Building Energy Consumption Prediction Method, System, Terminal and Medium Based on Multifactor Decomposition

Abstract

The present invention discloses a building energy consumption prediction method, system, terminal and medium based on multi-factor decomposition, which relates to the technical field of building energy consumption prediction. The key points of its technical solution are as follows: The present invention divides multiple factors affecting building energy consumption into environmental conditions considered from a global perspective, energy consumption activities considered from a local perspective, and behavioral characteristics considered from a detailed perspective. When the overall trend of the influence of environmental conditions on building energy consumption is characterized by basic electricity consumption data and an electricity consumption variable coefficient function, the associated influence between energy consumption activities, behavioral characteristics and environmental conditions can be simultaneously excavated, and accurate prediction of building energy consumption can be realized through limited sample data.

Description

Technical Field

[0001] The present invention relates to the technical field of building energy consumption prediction, and more specifically, to a building energy consumption prediction method, system, terminal and medium based on multi-factor decomposition. Background Art

[0002] Building energy consumption mainly refers to the electric energy consumed by a building during normal operation to meet the requirements of its internal environmental comfort, lighting, equipment operation, etc. Predicting building energy consumption can provide basic data for formulating energy-saving measures and power peak shaving.

[0003] The influencing factors of building energy consumption are diverse, such as building design parameters, climate conditions, and usage behaviors. Building design parameters include building shape and orientation, lighting and ventilation design, thermal insulation treatment of building envelopes, etc. The building energy consumption prediction methods recorded in the prior art mainly use prediction models based on machine learning algorithms and deep learning algorithms for prediction. Prediction models based on machine learning algorithms such as support vector regression, artificial neural network, etc., and prediction models based on deep learning algorithms such as recurrent neural network, autoencoder, generative adversarial network, etc. All of the above prediction models require a large amount of labeled sample data during the training process, and when the building surrounding environment is difficult to replicate, the reliability of the sample data is difficult to guarantee, which easily leads to poor prediction effects when the above prediction models are applied to new buildings or buildings with obvious differences. In addition, in the case of limited sample data, the above prediction models are difficult to discover the associated effects between different influencing factors, resulting in poor accuracy of building energy consumption prediction.

[0004] Therefore, how to research and design a building energy consumption prediction method, system, terminal and medium based on multi-factor decomposition that can overcome the above defects is an urgent problem for us to solve at present. Summary of the Invention

[0005] To solve the deficiencies in the prior art, the purpose of the present invention is to provide a building energy consumption prediction method, system, terminal and medium based on multi-factor decomposition, which divides multiple factors affecting building energy consumption into environmental conditions considered from a global perspective, energy consumption activities considered from a local perspective, and behavior characteristics considered from details. While characterizing the overall trend of building energy consumption affected by environmental conditions through basic electricity consumption data and electricity consumption variable coefficient functions, it simultaneously discovers the associated effects between energy consumption activities, behavior characteristics and environmental conditions, and can achieve accurate prediction of building energy consumption through limited sample data.

[0006] The above technical purpose of the present invention is achieved through the following technical solutions:

[0007] In the first aspect, a building energy consumption prediction method based on multi-factor decomposition is provided, including the following steps:

[0008] Collect the hourly and daily electricity consumption data of each target building in the target area;

[0009] Perform grid processing on the target area, and perform de-weighting processing on the corresponding total daily electricity consumption data according to the total building area in each grid unit to obtain the initial grid electricity consumption data of the target area at the daily level;

[0010] Obtain the energy consumption activity information of the target area at the daily level, and split the initial grid electricity consumption data into the first grid electricity consumption data with energy consumption activities and the second grid electricity consumption data without energy consumption activities;

[0011] Extract the daily electricity consumption data affected by environmental conditions in the target area from the second grid electricity consumption data, and obtain the basic electricity consumption data and electricity consumption variable coefficient function of the target area through fitting analysis of multiple daily electricity consumption data within a preset period;

[0012] Calculate the activity electricity consumption data affected by energy consumption activities by subtracting the basic electricity consumption data from the first grid electricity consumption data, and train and construct an activity electricity consumption function based on the activity types and electricity consumption variable coefficients of multiple activity electricity consumption data;

[0013] Calculate the estimated electricity consumption data based on the product of the basic electricity consumption data and the building area of the target building, calculate the daily fluctuation electricity consumption data of the corresponding target building by subtracting the estimated electricity consumption data from the daily electricity consumption data, and determine the hourly deterministic electricity consumption fluctuation feature set of the target building by combining the daily fluctuation electricity consumption data of the target building and the hourly electricity consumption data of multiple days;

[0014] Combine the basic electricity consumption data, electricity consumption variable coefficient function, activity electricity consumption function and deterministic electricity consumption fluctuation characteristics to achieve energy consumption prediction of the target building at the hourly level.

[0015] Further, the process of performing de-weighting processing on the corresponding total daily electricity consumption data according to the total building area in each grid unit is specifically as follows:

[0016] Divide the standard building area by the total building area in each grid unit to obtain the de-weighting coefficient of each grid unit;

[0017] Multiply the total daily electricity consumption data of each grid unit by the de-weighting coefficient to obtain the de-weighted electricity consumption data of each grid unit;

[0018] Combine the de-weighted electricity consumption data of each grid unit to form the initial grid electricity consumption data of the target area at the daily level.

[0019] Further, the calculation formula of the daily electricity consumption data is specifically as follows:

[0020] ;

[0021] Or, it is:

[0022] ;

[0023] Wherein, represents the daily electricity consumption data of the target area affected by environmental conditions on the th day; represents the ex - rights electricity consumption data of the th grid cell on the th day after ex - rights; represents the number of grid cells in the second grid electricity data.

[0024] Furthermore, the expressions of the basic electricity consumption data and the electricity consumption variable coefficient function of the target area are specifically:

[0025] ;

[0026] Wherein, represents the daily electricity consumption data of the target area affected by environmental conditions on the th day; represents the standard building area; represents the basic electricity consumption data of the target area; represents the th day's electricity consumption variable coefficient; represents the electricity consumption variable coefficient function.

[0027] Furthermore, the expression of the activity electricity consumption function is specifically:

[0028] ;

[0029] Wherein, represents the activity electricity consumption data corresponding to the activity type on the th day; represents the activity electricity consumption function; represents the th day's electricity consumption variable coefficient.

[0030] Furthermore, the calculation formula of the deterministic electricity consumption fluctuation feature set is specifically:

[0031] ;

[0032] Wherein, represents the daily - level electricity consumption data of the target building on the th day; represents the basic electricity consumption data of the target area; Represents the floor area of the target building ; Represents the daily fluctuation power consumption data of the target building in the th daily period; Represents the random power consumption fluctuation characteristics of the target building in the th daily period; Represents the power consumption fluctuation characteristics of the target building in the th daily period and the th hour. If the power consumption fluctuation characteristics of the same hour corresponding to the target building in different daily periods are different, the corresponding deterministic power consumption fluctuation characteristic value is 0; Represents the quantity of daily-level power consumption data; Represents the deterministic power consumption fluctuation characteristics of the target building in the th hour; Represents the power consumption fluctuation characteristics of the target building in the th daily period and the th hour; Represents the set of deterministic power consumption fluctuation characteristics of the target building at the hour level; Represents the deterministic power consumption fluctuation characteristics of the target building in the 1st hour; Represents the deterministic power consumption fluctuation characteristics of the target building in the 24th hour.

[0033] Furthermore, the process of realizing the energy consumption prediction of the target building at the hour level by combining the basic power consumption data, the power consumption variable coefficient function, the activity power consumption function, and the deterministic power consumption fluctuation characteristics is specifically as follows:

[0034] Using the basic power consumption data and the power consumption variable coefficient function to predict the basic power consumption data of the target area in the next daily period;

[0035] Estimating the activity power consumption data of the target area in the next daily period through the activity reporting information and the activity power consumption function;

[0036] Combining the basic power consumption data, the activity power consumption data of the target area in the next daily period, and the set of deterministic power consumption fluctuation characteristics of each target building to determine the energy consumption prediction result of the target building at the hour level.

[0037] In the second aspect, a building energy consumption prediction system based on multi-factor decomposition is provided. This system is used to implement the building energy consumption prediction method based on multi-factor decomposition described in any item of the first aspect, including: ​

[0038] A data acquisition module, configured to acquire hourly electricity consumption data and daily electricity consumption data of each target building in a target area;

[0039] A data de-weighting module, configured to perform grid processing on the target area, and de-weight the corresponding total daily electricity consumption data according to the total building area in each grid unit to obtain the initial grid electricity consumption data of the target area at the daily level;

[0040] A data splitting module, configured to obtain the energy consumption activity information of the target area at the daily level, and split the initial grid electricity consumption data into first grid electricity consumption data with energy consumption activities and second grid electricity consumption data without energy consumption activities;

[0041] An environmental analysis module, configured to extract the daily electricity consumption data affected by environmental conditions in the target area from the second grid electricity consumption data, and obtain the basic electricity consumption data and electricity consumption variable coefficient function of the target area through fitting analysis based on multiple daily electricity consumption data within a preset period;

[0042] An activity analysis module, configured to calculate the activity electricity consumption data affected by energy consumption activities by taking the difference between the first grid electricity consumption data and the basic electricity consumption data, and train and construct an activity electricity consumption function based on the activity types and electricity consumption variable coefficients of multiple activity electricity consumption data;

[0043] A fluctuation analysis module, configured to calculate the estimated electricity consumption data based on the product of the basic electricity consumption data and the building area of the target building, calculate the daily fluctuation electricity consumption data of the corresponding target building by taking the difference between the daily electricity consumption data and the estimated electricity consumption data, and determine the deterministic electricity consumption fluctuation feature set of the target building at the hourly level in combination with the daily fluctuation electricity consumption data of the target building and the hourly electricity consumption data of multiple days;

[0044] An energy consumption prediction module, configured to realize the hourly energy consumption prediction of the target building by combining the basic electricity consumption data, the electricity consumption variable coefficient function, the activity electricity consumption function and the deterministic electricity consumption fluctuation features.

[0045] In a third aspect, a computer terminal is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for predicting building energy consumption based on multi-factor decomposition as described in any one of the first aspects is implemented.

[0046] In a fourth aspect, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for predicting building energy consumption based on multi-factor decomposition as described in any one of the first aspects can be implemented.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The building energy consumption prediction method based on multi-factor decomposition provided by the present invention divides multiple factors affecting building energy consumption into environmental conditions considered from a global perspective, energy consumption activities considered from a local perspective, and behavioral characteristics considered in detail. When the overall trend of building energy consumption affected by environmental conditions is characterized by basic electricity consumption data and an electricity variable coefficient function, the associated impacts between energy consumption activities, behavioral characteristics, and environmental conditions are simultaneously mined, enabling accurate prediction of building energy consumption through limited sample data;

[0049] 2. When the present invention characterizes the overall trend of building energy consumption affected by environmental conditions through basic electricity consumption data and an electricity variable coefficient function, under the condition that the basic electricity consumption data remains unchanged within a certain period, multiple influencing factors are integrated into a single factor for fitting prediction, simplifying the difficulty of overall trend prediction;

[0050] 3. When analyzing the deterministic electricity consumption fluctuation feature set, the present invention can adaptively update the deterministic electricity consumption fluctuations according to the changes in basic electricity consumption data, and can effectively improve the prediction accuracy of building energy consumption at the hourly level during the process of environmental condition trend changes or oscillatory changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, form a part of this application, and do not limit the embodiments of the present invention. In the drawings:

[0052] Figure 1 is the flowchart in Embodiment 1 of the present invention;

[0053] Figure 2 is the system block diagram in Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the embodiments and the drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and do not limit the present invention.

[0055] Embodiment 1: The building energy consumption prediction method based on multi-factor decomposition, as Figure 1 shown, includes the following steps:

[0056] S1: Collect the hourly electricity consumption data and daily electricity consumption data of each target building in the target area;

[0057] S2: Perform grid processing on the target area, and perform de-weighting processing on the corresponding total daily electricity consumption data according to the total building area within each grid unit to obtain the initial grid electricity consumption data of the target area at the daily level;

[0058] S3: Obtain the energy consumption activity information of the target area at the daily level, and split the initial grid electricity consumption data into the first grid electricity consumption data with energy consumption activities and the second grid electricity consumption data without energy consumption activities;

[0059] S4: Extract the daily electricity consumption data affected by environmental conditions within the target area from the second grid electricity consumption data, and obtain the basic electricity consumption data and electricity consumption variable coefficient function of the target area through fitting analysis based on multiple daily electricity consumption data within a preset period;

[0060] S5: Calculate the activity electricity consumption data affected by energy consumption activities by taking the difference between the first grid electricity consumption data and the basic electricity consumption data, and train and construct an activity electricity consumption function based on the activity types and electricity consumption variable coefficients of multiple activity electricity consumption data;

[0061] S6: Calculate the estimated electricity consumption data by multiplying the basic electricity consumption data by the building area of the target building, calculate the daily fluctuation electricity consumption data of the corresponding target building by taking the difference between the daily-level electricity consumption data and the estimated electricity consumption data, and determine the hourly deterministic electricity consumption fluctuation feature set of the target building by combining the daily fluctuation electricity consumption data of the target building and the hourly electricity consumption data of multiple days;

[0062] S7: Combine the basic electricity consumption data, electricity consumption variable coefficient function, activity electricity consumption function and deterministic electricity consumption fluctuation characteristics to achieve hourly energy consumption prediction of the target building.

[0063] In step S1, the division of the target area can be determined according to the number of buildings or the area of the region, and there is no restriction here. Generally, the scale of the number of buildings in the target area can reach the hundreds or thousands.

[0064] It should be noted that each target building in a target area needs to be of the same type of building, such as all residential buildings or all commercial buildings.

[0065] The hourly electricity consumption data collected in the present invention refers to collecting data once per hour, and the data of one day constitutes an hourly sequence. The daily-level electricity consumption data refers to collecting data once per day, and the data continuously collected multiple times within a cycle constitutes a daily-level sequence.

[0066] In step S2, when the target area is being gridded, it can be evenly divided with the same specifications, or unevenly divided according to the distribution of the target buildings, and there is no restriction here.

[0067] Considering that there are differences in the building areas of the corresponding target buildings in each grid cell, this will also lead to differences in electricity consumption data. Therefore, in order to process data in the same dimension, the present invention performs de-weighting processing on the corresponding total daily electricity consumption data according to the total building area in each grid cell. The specific process is as follows: Divide the standard building area by the total building area in each grid cell to obtain the de-weighting coefficient of each grid cell; Multiply the total daily electricity consumption data of each grid cell by the de-weighting coefficient to obtain the de-weighted electricity consumption data of each grid cell; Combine the de-weighted electricity consumption data of each grid cell to form the initial grid electricity consumption data of the target area at the daily level.

[0068] It should be noted that the standard building area can be the area of a basic unit, that is, the standard building area is regarded as "1". The standard building area can also be other values, which are not restricted here.

[0069] In step S3, the energy consumption activity information refers to activities that have energy consumption behaviors and have been reported, such as concerts, commercial performance activities, etc. Since the distance of an activity can easily cause drastic fluctuations in electricity consumption data, it is necessary to split the initial grid electricity consumption data into the first grid electricity consumption data with energy consumption activities and the second grid electricity consumption data without energy consumption activities.

[0070] In step S4, although the second grid electricity consumption data does not contain the overall data of the target area, the purpose of the present invention is to analyze the overall trend. Therefore, the average electricity consumption level determined by the second grid electricity consumption data is used to equivalently replace the average electricity consumption level of the target area.

[0071] As an alternative implementation manner, the calculation formula of the daily electricity consumption data is specifically:

[0072] ;

[0073] Among them, represents the daily electricity consumption data of the target area affected by environmental conditions on the th day; represents the de-weighted electricity consumption data of the th grid cell on the th day after de-weighting; represents the number of grid cells in the second grid electricity consumption data.

[0074] As another alternative implementation manner, in addition to using the average value as the average electricity consumption level, the value under the condition of minimum fluctuation can also be used as the average electricity consumption level. The calculation formula of the daily electricity consumption data is specifically:

[0075] ;

[0076] Among them, indicating the daily electricity consumption data of the target area affected by environmental conditions on the th day; indicating the detrended electricity consumption data of the th grid cell on the th day; indicating the number of grid cells in the second grid electricity data.

[0077] In this embodiment, the expressions of the basic electricity consumption data and the electricity consumption variable coefficient function of the target area are specifically:

[0078] ;

[0079] where indicates the daily electricity consumption data of the target area affected by environmental conditions on the th day; indicates the standard building area; indicates the basic electricity consumption data of the target area; indicates the electricity consumption variable coefficient on the th day; indicates the electricity consumption variable coefficient function.

[0080] It should be noted that the electricity consumption variable coefficient function generally adopts a non-linear function, such as , and the specific expression of the electricity consumption variable coefficient function is determined by historical data analysis, and the change trend of the electricity consumption variable coefficient function is also determined by historical data.

[0081] In step S5, the active electricity consumption function can be constructed by methods such as linear regression, decision tree, and deep learning. The independent variables of the active electricity consumption function include the activity type and the electricity consumption variable coefficient, and the dependent variable is the active electricity consumption data.

[0082] The expression of the active electricity consumption function is specifically:

[0083] ;

[0084] where indicates the active electricity consumption data corresponding to the activity type on the th day; indicates the active electricity consumption function; indicates the electricity consumption variable coefficient on the th day.

[0085] It should be noted that the active electricity consumption function is also a non-linear function. The specific expression of the active electricity consumption function is determined by historical data analysis, and its change trend is also determined by historical data.

[0086] In step S6, the calculation formula for the deterministic electricity consumption fluctuation feature set is specifically as follows:

[0087] ;

[0088] where, represents the daily electricity consumption data of the target building in the th daily period; represents the basic electricity consumption data of the target area; represents the building area of the target building ; represents the daily fluctuation electricity consumption data of the target building in the th daily period; represents the random electricity consumption fluctuation feature of the target building in the th daily period; represents the electricity consumption fluctuation feature of the target building in the th daily period and the th hour. If the electricity consumption fluctuation features of the target building at the same hour in different daily periods are different, the corresponding value of the deterministic electricity consumption fluctuation feature is 0; represents the quantity of the daily electricity consumption data; represents the deterministic electricity consumption fluctuation feature of the target building in the th hour; represents the electricity consumption fluctuation feature of the target building in the th daily period and the th hour; represents the deterministic electricity consumption fluctuation feature set of the target building at the hourly level; ; represents the deterministic electricity consumption fluctuation feature of the target building at the 1st hour; represents the deterministic electricity consumption fluctuation feature of the target building at the 24th hour.

[0089] It should be noted that the daily fluctuation electricity consumption data is composed of the random electricity consumption fluctuation feature and the deterministic electricity consumption fluctuation feature. When dividing the deterministic electricity consumption fluctuation feature and the random electricity consumption fluctuation feature, either the th daily period can be compared with the th daily period, or the th daily period can be compared with the Compare with the daily data. In order to ensure the stability of the prediction results, it is necessary to extract as many deterministic electricity consumption fluctuation features as possible. Therefore, it is necessary to use the minimum sum of the absolute values of the random electricity consumption fluctuation features as the constraint condition.

[0090] In step S7, the process of realizing the hourly energy consumption prediction of the target building by combining the basic electricity consumption data, the electricity consumption variable coefficient function, the activity electricity consumption function, and the deterministic electricity consumption fluctuation features is as follows: Use the basic electricity consumption data and the electricity consumption variable coefficient function to predict the basic electricity consumption data of the target area in the next daily period; Estimate the activity electricity consumption data of the target area in the next daily period through the activity reporting information and the activity electricity consumption function; Combine the basic electricity consumption data, the activity electricity consumption data of the target area in the next daily period, and the deterministic electricity consumption fluctuation feature sets of each target building to determine the hourly energy consumption prediction results of the target building.

[0091] Specifically, the sum of the basic electricity consumption data and the activity electricity consumption data of the target area in the next daily period can calculate the overall electricity consumption situation of the target area in the next daily period. Adding the deterministic electricity consumption fluctuation feature set of the target building at the hourly level can calculate the hourly energy consumption prediction results of the target building.

[0092] Embodiment 2: A building energy consumption prediction system based on multi-factor decomposition. This system is used to implement the building energy consumption prediction method based on multi-factor decomposition as described in Embodiment 1, as Figure 2 shown, including a data collection module, a data de-weighting module, a data splitting module, an environmental analysis module, an activity analysis module, a fluctuation analysis module, and an energy consumption prediction module.

[0093] Among them, the data acquisition module is used to collect hourly electricity consumption data and daily electricity consumption data of each target building in the target area; the data de-weighting module is used to perform grid processing on the target area and de-weight the corresponding total daily electricity consumption data according to the total building area in each grid unit to obtain the initial grid electricity consumption data of the target area at the daily level; the data splitting module is used to obtain the energy consumption activity information of the target area at the daily level and split the initial grid electricity consumption data into the first grid electricity consumption data with energy consumption activities and the second grid electricity consumption data without energy consumption activities; the environmental analysis module is used to extract the daily electricity consumption data affected by environmental conditions in the target area from the second grid electricity consumption data, and fit and analyze multiple daily electricity consumption data within a preset period to obtain the basic electricity consumption data and the electricity consumption variable coefficient function of the target area; the activity analysis module is used to calculate the activity electricity consumption data affected by energy consumption activities by subtracting the basic electricity consumption data from the first grid electricity consumption data, and train and construct an activity electricity consumption function based on the activity types and electricity consumption variable coefficients of multiple activity electricity consumption data; the fluctuation analysis module is used to calculate the estimated electricity consumption data according to the product of the basic electricity consumption data and the building area of the target building, calculate the daily fluctuation electricity consumption data of the corresponding target building by subtracting the estimated electricity consumption data from the daily electricity consumption data, and determine the deterministic electricity consumption fluctuation feature set of the target building at the hourly level by combining the daily fluctuation electricity consumption data of the target building and the hourly electricity consumption data of multiple days; the energy consumption prediction module is used to realize the hourly energy consumption prediction of the target building by combining the basic electricity consumption data, the electricity consumption variable coefficient function, the activity electricity consumption function and the deterministic electricity consumption fluctuation features.

[0094] The present invention also records a computer terminal, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the building energy consumption prediction method based on multi-factor decomposition as recorded in Embodiment 1.

[0095] The present invention also records a computer-readable medium, on which a computer program is stored. When the computer program is executed by a processor, it can implement the building energy consumption prediction method based on multi-factor decomposition as recorded in Embodiment 1.

[0096] Working principle: The present invention divides multiple factors affecting building energy consumption into environmental conditions considered from a global perspective, energy consumption activities considered from a local perspective, and behavioral characteristics considered in detail. When the overall trend of building energy consumption affected by environmental conditions is characterized by basic electricity consumption data and an electricity consumption variable coefficient function, the associated impacts among energy consumption activities, behavioral characteristics, and environmental conditions are simultaneously explored, enabling accurate prediction of building energy consumption with limited sample data. In addition, when the overall trend of building energy consumption affected by environmental conditions is characterized by basic electricity consumption data and an electricity consumption variable coefficient function, and the basic electricity consumption data remains unchanged within a certain period, multiple influencing factors are integrated into a single factor for fitting prediction, simplifying the difficulty of overall trend prediction. Moreover, when analyzing the deterministic electricity consumption fluctuation feature set, the present invention can adaptively update the deterministic electricity consumption fluctuations according to changes in the basic electricity consumption data, effectively improving the prediction accuracy of building energy consumption at the hourly level during the process of environmental condition trend changes or oscillatory changes.

[0097] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can 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.

[0098] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows 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 the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or multiple flows and / or blocks

[0099] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the flows Figure 1 or multiple flows and / or blocks

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to generate a computer-implemented process, thereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one process or multiple processes and / or one block or multiple blocks in the flow Figure 1 one process or multiple processes and / or blocks Figure 1 steps of the functions specified in one block or multiple blocks.

[0101] The specific embodiments described above further elaborate on the objectives, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The building energy consumption prediction method based on multi-factor decomposition is characterized by: The following steps are involved: Collect hourly and daily electricity consumption data of each target building in the target area; Grid the target area, and divide the corresponding total daily electricity consumption data according to the total building area in each grid unit to obtain the initial grid electricity consumption data of the target area at the daily level; Obtaining energy consumption activity information of the target area at the daily level, and splitting the initial grid power consumption data into first grid power consumption data with energy consumption activities and second grid power consumption data without energy consumption activities; Extract daily electricity consumption data affected by environmental conditions in the target area from the second grid electricity consumption data, and obtain basic electricity consumption data and electricity consumption variable coefficient function of the target area based on fitting analysis of multiple daily electricity consumption data in a preset period; The activity electricity consumption data affected by the energy consumption activity is calculated by the difference between the first grid electricity consumption data and the basic electricity consumption data, and the activity electricity consumption function is constructed based on the activity types and electricity consumption variable coefficients of the multiple activity electricity consumption data; The estimated electricity consumption data is calculated based on the product of the basic electricity consumption data and the building area of ​​the target building, and the daily fluctuation electricity consumption data of the corresponding target building is calculated based on the difference between the daily electricity consumption data and the estimated electricity consumption data. In addition, the deterministic electricity consumption fluctuation feature set of the target building at the hourly level is determined by combining the daily fluctuation electricity consumption data of the target building and the hourly electricity consumption data of multiple days; Combine basic electricity consumption data, electricity consumption variable coefficient function, activity electricity consumption function and deterministic electricity consumption fluctuation characteristics to achieve hourly energy consumption prediction of target buildings; The basic electricity consumption data and electricity consumption variable coefficient function of the target area are specifically expressed as follows: Among them, Q h,d represents the daily electricity consumption data of the target area affected by environmental conditions on the dth day; S0 represents the standard building area; Q c represents the basic electricity consumption data of the target area; f(d) represents the electricity consumption variable coefficient of the dth day; f(·) represents the electricity consumption variable coefficient function; The expression of the activity power consumption function is specifically: Q k,d =F(k,f(d)); Among them, Q k,d represents the activity electricity consumption data corresponding to activity type k in the d-th day; F(·) represents the activity electricity consumption function; f(d) represents the electricity consumption variable coefficient of the d-th day.

2. The building energy consumption prediction method based on multi-factor decomposition according to claim 1 is characterized in that: The process of performing weighted processing on the corresponding total daily electricity consumption data according to the total building area in each grid unit is specifically as follows: Divide the standard building area by the total building area in each grid unit to obtain the weighting coefficient of each grid unit; The total daily electricity consumption data of each grid unit is multiplied by the weighted coefficient to obtain the weighted electricity consumption data of each grid unit; The initial grid electricity consumption data of the target area at the daily level is constructed based on the combination of the net power consumption data of each grid unit.

3. The building energy consumption prediction method based on multi-factor decomposition according to claim 1 is characterized in that: The calculation formula of the daily electricity consumption data is specifically as follows: or, as: Among them, Q h,d represents the daily electricity consumption data of the target area affected by environmental conditions on the dth day; Q i,d represents the ex-rights electricity consumption data of the ith grid unit on the dth day; N represents the number of grid units in the second grid electricity consumption data.

4. The building energy consumption prediction method based on multi-factor decomposition according to claim 1 is characterized in that: The calculation formula of the deterministic power consumption fluctuation feature set is specifically: Among them, Q m,d represents the daily electricity consumption data of the target building m on the dth day; Q c Indicates the basic electricity consumption data of the target area; S m represents the building area of ​​the target building m; ΔQ m,d represents the daily fluctuation power consumption data of the target building m on the dth day; ΔB m,d represents the random power consumption fluctuation characteristics of the target building m on the dth day; Δq m,d,j represents the electricity consumption fluctuation characteristics of the target building m in the jth hour of the dth day. If the electricity consumption fluctuation characteristics of the target building in the same hour in different days are different, the corresponding deterministic electricity consumption fluctuation characteristic value is 0; T represents the number of daily electricity consumption data; Δq m,j represents the deterministic power consumption fluctuation characteristics of the target building m at the jth hour; Δq m,d+1,j represents the power consumption fluctuation characteristics of the target building m in the jth hour of the d+1th day; Δq m represents the deterministic electricity consumption fluctuation feature set of the target building m at the hourly level; Δq m,1 represents the deterministic power consumption fluctuation characteristics of the target building m in the first hour; Δq m,24 It shows the deterministic power consumption fluctuation characteristics of the target building m in the 24th hour.

5. The building energy consumption prediction method based on multi-factor decomposition according to claim 1 is characterized in that: The process of realizing the hourly energy consumption prediction of the target building by combining the basic electricity consumption data, the electricity consumption variable coefficient function, the activity electricity consumption function and the deterministic electricity consumption fluctuation characteristics is specifically as follows: The basic electricity consumption data and the electricity consumption variable coefficient function are used to predict the basic electricity consumption data of the target area in the next day; Estimate the activity electricity consumption data of the target area in the next day through the activity reporting information and activity electricity consumption function; Combined with the target area's basic electricity consumption data for the next day, active electricity consumption data, and the deterministic electricity consumption fluctuation feature set of each target building, the energy consumption forecast result of the target building at the hourly level is determined.

6. Building energy consumption prediction system based on multi-factor decomposition, characterized by: The system is used to implement the building energy consumption prediction method based on multi-factor decomposition as described in any one of claims 1 to 5, comprising: A data collection module is used to collect hourly and daily electricity consumption data of each target building in the target area; The data weighting module is used to perform grid processing on the target area and weight-reduced processing on the corresponding total daily electricity consumption data according to the total building area in each grid unit to obtain the initial grid electricity consumption data of the target area at the daily level; A data splitting module is used to obtain the energy consumption activity information of the target area at the daily level, and split the initial grid power consumption data into the first grid power consumption data with energy consumption activity and the second grid power consumption data without energy consumption activity; An environmental analysis module is used to extract daily electricity consumption data affected by environmental conditions in the target area from the second grid electricity consumption data, and obtain basic electricity consumption data and electricity consumption variable coefficient function of the target area based on fitting analysis of multiple daily electricity consumption data in a preset period; An activity analysis module, configured to calculate the activity electricity consumption data affected by the energy consumption activity by using the difference between the first grid electricity consumption data and the basic electricity consumption data, and to construct an activity electricity consumption function based on the activity types and electricity consumption variable coefficients of the plurality of activity electricity consumption data; The fluctuation analysis module is used to calculate the estimated electricity consumption data based on the product of the basic electricity consumption data and the building area of ​​the target building, and calculate the daily fluctuation electricity consumption data of the corresponding target building based on the difference between the daily electricity consumption data and the estimated electricity consumption data, and determine the deterministic electricity consumption fluctuation feature set of the target building at the hourly level by combining the daily fluctuation electricity consumption data of the target building and the hourly electricity consumption data of multiple days; The energy consumption prediction module is used to combine basic electricity consumption data, electricity consumption variable coefficient function, activity electricity consumption function and deterministic electricity consumption fluctuation characteristics to realize the energy consumption prediction of the target building at the hourly level.

7. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the building energy consumption prediction method based on multi-factor decomposition as described in any one of claims 1 to 5 is implemented.

8. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the building energy consumption prediction method based on multi-factor decomposition as described in any one of claims 1 to 5.

Images