CN114169254A - Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model - Google Patents
Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model Download PDFInfo
- Publication number
- CN114169254A CN114169254A CN202111648640.XA CN202111648640A CN114169254A CN 114169254 A CN114169254 A CN 114169254A CN 202111648640 A CN202111648640 A CN 202111648640A CN 114169254 A CN114169254 A CN 114169254A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- prediction model
- short
- term
- consumption prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 205
- 238000003745 diagnosis Methods 0.000 title claims abstract description 67
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012360 testing method Methods 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 34
- 238000012795 verification Methods 0.000 claims abstract description 22
- 238000010220 Pearson correlation analysis Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 230000006399 behavior Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 19
- 238000012216 screening Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 8
- 230000006403 short-term memory Effects 0.000 claims description 7
- 230000007787 long-term memory Effects 0.000 claims description 5
- 238000010200 validation analysis Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 239000005431 greenhouse gas Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Game Theory and Decision Science (AREA)
- Geometry (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an abnormal energy consumption diagnosis method and system based on a short-term building energy consumption prediction model, wherein an energy consumption sample set is constructed and divided into a training set, a verification set and a test set through Pearson correlation analysis and data preprocessing; the LSTM network multi-step advanced short-term energy consumption prediction model based on 10 input parameters such as historical energy consumption data, occupant behaviors, meteorological factors and time factors is provided; predicting the hourly energy consumption of the building in a supervision learning mode by adopting an MIMO strategy; providing a diagnosis method based on a mathematical relationship between a predicted value and an actual value on a smaller time scale according to a prediction model; the invention has the advantages of high diagnosis speed, high diagnosis precision and strong practicability.
Description
Technical Field
The invention belongs to the technical field of building energy consumption prediction, and particularly relates to an abnormal energy consumption diagnosis method and system based on a short-term building energy consumption prediction model.
Background
Currently, the construction industry accounts for 39% and 38% of the total global energy consumption and greenhouse gas emissions, respectively. Compared with the transportation and industrial sectors, the energy saving potential of buildings is much greater. Meanwhile, in recent years, with the gradual increase of building area and energy consumption, energy saving research has become an important research direction. The rapid and accurate energy consumption prediction can provide data for optimized operation, and is helpful for China to realize the carbon dioxide emission peak in 2030.
The role of the building energy consumption prediction varies depending on the prediction period. Long-term forecasts (e.g., more than one year) are typically used for energy maintenance planning and power distribution; medium term prediction (e.g., month, year) is mainly used for predictive maintenance and component operating mode determination; short-term predictions (e.g., sub-hours, or days) are typically used for predictive model control, fault detection, control optimization. Short-term building energy consumption prediction has attracted great interest to building professionals because it is closely related to the daily operation of various service systems.
Existing building anomaly energy consumption diagnostics are often on a daily or monthly basis, are challenging on a small timescale, and do not meet the needs of a practical optimal operation well.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a method and a system for diagnosing abnormal energy consumption based on a short-term building energy consumption prediction model, aiming at the defects in the prior art, so as to solve the problem that the abnormal energy consumption diagnosis cannot be performed on a small time scale.
The invention adopts the following technical scheme:
the abnormal energy consumption diagnosis method based on the short-term building energy consumption prediction model comprises the following steps:
s1, collecting historical building energy consumption data and data influencing energy consumption factors, and screening out features of Pearson correlation coefficients within a threshold value through Pearson correlation analysis to serve as input features of an energy consumption prediction model;
s2, preprocessing the input characteristic data obtained in the step S1, constructing an energy consumption sample set, and dividing the energy consumption sample set into a training set, a verification set and a test set;
s3, optimizing the long-term and short-term memory network by using a multi-input multi-output strategy, and establishing a supervised multi-step advanced short-term energy consumption prediction model;
s4, training the supervised multi-step advanced short-term energy consumption prediction model established in the step S3 by using the training set data obtained in the step S2, optimizing hyper-parameters of the trained supervised multi-step advanced short-term energy consumption prediction model by using the verification set obtained in the step S2 to obtain an optimized short-term building energy consumption prediction model, and evaluating the short-term building energy consumption prediction model by using a part of the test set obtained in the step S2;
s5, determining an abnormal energy consumption diagnosis method on the time scale of each hour based on the short-term building energy consumption prediction model evaluated in the step S4;
and S6, performing energy consumption diagnosis on the residual test set obtained in the step S2 by using the abnormal energy consumption diagnosis method determined in the step S5, and realizing abnormal energy consumption analysis according to the diagnosis result.
Specifically, in step S1, the data affecting the energy consumption factors includes occupant behavior, weather factors, and time factors.
Specifically, in step S1, the Pearson correlation coefficient is calculated as follows:
where ρ isX,YIs the correlation coefficient for variable X, Y, and E is the mathematical expectation of the sample.
Specifically, in step S2, the energy consumption sample set is set according to 6: 2: 2 into a training set, a validation set and a test set.
Further, the test set was expressed as 1: 1 is divided into two parts, which are respectively used for evaluating the short-term building energy consumption prediction model in the step S4 and carrying out energy consumption diagnosis in the step S6.
Specifically, in step S4, the short-term building energy consumption prediction model is used for energy consumption diagnosis when the variation coefficient of the root mean square error on the hourly time scale is less than 30%.
Further, the coefficient of variation CV-RMSE of the root mean square error is specifically:
wherein, yiAndrespectively is the actual value and the predicted value at the ith moment, and n is the number of samples.
Specifically, in step S5, the abnormal energy consumption diagnosis method specifically includes:
s501, regarding data obtained by the prediction model as energy-saving data, and regarding actual data as non-energy-saving data;
s502, representing the difference between the actual energy consumption value and the predicted value by using a residual error epsilon, and representing the test set for evaluating the performance of the prediction model by using an average absolute error MAE, wherein the actual value is larger than the average absolute error under the predicted value;
and S503, dividing the energy utilization condition into an energy-saving state, an attention state and a non-energy-saving state according to the evaluation standard.
Further, in step S503, the evaluation criteria are:
when epsilon is less than or equal to 0, it is in energy-saving state, when 0< epsilon is less than or equal to MAE, it is in attention state, and when epsilon > MAE, it is in non-energy-saving state.
Another technical solution of the present invention is an abnormal energy consumption diagnosis system based on a short-term building energy consumption prediction model, including:
the screening module is used for acquiring historical building energy consumption data and data influencing energy consumption factors, and screening out the characteristic of a Pearson correlation coefficient within a threshold value through Pearson correlation analysis to serve as the input characteristic of the energy consumption prediction model;
the processing module is used for preprocessing the input characteristic data obtained by the screening module, constructing an energy consumption sample set and dividing the energy consumption sample set into a training set, a verification set and a test set;
the output module optimizes the long-term and short-term memory network by using a multi-input multi-output strategy and establishes a supervised multi-step advanced short-term energy consumption prediction model;
the optimization module is used for training the supervised multi-step advanced short-term energy consumption prediction model established by the output module by using the training set data obtained by the processing module, optimizing the hyper-parameters of the supervised multi-step advanced short-term energy consumption prediction model after training by using the verification set obtained by the processing module to obtain an optimized short-term building energy consumption prediction model, and evaluating the short-term building energy consumption prediction model by using a part of test set obtained by the processing module;
the diagnosis module is used for determining an abnormal energy consumption diagnosis method on the time scale of each hour based on the short-term building energy consumption prediction model evaluated by the optimization module;
and the analysis module is used for diagnosing the energy consumption of the residual test set obtained by the processing module by using the abnormal energy consumption diagnosis method determined by the diagnosis module and realizing abnormal energy consumption analysis according to the diagnosis result.
Compared with the prior art, the invention has at least the following beneficial effects:
the invention relates to an abnormal energy consumption diagnosis method based on a short-term building energy consumption prediction model, which comprises the steps of constructing an energy consumption sample set and dividing the energy consumption sample set into a training set, a verification set and a test set through Pearson correlation analysis and data preprocessing; the LSTM network multi-step advanced short-term energy consumption prediction model based on 10 input parameters such as historical energy consumption data, occupant behaviors, meteorological factors and time factors is provided; predicting the hourly energy consumption of the building in a supervision learning mode by adopting an MIMO strategy; providing a diagnosis method based on a mathematical relationship between a predicted value and an actual value on a smaller time scale according to a prediction model; the general method steps of machine learning are adopted, and the problems of long physical modeling period and large engineering quantity are solved.
Furthermore, the factors influencing energy consumption are divided into three categories, which is beneficial to selecting the factors with larger influence in each category.
Furthermore, 0.3 is used as a threshold value of the Pearson correlation coefficient, so that factors with large influence can be correctly selected, unimportant factors are eliminated, and the influence on the performance of the prediction model is eliminated.
Further, the energy consumption sample set is as follows: 2: 2, dividing the energy consumption sample set into a training set, a verification set and a test set, and comparing the energy consumption sample set with the energy consumption sample set of 7: and 3, the model is divided into a training set and a test set, and the optimal hyper-parameter of the model can be selected by fully utilizing a verification set.
Further, the test set was expressed as 1: 1 is divided into two parts, which can meet the requirement of evaluating the performance of the model and can also be used for energy consumption diagnosis.
Furthermore, the variation coefficient of the root mean square error is smaller than 30% as the standard for measuring whether the prediction model under the time scale of each hour can be used for energy consumption diagnosis, and at the moment, the model prediction precision is high, and the requirement of actual engineering is met.
Furthermore, the ratio of the standard deviation of the data to the average is adopted according to the coefficient of variation CV-RMSE of the root mean square error, so that the influence of the measurement scale and dimension of the traditional statistical quantity is overcome.
Further, the diagnosis method based on the abnormal energy consumption is based on the mathematical relationship between the predicted value and the actual value, so that the method has good universality and practicability in practical application.
Furthermore, the energy consumption service condition is divided into three grades according to the evaluation standard, so that managers can know the abnormal condition of energy consumption in time.
In conclusion, the invention has the characteristics of high diagnosis speed, high diagnosis precision and good universality and practicability in practical application.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a graph of Pearson correlation between other factors affecting energy consumption and energy consumption in accordance with the present invention;
FIG. 2 is a diagram of the LSTM model architecture of the present invention;
FIG. 3 is a diagram of the MIMO strategy architecture of the present invention;
FIG. 4 is a prediction flow diagram of the present invention;
FIG. 5 is a diagnostic flow chart of the present invention;
FIG. 6 is a graph showing the results of diagnosis according to the present embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be understood that the terms "comprises" and/or "comprising" indicate the presence of the stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Various structural schematics according to the disclosed embodiments of the invention are shown in the drawings. The figures are not drawn to scale, wherein certain details are exaggerated and possibly omitted for clarity of presentation. The shapes of various regions, layers and their relative sizes and positional relationships shown in the drawings are merely exemplary, and deviations may occur in practice due to manufacturing tolerances or technical limitations, and a person skilled in the art may additionally design regions/layers having different shapes, sizes, relative positions, according to actual needs.
The invention provides an abnormal energy consumption diagnosis method based on a short-term building energy consumption prediction model, which comprises the steps of constructing an energy consumption sample set and dividing the energy consumption sample set into a training set, a verification set and a test set through Pearson correlation analysis and data preprocessing; the LSTM network multi-step advanced short-term energy consumption prediction model based on 10 input parameters such as historical energy consumption data, occupant behaviors, meteorological factors and time factors is provided; predicting the hourly energy consumption of the building in a supervision learning mode by adopting an MIMO strategy; providing a diagnosis method based on a mathematical relationship between a predicted value and an actual value on a smaller time scale according to a prediction model; the invention has the advantages of high diagnosis speed, high diagnosis precision and strong practicability.
Referring to the drawings, the abnormal energy consumption diagnosis method based on the short-term building energy consumption prediction model of the invention comprises the following steps:
s1, collecting historical building energy consumption data and other data influencing energy consumption factors, and screening out the characteristics of Pearson correlation coefficients within a threshold value as input characteristics of an energy consumption prediction model through Pearson correlation analysis;
other factors affecting energy consumption include: occupant behavior, weather factors, and time factors.
Pearson correlation coefficients are calculated as follows:
where ρ isX,YIs the correlation coefficient for variable X, Y, and E is the mathematical expectation of the sample.
S2, preprocessing input characteristic data, constructing an energy consumption sample set, and dividing the energy consumption sample set into a training set, a verification set and a test set;
according to the following steps of 6: 2: and 2, dividing a training set, a verification set and a test set.
Wherein, the test set is as follows: 1, respectively used for evaluating the performance of the prediction model and diagnosing the energy consumption.
S3, optimizing a long short-term memory (LSTM) network by using a multiple-input multiple-output (MIMO) strategy, and establishing a supervised multi-step advanced short-term energy consumption prediction model;
s4, training the model by using the data of the training set, optimizing the hyper-parameters of the model on the verification set to obtain an optimized short-term building energy consumption prediction model, and evaluating the prediction model on the test set;
when the variation coefficient CV-RMSE of the root mean square error of the short-term building energy consumption prediction model taking each hour as the time scale is less than 30%, the model is considered to fully meet the requirement of engineering purposes and can be used for energy consumption diagnosis.
Specifically, the variation coefficient of the root mean square error is:
wherein, yiAndrespectively is the actual value and the predicted value at the ith moment, and n is the number of samples.
S5, developing an abnormal energy consumption diagnosis method on a smaller time scale (every hour) based on the prediction model;
s501, regarding data obtained by the prediction model as energy-saving data, and regarding actual data as non-energy-saving data;
s502, representing the difference between the actual energy consumption value and the predicted value by using a residual error epsilon, and representing the test set for evaluating the performance of the prediction model by using an average absolute error MAE, wherein the actual value is larger than the average absolute error under the predicted value;
the residual epsilon and mean absolute error MAE are:
wherein, yiAndrespectively is the actual value and the predicted value at the ith moment, and n is the number of samples.
And S503, dividing the energy utilization condition into an energy-saving state, an attention state and a non-energy-saving state according to the evaluation standard.
The evaluation criteria were:
and S6, performing energy consumption diagnosis on the test set, and performing deep analysis on abnormal energy consumption according to the diagnosis result.
In another embodiment of the present invention, an abnormal energy consumption diagnosis system based on a short-term building energy consumption prediction model is provided, and the system can be used for implementing the above abnormal energy consumption diagnosis method based on the short-term building energy consumption prediction model.
The screening module is used for acquiring historical building energy consumption data and data influencing energy consumption factors, and screening out the characteristic of Pearson correlation coefficient within a threshold value through Pearson correlation analysis as the input characteristic of the energy consumption prediction model;
the processing module is used for preprocessing the input characteristic data obtained by the screening module, constructing an energy consumption sample set and dividing the energy consumption sample set into a training set, a verification set and a test set;
the output module optimizes the long-term and short-term memory network by using a multi-input multi-output strategy and establishes a supervised multi-step advanced short-term energy consumption prediction model;
the optimization module is used for training the supervised multi-step advanced short-term energy consumption prediction model established by the output module by using the training set data obtained by the processing module, optimizing the hyper-parameters of the supervised multi-step advanced short-term energy consumption prediction model after training by using the verification set obtained by the processing module to obtain an optimized short-term building energy consumption prediction model, and evaluating the short-term building energy consumption prediction model by using a part of test set obtained by the processing module;
the diagnosis module is used for determining an abnormal energy consumption diagnosis method on the time scale of each hour based on the short-term building energy consumption prediction model evaluated by the optimization module;
and the analysis module is used for diagnosing the energy consumption of the residual test set obtained by the processing module by using the abnormal energy consumption diagnosis method determined by the diagnosis module and realizing abnormal energy consumption analysis according to the diagnosis result.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As a specific embodiment of the invention, the data related to energy consumption of 9-2021-9 months in 2020 is selected for model training, the data of 5-7 months in 2021 is taken as a verification set, the data of 8-9 months in 2021 is taken as a prediction model evaluation, and finally, the data of 10 months in 2021 is selected to diagnose the abnormal energy consumption.
The process of pre-screening the influence factors of the building energy consumption by adopting Pearson correlation analysis specifically comprises the following steps:
s1, other factors affecting energy consumption include: occupant behavior, weather factors, and time factors; and calculating a Pearson correlation coefficient, and selecting a variable with the absolute value of the correlation coefficient larger than 0.3 as an input variable of the prediction model according to a Pearson correlation standard, wherein the variable comprises 10 parameters such as historical building energy consumption, indoor pedestrian flow, entrance pedestrian flow and the like.
S2, preprocessing input characteristic data, constructing an energy consumption sample set, and dividing the energy consumption sample set into a training set, a verification set and a test set;
and S3, optimizing a long short-term memory (LSTM) network by using a multiple-input multiple-output (MIMO) strategy, and establishing a supervised multi-step advanced short-term energy consumption prediction model.
S4, training the model by using the data of the training set, optimizing the hyper-parameters of the model on the verification set to obtain an optimized short-term building energy consumption prediction model, and evaluating the prediction model on the test set;
s401, obtaining the hyper-parameters after model optimization on the verification set as follows:
s402, when the variation coefficient of the root mean square error (CV-RMSE) of the short-term building energy consumption prediction model with the time scale of each hour is less than 30%, the model is considered to fully meet the requirement of the engineering purpose and can be used for energy consumption diagnosis;
and S403, obtaining the CV-RMSE of the optimized model as 0.1434.
S5, developing an abnormal energy consumption diagnosis method on a smaller time scale (every hour) based on the prediction model;
s501, regarding data obtained by the prediction model as energy-saving data, and regarding actual data as non-energy-saving data;
s502, representing the difference between the actual energy consumption value and the predicted value by using a residual error epsilon, and representing the test set for evaluating the performance of the prediction model by using an average absolute error MAE, wherein the actual value is larger than the average absolute error under the predicted value;
and S503, dividing the energy utilization condition into an energy-saving state, an attention state and a non-energy-saving state according to the evaluation standard.
And S6, performing energy consumption diagnosis on the test set, and performing deep analysis on abnormal energy consumption according to the diagnosis result.
S601, calculating a residual epsilon between the actual energy consumption value and the predicted value of each time step.
S602, calculates MAE 7.8253.
S603, when the epsilon is less than or equal to 0, the energy-saving state is considered; ε is greater than 0 and less than or equal to 7.8253, then the attentive state is considered; when ε is greater than 7.8253, the state is considered to be a non-energy saving state.
The experimental result shows that 67 data in 744 data of 10 months are diagnosed as a non-energy-saving state, wherein the relative error of three time points is more than 20%, and the non-energy-saving time in the building operation is successfully diagnosed.
TABLE 1 statistical table of diagnostic results
TABLE 2 partial contents of non-power saving state
In conclusion, the abnormal energy consumption diagnosis method and system based on the short-term building energy consumption prediction model predict the short-term building energy consumption through the LSTM neural network modeling, can quickly provide energy consumption prediction after training is completed, and solve the problems of long physical modeling period and large engineering quantity; the LSTM neural network is optimized through an MIMO strategy, and a supervised learning mode is adopted, so that the model prediction performance is improved, and the energy consumption diagnosis precision of the building is obviously improved; the diagnosis method is obtained based on the mathematical relationship between the predicted value and the actual value, so that the method has good universality and practicability in practical application.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned contents are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modification made on the basis of the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (10)
1. The abnormal energy consumption diagnosis method based on the short-term building energy consumption prediction model is characterized by comprising the following steps of:
s1, collecting historical building energy consumption data and data influencing energy consumption factors, and screening out features of Pearson correlation coefficients within a threshold value through Pearson correlation analysis to serve as input features of an energy consumption prediction model;
s2, preprocessing the input characteristic data obtained in the step S1, constructing an energy consumption sample set, and dividing the energy consumption sample set into a training set, a verification set and a test set;
s3, optimizing the long-term and short-term memory network by using a multi-input multi-output strategy, and establishing a supervised multi-step advanced short-term energy consumption prediction model;
s4, training the supervised multi-step advanced short-term energy consumption prediction model established in the step S3 by using the training set data obtained in the step S2, optimizing hyper-parameters of the trained supervised multi-step advanced short-term energy consumption prediction model by using the verification set obtained in the step S2 to obtain an optimized short-term building energy consumption prediction model, and evaluating the short-term building energy consumption prediction model by using a part of the test set obtained in the step S2;
s5, determining an abnormal energy consumption diagnosis method on the time scale of each hour based on the short-term building energy consumption prediction model evaluated in the step S4;
and S6, performing energy consumption diagnosis on the residual test set obtained in the step S2 by using the abnormal energy consumption diagnosis method determined in the step S5, and realizing abnormal energy consumption analysis according to the diagnosis result.
2. The abnormal energy consumption diagnosis method based on the short-term building energy consumption prediction model as claimed in claim 1, wherein the data affecting the energy consumption factors comprises occupant behavior, meteorological factors and time factors in step S1.
3. The method for diagnosing abnormal energy consumption based on the short-term building energy consumption prediction model according to claim 1, wherein in step S1, the Pearson correlation coefficient is calculated as follows:
where ρ isX,YIs the correlation coefficient for variable X, Y, and E is the mathematical expectation of the sample.
4. The method for diagnosing abnormal energy consumption based on the short-term building energy consumption prediction model as claimed in claim 1, wherein in step S2, the energy consumption sample set is set according to the ratio of 6: 2: 2 into a training set, a validation set and a test set.
5. The method for diagnosing abnormal energy consumption based on the short-term building energy consumption prediction model according to claim 4, wherein the test set is set according to the following formula 1: 1 is divided into two parts, which are respectively used for evaluating the short-term building energy consumption prediction model in the step S4 and carrying out energy consumption diagnosis in the step S6.
6. The method for diagnosing abnormal energy consumption based on the short-term building energy consumption prediction model as claimed in claim 1, wherein in step S4, the short-term building energy consumption prediction model is used for energy consumption diagnosis when the variation coefficient of the root mean square error in the hourly time scale is less than 30%.
7. The method for diagnosing abnormal energy consumption based on the short-term building energy consumption prediction model as claimed in claim 6, wherein the coefficient of variation CV-RMSE of root mean square error is specifically:
8. The method for diagnosing abnormal energy consumption based on the short-term building energy consumption prediction model as claimed in claim 1, wherein in step S5, the method for diagnosing abnormal energy consumption is specifically as follows:
s501, regarding data obtained by the prediction model as energy-saving data, and regarding actual data as non-energy-saving data;
s502, representing the difference between the actual energy consumption value and the predicted value by using a residual error epsilon, and representing the test set for evaluating the performance of the prediction model by using an average absolute error MAE, wherein the actual value is larger than the average absolute error under the predicted value;
and S503, dividing the energy utilization condition into an energy-saving state, an attention state and a non-energy-saving state according to the evaluation standard.
9. The method for diagnosing abnormal energy consumption based on the short-term building energy consumption prediction model according to claim 8, wherein in step S503, the evaluation criteria are:
when epsilon is less than or equal to 0, it is in energy-saving state, when 0< epsilon is less than or equal to MAE, it is in attention state, and when epsilon > MAE, it is in non-energy-saving state.
10. An abnormal energy consumption diagnosis system based on a short-term building energy consumption prediction model is characterized by comprising:
the screening module is used for acquiring historical building energy consumption data and data influencing energy consumption factors, and screening out the characteristic of a Pearson correlation coefficient within a threshold value through Pearson correlation analysis to serve as the input characteristic of the energy consumption prediction model;
the processing module is used for preprocessing the input characteristic data obtained by the screening module, constructing an energy consumption sample set and dividing the energy consumption sample set into a training set, a verification set and a test set;
the output module optimizes the long-term and short-term memory network by using a multi-input multi-output strategy and establishes a supervised multi-step advanced short-term energy consumption prediction model;
the optimization module is used for training the supervised multi-step advanced short-term energy consumption prediction model established by the output module by using the training set data obtained by the processing module, optimizing the hyper-parameters of the supervised multi-step advanced short-term energy consumption prediction model after training by using the verification set obtained by the processing module to obtain an optimized short-term building energy consumption prediction model, and evaluating the short-term building energy consumption prediction model by using a part of test set obtained by the processing module;
the diagnosis module is used for determining an abnormal energy consumption diagnosis method on the time scale of each hour based on the short-term building energy consumption prediction model evaluated by the optimization module;
and the analysis module is used for diagnosing the energy consumption of the residual test set obtained by the processing module by using the abnormal energy consumption diagnosis method determined by the diagnosis module and realizing abnormal energy consumption analysis according to the diagnosis result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111648640.XA CN114169254A (en) | 2021-12-29 | 2021-12-29 | Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111648640.XA CN114169254A (en) | 2021-12-29 | 2021-12-29 | Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114169254A true CN114169254A (en) | 2022-03-11 |
Family
ID=80488857
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111648640.XA Pending CN114169254A (en) | 2021-12-29 | 2021-12-29 | Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114169254A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115656831A (en) * | 2022-10-08 | 2023-01-31 | 昆明理工大学 | Multi-step advanced prediction and fault diagnosis method for single battery voltage |
CN116068479A (en) * | 2023-03-07 | 2023-05-05 | 潍柴动力股份有限公司 | Abnormality detection method and device for output performance signal in fuel cell endurance test |
CN116128124A (en) * | 2023-01-09 | 2023-05-16 | 北京建筑大学 | Building energy consumption prediction method based on abnormal energy value processing and time sequence decomposition |
CN116757359A (en) * | 2023-06-12 | 2023-09-15 | 国网北京市电力公司 | Park carbon efficiency diagnosis method and system based on building carbon emission characteristic parameters |
CN117290797A (en) * | 2023-11-24 | 2023-12-26 | 国网山东省电力公司济宁供电公司 | Building energy consumption prediction method, system, device and medium |
CN116757359B (en) * | 2023-06-12 | 2024-09-24 | 国网北京市电力公司 | Park carbon efficiency diagnosis method and system based on building carbon emission characteristic parameters |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108320016A (en) * | 2018-03-08 | 2018-07-24 | 南京工业大学 | Short-term prediction method for building energy consumption |
CN108596229A (en) * | 2018-04-13 | 2018-09-28 | 北京华电智慧科技产业有限公司 | Online abnormal monitoring, diagnosing method and system |
US20180285788A1 (en) * | 2015-10-13 | 2018-10-04 | British Gas Trading Limited | System for energy consumption prediction |
AU2020102461A4 (en) * | 2020-09-28 | 2020-11-12 | Jiang, Tianxin Miss | Method of Stock Yield Prediction Based on LSTM Mode |
-
2021
- 2021-12-29 CN CN202111648640.XA patent/CN114169254A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180285788A1 (en) * | 2015-10-13 | 2018-10-04 | British Gas Trading Limited | System for energy consumption prediction |
CN108320016A (en) * | 2018-03-08 | 2018-07-24 | 南京工业大学 | Short-term prediction method for building energy consumption |
CN108596229A (en) * | 2018-04-13 | 2018-09-28 | 北京华电智慧科技产业有限公司 | Online abnormal monitoring, diagnosing method and system |
AU2020102461A4 (en) * | 2020-09-28 | 2020-11-12 | Jiang, Tianxin Miss | Method of Stock Yield Prediction Based on LSTM Mode |
Non-Patent Citations (1)
Title |
---|
田颖;于军琪;杨熊;赵安军: "FCM优化BP神经网络的建筑电耗预测模型", 第十五届国际绿色建筑与建筑节能大会暨新技术与产品博览会, 31 December 2019 (2019-12-31) * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115656831A (en) * | 2022-10-08 | 2023-01-31 | 昆明理工大学 | Multi-step advanced prediction and fault diagnosis method for single battery voltage |
CN116128124A (en) * | 2023-01-09 | 2023-05-16 | 北京建筑大学 | Building energy consumption prediction method based on abnormal energy value processing and time sequence decomposition |
CN116068479A (en) * | 2023-03-07 | 2023-05-05 | 潍柴动力股份有限公司 | Abnormality detection method and device for output performance signal in fuel cell endurance test |
CN116757359A (en) * | 2023-06-12 | 2023-09-15 | 国网北京市电力公司 | Park carbon efficiency diagnosis method and system based on building carbon emission characteristic parameters |
CN116757359B (en) * | 2023-06-12 | 2024-09-24 | 国网北京市电力公司 | Park carbon efficiency diagnosis method and system based on building carbon emission characteristic parameters |
CN117290797A (en) * | 2023-11-24 | 2023-12-26 | 国网山东省电力公司济宁供电公司 | Building energy consumption prediction method, system, device and medium |
CN117290797B (en) * | 2023-11-24 | 2024-02-02 | 国网山东省电力公司济宁供电公司 | Building energy consumption prediction method, system, device and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114169254A (en) | Abnormal energy consumption diagnosis method and system based on short-term building energy consumption prediction model | |
CN112036075A (en) | Abnormal data judgment method based on environmental monitoring data association relation | |
CN106649919A (en) | Method and system for predicting carbon content of fly ash in coal-fired power plant boiler | |
CN112364560B (en) | Intelligent prediction method for working hours of mine rock drilling equipment | |
CN112365056A (en) | Electrical load joint prediction method and device, terminal and storage medium | |
CN109063892A (en) | Industry watt-hour meter prediction technique based on BP-LSSVM combination optimization model | |
CN110097205A (en) | A kind of building load prediction weather forecast data preprocessing method | |
CN113506121A (en) | Analysis method and device for price influence factors | |
CN113268883A (en) | Method for predicting corrosion rate of submarine crude oil pipeline based on PCA-ABC-SVM model | |
CN113408659A (en) | Building energy consumption integrated analysis method based on data mining | |
CN117114438A (en) | Building area energy system cold and hot load data driving prediction method with flexibility and interpretability | |
Ak et al. | Data analytics and uncertainty quantification for energy prediction in manufacturing | |
CN111680712A (en) | Transformer oil temperature prediction method, device and system based on similar moments in the day | |
CN108830405B (en) | Real-time power load prediction system and method based on multi-index dynamic matching | |
CN107544447A (en) | A kind of chemical process Fault Classification based on core study | |
CN117370759A (en) | Gas consumption prediction method based on artificial intelligence | |
CN117575564A (en) | Extensible infrastructure network component maintenance and transformation decision evaluation method and system | |
CN112418662A (en) | Power distribution network operation reliability analysis method using artificial neural network | |
CN116258467A (en) | Electric power construction management and control system | |
CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method | |
Kaligambe et al. | Indoor Room Temperature and Relative Humidity Estimation in a Commercial Building Using the XGBoost Machine Learning Algorithm | |
Koistinen et al. | Adaptation framework for an industrial digital twin | |
CN118536410B (en) | Big data driven modeling-based energy consumption optimization decision analysis method and system | |
CN110781538A (en) | Windowing simulation algorithm based on-site monitoring | |
PRIETO | CHAPTER THIRTEEN HVAC EARLY FAULT DETECTION USING A FUZZY LOGIC-BASED APPROACH VICTOR MARTINEZ-VIOL1, EVA M. URBANO1 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |