the jth column of data in the preprocessed building energy consumption dataset, S σ Represents X j +X i The standard deviation of X ρ represents the standard deviation of the data in the i-th column of the preprocessed building energy consumption dataset, s represents the mean of the data in the i-th column of the preprocessed building energy consumption dataset, and || represents the norm sign.

[0066] The above-obtained F0, F1, F2, and F3 are fused to obtain the key feature P, which can be expressed as P = {F0, F1, F2, F3}.

[0067] S140. Based on the key features, determine a trained building energy consumption prediction model.

[0068] Specifically, based on the above embodiment, the key features are determined using the existing building energy consumption data. At this time, the key features are known, and then the building energy consumption prediction model is constructed using the key features. Then, the loss function is used to optimize the building energy consumption prediction model to obtain a trained building energy consumption prediction model.

[0069] Among them, the expression of the building energy consumption prediction model is:

[0070] The best model parameters, b * represents the optimal bias term of the model, ∈ represents the model penalty factor, and P is the key feature.

[0071] In one embodiment, the building energy consumption prediction model is optimized based on the loss function to determine the optimal model parameters and the optimal model bias items.

[0072] In the above building energy consumption prediction model, ω * and b * is the initial parameter of the model, which needs to be optimized using the loss function to obtain the best model parameter ω * and the model's optimal bias term b * .

[0073] Among them, the expression of the loss function is:

[0074]

[0075] Among them, L represents the loss function, N represents the number of data in the preprocessed building energy consumption dataset, and X i represents the i-th column data in the preprocessed building energy consumption dataset, X j represents the jth column of data in the preprocessed building energy consumption dataset, M(X i ,ω * ,b * ) indicates X i The predicted energy consumption result, ω * represents the optimal model parameter, b * represents the optimal bias term of the model, Represents X i and X j The geometric distribution density function of .

[0076] After obtaining the optimal model parameters and the optimal model bias, substitute them into the building energy consumption prediction model and update the optimal model parameters ω * and the model's optimal bias term b * , and obtain the trained building energy consumption prediction model.

[0077] S150: Input new building energy consumption data into the trained building energy consumption prediction model to obtain predicted energy consumption results.

[0078] It can be understood that, based on the above embodiments, a trained building energy consumption prediction model is obtained, and then new building energy consumption data is obtained, and the new building energy consumption data is input into the trained building energy consumption prediction model to obtain a predicted energy consumption result. Among them, the predicted energy consumption result can be a predicted energy consumption value at a certain point in the future. By analyzing the trend of the predicted energy consumption value changing over time, energy use can be controlled more accurately, unnecessary energy consumption can be reduced, and overall energy efficiency can be improved. It can also guide the intelligent building management system to perform self-optimization and automatically adjust the equipment operation parameters to adapt to actual energy consumption requirements.

[0079] It is understandable that the new building energy consumption data does not belong to the building energy consumption dataset. The building energy consumption dataset is equivalent to a sample dataset and is used to construct and optimize the building energy consumption prediction model.

[0080] The building energy consumption prediction method provided in this embodiment obtains a building energy consumption data set, and preprocesses the building energy consumption data set to obtain a preprocessed building energy consumption data set; the building energy consumption data can be cleaned by preprocessing, reducing the sensitivity of random fluctuations in the data and the influence of outliers, improving the data quality of building energy consumption models, and improving the robustness of building energy consumption models; then based on the preprocessed building energy consumption data set, key features are determined; based on the key features, a trained building energy consumption prediction model is determined; through the processing of key features, data quality and correlation between data can be further improved, and the robustness of the building energy consumption prediction model can be improved; finally, the new building energy consumption data is input into the trained building energy consumption prediction model to obtain predicted energy consumption results. The present disclosure can realize accurate prediction and real-time monitoring of building energy consumption through a trained building energy consumption prediction model, improve management efficiency, and reduce energy waste.

[0081] Figure 2 FIG. 1 is a schematic diagram of the structure of a building energy consumption prediction device in an embodiment of the present disclosure. Figure 2 As shown: the device includes: a first acquisition module 210, a second acquisition module 220, a first determination module 230, a second determination module 240 and a third acquisition module 250.

[0082] A first acquisition module 210 is used to acquire a building energy consumption data set, wherein the building energy consumption data set includes electricity usage, water usage, heat usage, temperature, humidity and light intensity;

[0083] A second acquisition module 220 is used to preprocess the building energy consumption data set to obtain a preprocessed building energy consumption data set;

[0084] A first determination module 230, configured to determine key features based on the preprocessed building energy consumption data set;

[0085] A second determination module 240 is used to determine a trained building energy consumption prediction model based on the key features;

[0086] The third acquisition module 250 inputs the new building energy consumption data into the trained building energy consumption prediction model to obtain the predicted energy consumption result.

[0087] Optionally, the second acquisition module 220 is further used to standardize and normalize the building energy consumption data set to obtain a first processed data set;

[0088] Noise and outlier filtering is performed on the first processed data set to obtain a second processed data set.

[0089] Optionally, the second acquisition module 220 is further used to determine a standard deviation and a first mean of the first processed data set;

[0090] Determine a denoised data set using a denoising formula based on the first processed data set, the standard deviation and the first mean;

[0091] Determining a variance and a second mean of the denoised data set;

[0092] The denoised data set is filtered using an abnormality factor based on the denoised data set, the variance and the second mean to obtain a second processed data set.

[0093] The noise reduction formula is expressed as:

[0094]

[0095] Wherein, X represents the denoised data set, C1 represents the first processed data set, k1 represents the standard deviation, M1 represents the first mean of C1, and a1 represents the adjustable filtering weight factor;

[0096] The expression of the abnormal factor is:

[0097]

[0098] Where D represents the anomaly factor, X represents the denoised dataset, ρ represents the variance of X, μ represents the second mean of X, and V -1 represents the inverse of the covariance and T represents the transposed matrix.

[0099] Optionally, the first determination module is further used to determine a column data set based on the preprocessed building energy consumption data set;

[0100] Based on the column data set, statistical features, aggregation features, descriptive features and relationship features are determined respectively.

[0101] The expression of the aggregation feature is:

[0102]

[0103] The expression describing the feature is:

[0104] The expression of the relationship feature is:

[0105]

[0106] Among them, F1 represents the aggregation feature, F2 represents the description feature, F3 represents the relationship feature, N represents the number of data in the preprocessed building energy consumption dataset, and X i represents the i-th column data in the preprocessed building energy consumption dataset, X j represents the jth column of data in the preprocessed building energy consumption dataset, S σ Represents X j +X i The standard deviation of X ρ represents the standard deviation of the data in the i-th column of the preprocessed building energy consumption dataset, s represents the mean of the data in the i-th column of the preprocessed building energy consumption dataset, and || represents the norm sign.

[0107] Optionally, the device also includes a third determination module, which is used to optimize the building energy consumption prediction model based on the loss function and determine the optimal model parameters and the optimal model bias item.

[0108] Among them, the expression of the loss function is:

[0109]

[0110] Among them, L represents the loss function, N represents the number of data in the preprocessed building energy consumption dataset, and X i represents the i-th column data in the preprocessed building energy consumption dataset, X j represents the jth column of data in the preprocessed building energy consumption dataset, M(X i ,ω * ,b * ) indicates X i The predicted energy consumption result, ω * represents the optimal model parameter, b * represents the optimal bias term of the model, Represents X i and X j The geometric distribution density function

[0111] The building energy consumption prediction device provided in the embodiment of the present disclosure can execute the steps in the building energy consumption prediction method provided in the method embodiment of the present disclosure, and the execution steps and beneficial effects are no longer repeated here.

[0112] Figure 3Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 3 , which shows a structural schematic diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0113] like Figure 3 As shown, the electronic device 500 may include a processing device 501, a ROM 502, a RAM 503, a bus 504, an input / output (I / O) interface 505, an input device 506, an output device 507, a storage device 508, and a communication device 509. The processing device (e.g., a central processing unit, a graphics processor, etc.) 501 can perform various appropriate actions and processes to implement the method of the embodiment described in the present disclosure according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage device 508 to the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0114] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart, thereby implementing the building energy consumption prediction method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above functions defined in the method of the embodiment of the present disclosure are executed.

[0115] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0116] The computer-readable medium may be included in the electronic device; or it may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a building energy consumption data set, wherein the building energy consumption data set includes electricity consumption, water consumption, heat consumption, temperature, humidity and light intensity; preprocesses the building energy consumption data set to obtain a preprocessed building energy consumption data set; determines key features based on the preprocessed building energy consumption data set; determines a trained building energy consumption prediction model based on the key features; inputs new building energy consumption data into the trained building energy consumption prediction model to obtain predicted energy consumption results.

[0117] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0118] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0119] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

Claims

1. A method for predicting building energy consumption, characterized in that: The method comprises: Acquire a building energy consumption data set, wherein the building energy consumption data set includes electricity usage, water usage, heat usage, temperature, humidity, and light intensity; Preprocessing the building energy consumption data set to obtain a preprocessed building energy consumption data set; Based on the preprocessed building energy consumption dataset, determining key features; Based on the key features, determining a trained building energy consumption prediction model; The new building energy consumption data is input into the trained building energy consumption prediction model to obtain the predicted energy consumption result.

2. The method according to claim 1, characterized in that: The preprocessing of the building energy consumption data set to obtain a preprocessed building energy consumption data set includes: Standardizing and normalizing the building energy consumption data set to obtain a first processed data set; Noise and outlier filtering is performed on the first processed data set to obtain a second processed data set.

3. The method according to claim 2, characterized in that The filtering of the first processed data set for noise and outliers to obtain a second processed data set includes: determining a standard deviation and a first mean of the first processed data set; Determine a denoised data set using a denoising formula based on the first processed data set, the standard deviation and the first mean; Determining a variance and a second mean of the denoised data set; Based on the denoised data set, the variance and the second mean, the denoised data set is filtered using an abnormal factor to obtain a second processed data set.

4. The method according to claim 3, characterized in that The expression of the noise reduction formula is: Wherein, X represents the denoised data set, C1 represents the first processed data set, k1 represents the standard deviation, M1 represents the first mean of C1, and a1 represents the adjustable filtering weight factor; The expression of the abnormal factor is: Where D represents the anomaly factor, X represents the denoised dataset, ρ represents the variance of X, v represents the second mean of X, and V -1 represents the inverse of the covariance and T represents the transposed matrix.

5. The method according to claim 1, characterized in that The key features include statistical features, aggregation features, descriptive features and relationship features. The key features are determined based on the pre-processed building energy consumption data set, including: Determining a column data set based on the preprocessed building energy consumption data set; Based on the column data set, statistical features, aggregation features, descriptive features and relationship features are determined respectively.

6. The method according to claim 5, characterized in that The expression of the aggregation feature is: The expression describing the feature is: The expression of the relationship feature is: Among them, F1 represents the aggregation feature, F2 represents the description feature, F3 represents the relationship feature, N represents the number of data in the preprocessed building energy consumption dataset, and X i represents the i-th column data in the preprocessed building energy consumption dataset, X j represents the jth column of data in the preprocessed building energy consumption dataset, S σ Represents X j +X i The standard deviation of X ρ represents the standard deviation of the data in the i-th column of the preprocessed building energy consumption dataset, s represents the mean of the data in the i-th column of the preprocessed building energy consumption dataset, and || represents the norm sign.

7. The method according to claim 1, characterized in that The expression of the building energy consumption prediction model is: The best model parameters, b * represents the optimal bias term of the model, ∈ represents the model penalty factor, and P is the key feature.

8. The method according to claim 7, characterized in that The method further comprises: The building energy consumption prediction model is optimized based on the loss function to determine the optimal model parameters and the optimal model bias items.

9. The method according to claim 6, characterized in that The expression of the loss function is: Among them, L represents the loss function, N represents the number of data in the preprocessed building energy consumption dataset, and X i represents the i-th column data in the preprocessed building energy consumption dataset, X j represents the jth column of data in the preprocessed building energy consumption dataset, M(X i ,ω * ,b * ) indicates X i The predicted energy consumption result, ω * represents the optimal model parameter, b * represents the optimal bias term of the model, Represents X i and X j The geometric distribution density function of .

10. A building energy consumption prediction device, characterized in that: include: A first acquisition module is used to acquire a building energy consumption data set, wherein the building energy consumption data set includes electricity consumption, water consumption, heat consumption, temperature, humidity and light intensity; A second acquisition module is used to preprocess the building energy consumption data set to obtain a preprocessed building energy consumption data set; A first determination module, configured to determine key features based on the preprocessed building energy consumption data set; A second determination module is used to determine a trained building energy consumption prediction model based on the key features; The third acquisition module inputs the new building energy consumption data into the trained building energy consumption prediction model to obtain the predicted energy consumption result.

Images