CN114154689A - Method and system for predicting single-machine energy consumption of cold water host and storage medium - Google Patents
Method and system for predicting single-machine energy consumption of cold water host and storage medium Download PDFInfo
- Publication number
- CN114154689A CN114154689A CN202111367671.8A CN202111367671A CN114154689A CN 114154689 A CN114154689 A CN 114154689A CN 202111367671 A CN202111367671 A CN 202111367671A CN 114154689 A CN114154689 A CN 114154689A
- Authority
- CN
- China
- Prior art keywords
- correlation
- adjacency matrix
- energy consumption
- global
- local
- 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 42
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 31
- 239000011159 matrix material Substances 0.000 claims abstract description 89
- 238000003062 neural network model Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000005057 refrigeration Methods 0.000 claims abstract description 11
- 238000012512 characterization method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 238000011478 gradient descent method Methods 0.000 claims description 7
- 230000015654 memory Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000004378 air conditioning Methods 0.000 abstract description 5
- 230000008859 change Effects 0.000 abstract description 5
- 238000013528 artificial neural network Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000003993 interaction Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000000498 cooling water Substances 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012352 Spearman correlation analysis Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- 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"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Optimization (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Marketing (AREA)
- Pure & Applied Mathematics (AREA)
- Primary Health Care (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Algebra (AREA)
Abstract
The invention relates to the technical field of energy consumption prediction of a central air-conditioning water chilling unit, and discloses a method, a system and a storage medium for predicting the energy consumption of a single machine of a water chilling host, wherein the method comprises the steps of acquiring an operation data set of a management system of a building refrigeration station to be tested; constructing a global correlation adjacency matrix of the characteristics according to the correlation coefficient of the operation data set; dividing the operating data set into a plurality of subsets, and constructing a local association adjacency matrix of the characteristics according to the association coefficient of each subset; constructing a target dynamic correlation adjacency matrix based on the global correlation adjacency matrix and the local correlation adjacency matrix; performing iterative training based on the target dynamic correlation adjacency matrix to obtain a target graph neural network model; and inputting the data to be detected acquired in real time into the target graph neural network model to obtain the predicted energy consumption, dynamically representing the correlation condition among all data in the operation data set of the building refrigeration station management system according to the time change, and predicting the single-machine energy consumption of the cold water main machine in real time.
Description
Technical Field
The invention relates to the technical field of energy consumption prediction of a central air-conditioning water chilling unit, in particular to a method and a system for predicting the energy consumption of a single machine of a water chilling host and a storage medium.
Background
The heating, ventilating and air conditioning system is used as an important part in building energy consumption, and monitoring and predicting the energy consumption is one of important prerequisites for further energy-saving control. At present, in a large-scale air conditioning system, a cold water main machine is used as a core device for refrigeration, the system structure is complex, and a plurality of physical processes are involved in working, so that more professional theoretical knowledge is needed in the traditional method for reasonably predicting the energy consumption of the air conditioning system.
With the increasing computing power of computing devices, machine learning has been widely used in the industrial field. The large-scale cold station is also provided with a data collection device, which is beneficial to data-driven modeling of the energy consumption of the cold water host. Because the cold water main machines are usually operated in parallel, the main machines have strong coupling, the interaction among the machines can generate certain influence on the energy consumption of a single cold machine, the study on the energy consumption of the cold water main machines generally focuses on the condition of a single cold water main machine or the whole cold station, the interaction among the multiple cold water main machines is difficult to be displayed explicitly, the interaction among input variables is difficult to be represented intuitively by a traditional algorithm, an important way is provided for solving the association degree among different input variables by a graph neural network, and the association can reflect the relationship and the interaction among the variables to a certain extent. However, in the conventional graph neural network, the association graph composed of nodes and edges has no general construction method. Meanwhile, due to the complexity and diversity of the external environment, the running working conditions of the water chilling unit at different moments may be different, the association degree among the variables can also change along with the fluctuation of the working conditions, and the characteristic of the time-varying association degree puts higher requirements on the real-time performance of the characterization method.
Therefore, how to dynamically characterize the correlation between various collected data according to the time change becomes a problem to be solved urgently according to the real-time prediction of the correlation and the currently collected data.
Disclosure of Invention
The invention provides a method, a system and a storage medium for predicting the stand-alone energy consumption of a cold water host, which aim to solve the problems in the prior art.
In order to achieve the purpose, the invention is realized by the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for predicting energy consumption of a single machine of a cold water host, including the following steps:
acquiring an operation data set of a management system of a building refrigeration station to be tested;
constructing a global correlation adjacency matrix of the features according to the correlation coefficient of the operation data set;
dividing the operating data set into a plurality of subsets, and constructing a local association adjacency matrix of the characteristics according to the association coefficient of each subset;
constructing a target dynamic associative adjacency matrix based on the global associative adjacency matrix and the local associative adjacency matrix;
performing iterative training based on the target dynamic correlation adjacency matrix to obtain a target graph neural network model;
and inputting the data to be detected acquired in real time into the target graph neural network model to obtain the predicted energy consumption output by the target graph neural network model.
Optionally, the constructing a global associative adjacency matrix of the feature according to the correlation coefficients of the running data set includes:
determining characteristic variables of the operation data set, and calculating a correlation coefficient between the characteristic variables;
constructing a global correlation adjacency matrix of the features according to the correlation coefficients, wherein the absolute values of the correlation coefficients are used for representing the global correlation degree between the feature variables, and the global correlation adjacency matrix comprises the global correlation degree;
the global associative adjacency matrix is a mathematical characterization of the global relational graph.
Optionally, the dividing the operation data set into several subsets includes:
and carrying out continuous sliding window processing on the running data set to obtain a plurality of continuous subsets.
Optionally, the constructing a local associative adjacency matrix of the feature according to the association coefficient of each subset includes:
determining characteristic variables in each subset, and calculating a correlation coefficient between the characteristic variables of each subset according to data in each subset;
constructing a local correlation adjacency matrix of the features according to the correlation coefficients among the feature variables of each subset, wherein the absolute values of the correlation coefficients among the feature variables of each subset are used for representing the local correlation degree among the feature variables, and the local correlation adjacency matrix comprises the local correlation degree;
the local associative adjacency matrix is a mathematical characterization of a local relational graph.
Optionally, the target dynamic associative adjacency matrix satisfies the following relation:
Adt=As[α+(1-α)Avt],α∈[0,1]
wherein A isdtRepresenting the target dynamic associative adjacency matrix at time t, AsRepresenting a global associative adjacency matrix, AvtThe local associative adjacency matrix at the time t is shown, and alpha represents the stability coefficient of the formula.
Optionally, the method further comprises: optimizing the stability coefficient by adopting a preset mode;
the preset mode comprises at least one of the following modes:
non-gradient descent method or gradient descent method.
In a second aspect, an embodiment of the present application further provides a system for predicting stand-alone energy consumption of a cold water host, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect when executing the computer program.
In a third aspect, embodiments of the present application further provide a computer storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method in the first aspect.
The invention has the following beneficial effects:
the invention provides a method for predicting the energy consumption of a single machine of a cold water main machine, which comprises the steps of constructing a global correlation adjacent matrix and a local correlation adjacent matrix through an operation data set of a building refrigeration station management system, and constructing a target dynamic correlation adjacent matrix based on the global correlation adjacent matrix and the local correlation adjacent matrix; performing iterative training based on the target dynamic correlation adjacency matrix to obtain a target graph neural network model; inputting the data to be detected acquired in real time into a target graph neural network model to obtain the predicted energy consumption output by the target graph neural network model; therefore, the correlation condition among the data in the operation data set of the building refrigeration station management system can be dynamically represented according to the time change, and the single-machine energy consumption of the cold water main machine can be predicted in real time according to the correlation condition and the currently acquired data.
Drawings
FIG. 1 is a flowchart of a method for predicting stand-alone energy consumption of a cold water main unit according to a preferred embodiment of the present invention;
FIG. 2 is a second flowchart of a method for predicting stand-alone energy consumption of a cold water main unit according to the preferred embodiment of the present invention;
FIG. 3 is a schematic diagram of a form of a correlation matrix provided in the preferred embodiment of the present invention;
fig. 4 is a comparison diagram of the prediction results of the energy consumption prediction method provided by the preferred embodiment of the present invention and the existing prediction method.
Detailed Description
The technical solutions of the present invention are described clearly and completely below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. 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.
Referring to fig. 1-2, an embodiment of the present application provides a method for predicting stand-alone energy consumption of a cold water main unit, including the following steps:
In this step, the operational data set of the building refrigeration station management system includes critical data including, but not limited to, chilled water main operation data, water pump operation data, weather data, time data. This is by way of example only and not by way of limitation.
And 102, constructing a global correlation adjacency matrix of the characteristics according to the correlation coefficient of the operation data set.
And 103, dividing the running data set into a plurality of subsets, and constructing a local association adjacency matrix of the characteristic according to the association coefficient of each subset.
And 104, constructing a target dynamic correlation adjacency matrix based on the global correlation adjacency matrix and the local correlation adjacency matrix.
And 105, performing iterative training based on the target dynamic correlation adjacency matrix to obtain a target graph neural network model.
In this step, the target graph neural network model may be a graph spatiotemporal neural network formed by combining a graph convolution network and a convolution neural network. And during iterative training, inputting the target dynamic association adjacency matrix and the collected operation data set into the target graph neural network model for iterative training, and continuously reducing the difference between the fitting energy consumption value and the actual energy consumption value of the model through the training iteration of the network. And stopping training and storing the model until the model with the required precision is obtained.
And 106, inputting the data to be detected acquired in real time into the target graph neural network model to obtain the predicted energy consumption output by the target graph neural network model.
The method for predicting the energy consumption of the single machine of the cold water main machine comprises the steps of constructing a global correlation adjacent matrix and a local correlation adjacent matrix through an operation data set of a building refrigeration station management system, and constructing a target dynamic correlation adjacent matrix based on the global correlation adjacent matrix and the local correlation adjacent matrix; performing iterative training based on the target dynamic correlation adjacency matrix to obtain a target graph neural network model; inputting the data to be detected acquired in real time into a target graph neural network model to obtain the predicted energy consumption output by the target graph neural network model; therefore, the correlation condition among the data in the operation data set of the building refrigeration station management system can be dynamically represented according to the time change, and the single-machine energy consumption of the cold water main machine can be predicted in real time according to the correlation condition and the currently acquired data.
Optionally, the constructing a global associative adjacency matrix of the feature according to the correlation coefficients of the running data set includes:
determining characteristic variables of the operation data set, and calculating a correlation coefficient between the characteristic variables;
constructing a global correlation adjacency matrix of the features according to the correlation coefficients, wherein the absolute values of the correlation coefficients are used for representing the global correlation degree between the feature variables, and the global correlation adjacency matrix comprises the global correlation degree;
the global associative adjacency matrix is a mathematical characterization of the global relational graph.
In this alternative embodiment, the characteristic variable of the operational data set may be the host j condenser approach temperature (T;)cond_j) Host j evaporator approach temperature (T)evap_j) Condensing pressure (P) of main unit jcond_j) Host j evaporation pressure (P)evap_j) Host j Power (Power)j) And j chilled water flow (Q) of the main machinej) Host j refrigerating capacity (R)j) Host j energy efficiency ratio (COP)j) And the inlet water temperature (T) of the chilled water of the main unit jchi_j) And the outlet water temperature (T) of the chilled water of the main machine jcho_j) And the cooling water inlet temperature (T) of the main engine jci_j) And the outlet water temperature (T) of cooling water of the main unit jco_j) Outdoor wet bulb temperature (T)wet) Week or month, day and hour (Time) of data collection, and on-off condition (IO) of host jj) And a host startup number (N). Are given here by way of example only and not as limitations。
The global relationship graph comprises nodes and edges, the nodes in the global relationship graph represent characteristic variables, the edges represent relationships among the characteristic variables, the association degree between the characteristic variables is regarded as a measurement standard of the distance between the nodes, and when the association degree between two nodes is higher, the regarded distance is smaller, and the fusion degree of data between the two nodes is higher when information aggregation is carried out.
And calculating all the characteristic variables to obtain a global association adjacency matrix which is formed by arranging and combining the association degrees between every two characteristic variables in sequence and is symmetrical along a diagonal, wherein the form of the association adjacency matrix is shown in figure 3, and the global association adjacency matrix represents the structure of a global relationship diagram and reflects the association relationship between the characteristic variables.
Specifically, the global associative adjacency matrix may satisfy the following relation:
wherein A ismnA value, | correct (X), representing the m-th row and n-th column of the associative adjacency matrixm,Xn) | is feature XmAnd feature XnThe absolute value of the correlation coefficient is, in particular, when m is equal to n, the degree of correlation indicating the feature itself is set to 0. Sigma represents a relation threshold, and when the absolute value of the correlation coefficient between the features is smaller than sigma, the correlation value A of the corresponding positionmnIs set to 0.
In this optional embodiment, by constructing the global relationship graph, the association relationship between the data can be sufficiently discovered, and the data association degree can be intuitively reflected. Enough data information can be provided for network training, the accuracy of a prediction result is guaranteed, and meanwhile, data information can be provided for the construction of a target dynamic association adjacency matrix.
Optionally, the dividing the operation data set into several subsets includes:
and carrying out continuous sliding window processing on the running data set to obtain a plurality of continuous subsets.
In this alternative embodiment, each subset of the data set contains the same number of features.
Optionally, the constructing a local associative adjacency matrix of the feature according to the association coefficient of each subset includes:
determining characteristic variables in each subset, and calculating a correlation coefficient between the characteristic variables of the subsets according to data in the subsets;
constructing a local correlation adjacency matrix of the features according to the correlation coefficients among the feature variables of each subset, wherein the absolute values of the correlation coefficients among the feature variables of each subset are used for representing the local correlation degree among the feature variables, and the local correlation adjacency matrix comprises the local correlation degree;
the local associative adjacency matrix is a mathematical characterization of a local relational graph.
In this alternative embodiment, the operational data set is denoted as D, and each subset is denoted as DtAnd the characteristic variable is marked as Xi. The methods used for analyzing the association relationship between every two characteristic variables in the subsets include but are not limited to spearman correlation analysis, pearson correlation coefficient, cosine similarity and inverse Euclidean distance of data. This is by way of example only and not by way of limitation.
The manner of constructing the local relationship graph and the local association adjacency matrix is consistent with the manner of constructing the global, and details are not repeated here.
Optionally, the target dynamic associative adjacency matrix satisfies the following relation:
Adt=As[α+(1-α)Avt],α∈[0,1]
wherein A isdtRepresenting the target dynamic associative adjacency matrix at time t, AsRepresenting a global associative adjacency matrix, AvtThe local associative adjacency matrix at the time t is shown, and alpha represents the stability coefficient of the formula.
In the optional embodiment, the relevance construction between the data is realized through the target dynamic relevance adjacency matrix, the data relevance degree between the sensors is reflected, the spatial relevance of the data between the sensors can be established, and the extraction capability of the network on the real information is enhanced. The relation threshold value can reasonably limit the characteristic relevance, and unnecessary data relevance is eliminated to reduce the operation amount.
Optionally, the method further comprises: optimizing the stability coefficient by adopting a preset mode;
the preset mode comprises at least one of the following modes:
non-gradient descent method or gradient descent method.
In this optional embodiment, by optimizing the stability coefficient, the proportional relationship between the global association degree and the local association degree can be changed, so that the network model can be flexibly adjusted according to the processing capability of the computer, and the adaptability of the network model can be improved.
In an example, in constructing a global association adjacency matrix or a local association adjacency matrix, a relation threshold may be 0, in the process of training a network, a stability coefficient is used as a parameter to be trained, and a target dynamic association adjacency matrix a is used as a target dynamic association adjacency matrixdtAnd corresponding subset DtAnd carrying out model training by using a gradient descent method through a space-time diagram neural network, reducing the difference between the predicted value and the actual value of the model, stopping training until obtaining the model with the accuracy meeting the requirement, and storing the model.
And running the trained model on a system and a storage medium, updating the dynamic association adjacency matrix in real time according to historical data and latest live data, predicting the energy consumption of the cold water host, and storing the data to a specified storage medium for subsequent calling.
By adopting the method in the embodiment, the effect analysis is performed on the model trained by using the space-time diagram neural network on the test set, and the energy consumption prediction effect comparison is performed by adopting the mature convolutional neural network and the long-term and short-term memory neural network, and the result is shown in fig. 4, so that the accuracy of the energy consumption prediction is higher than that of the other two models when the host runs by adopting the model of the invention.
In summary, based on the space-time diagram neural network model, a dynamic association adjacency matrix is constructed by using historical data and real-time data, the space-time diagram neural network performs convolution operation on the data in a time domain and a space domain respectively, introduction of time domain convolution ensures that the model can extract high-order features of the data in the time domain, and space domain convolution ensures that correlation information between the features provided by the dynamic association adjacency matrix is fully utilized.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A method for predicting the stand-alone energy consumption of a cold water main machine is characterized by comprising the following steps:
acquiring an operation data set of a management system of a building refrigeration station to be tested;
constructing a global correlation adjacency matrix of the features according to the correlation coefficient of the operation data set;
dividing the operating data set into a plurality of subsets, and constructing a local association adjacency matrix of the characteristics according to the association coefficient of each subset;
constructing a target dynamic associative adjacency matrix based on the global associative adjacency matrix and the local associative adjacency matrix;
performing iterative training based on the target dynamic correlation adjacency matrix to obtain a target graph neural network model;
and inputting the data to be detected acquired in real time into the target graph neural network model to obtain the predicted energy consumption output by the target graph neural network model.
2. The method for predicting the stand-alone energy consumption of the cold water main units according to claim 1, wherein the step of constructing a global correlation adjacency matrix of the features according to the correlation coefficients of the operation data sets comprises the following steps:
determining characteristic variables of the operation data set, and calculating a correlation coefficient between the characteristic variables;
constructing a global correlation adjacency matrix of the features according to the correlation coefficients, wherein the absolute values of the correlation coefficients are used for representing the global correlation degree between the feature variables, and the global correlation adjacency matrix comprises the global correlation degree;
the global associative adjacency matrix is a mathematical characterization of the global relational graph.
3. The chilled water host stand-alone energy consumption prediction method of claim 1, wherein the dividing the set of operational data into a number of subsets comprises:
and carrying out continuous sliding window processing on the running data set to obtain a plurality of continuous subsets.
4. The method for predicting the stand-alone energy consumption of the cold water main units according to claim 2, wherein the step of constructing a local correlation adjacency matrix of the features according to the correlation coefficient of each subset comprises the following steps:
determining characteristic variables in each subset, and calculating a correlation coefficient between the characteristic variables of each subset according to data in each subset;
constructing a local correlation adjacency matrix of the features according to the correlation coefficients among the feature variables of each subset, wherein the absolute values of the correlation coefficients among the feature variables of each subset are used for representing the local correlation degree among the feature variables, and the local correlation adjacency matrix comprises the local correlation degree;
the local associative adjacency matrix is a mathematical characterization of a local relational graph.
5. The chilled water host stand-alone energy consumption prediction method according to claim 4, wherein the target dynamic correlation adjacency matrix satisfies the following relation:
Adt=As[α+(1-α)Avt],α∈[0,1]
wherein A isdtRepresenting the target dynamic associative adjacency matrix at time t, AsRepresenting a global associative adjacency matrix, AvtThe local associative adjacency matrix at the time t is shown, and alpha represents the stability coefficient of the formula.
6. The chilled water main unit stand-alone energy consumption prediction method according to claim 5, further comprising: optimizing the stability coefficient by adopting a preset mode;
the preset mode comprises at least one of the following modes:
non-gradient descent method or gradient descent method.
7. A cold water host stand-alone energy consumption prediction system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program performs the steps of the method of any one of the preceding claims 1 to 6.
8. A computer storage medium on which a computer program is stored, characterized in that the program, when being executed by a processor, carries out the steps of the method of any one of the preceding claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111367671.8A CN114154689A (en) | 2021-11-18 | 2021-11-18 | Method and system for predicting single-machine energy consumption of cold water host and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111367671.8A CN114154689A (en) | 2021-11-18 | 2021-11-18 | Method and system for predicting single-machine energy consumption of cold water host and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114154689A true CN114154689A (en) | 2022-03-08 |
Family
ID=80456609
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111367671.8A Pending CN114154689A (en) | 2021-11-18 | 2021-11-18 | Method and system for predicting single-machine energy consumption of cold water host and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114154689A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115542824A (en) * | 2022-12-02 | 2022-12-30 | 广州市创博机电设备安装有限公司 | Central air conditioning unit control method and system based on energy consumption management and control |
WO2023246712A1 (en) * | 2022-06-22 | 2023-12-28 | 北京罗克维尔斯科技有限公司 | Local flow model construction method, apparatus and device, medium, and vehicle |
-
2021
- 2021-11-18 CN CN202111367671.8A patent/CN114154689A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023246712A1 (en) * | 2022-06-22 | 2023-12-28 | 北京罗克维尔斯科技有限公司 | Local flow model construction method, apparatus and device, medium, and vehicle |
CN115542824A (en) * | 2022-12-02 | 2022-12-30 | 广州市创博机电设备安装有限公司 | Central air conditioning unit control method and system based on energy consumption management and control |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022012542A1 (en) | Data-analysis-based energy-saving control method for precision air conditioner in cloud computing data center | |
Li et al. | An explainable one-dimensional convolutional neural networks based fault diagnosis method for building heating, ventilation and air conditioning systems | |
Li et al. | Data partitioning and association mining for identifying VRF energy consumption patterns under various part loads and refrigerant charge conditions | |
Fan et al. | A framework for knowledge discovery in massive building automation data and its application in building diagnostics | |
Li et al. | Application of pattern matching method for detecting faults in air handling unit system | |
CN114154689A (en) | Method and system for predicting single-machine energy consumption of cold water host and storage medium | |
CN114484731B (en) | Central air conditioner fault diagnosis method and device based on stacking fusion algorithm | |
CN107735735A (en) | Device characteristics model learning device, device characteristics model learning method and storage medium | |
CN110715401B (en) | Defrosting control method and device for air conditioning equipment, medium and air conditioning equipment | |
Fan et al. | A graph mining-based methodology for discovering and visualizing high-level knowledge for building energy management | |
CN112329813B (en) | Energy consumption prediction feature extraction method and system | |
CN117272212B (en) | Method for selecting optimal operation parameters of refrigeration system based on real-time data | |
CN110009156A (en) | Building energy consumption budget management method and storage medium | |
Zucker et al. | Improving energy efficiency of buildings using data mining technologies | |
CN113432247B (en) | Water chilling unit energy consumption prediction method and system based on graph neural network and storage medium | |
Li et al. | Simulated annealing wrapped generic ensemble fault diagnostic strategy for VRF system | |
Wu et al. | Performance prediction of room air conditioners and optimization of control strategy for energy conservation | |
Guo et al. | Multivariate fault detection for residential HVAC systems using cloud-based thermostat data, part I: Methodology | |
CN117706927A (en) | Energy-saving control method and system for energy system based on sample library management composite model | |
CN116045461B (en) | Energy-saving control method and device for air-cooled air conditioner based on water supply and return temperature adjustment | |
Zhang et al. | Investigations on machine learning-based control-oriented modeling using historical thermal data of buildings | |
CN117494546A (en) | Data-driven air conditioner set temperature correlation simulation method, equipment and medium | |
CN117013520A (en) | Flexible load adjustable power evaluation method based on incremental learning | |
WO2022110213A1 (en) | Method and device for generating prediction model of analysis object, and storage medium | |
Cheng et al. | Abnormal energy consumption detection using ensemble model for water chilling unit on HVAC system |
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 |