CN116187598B - Building-based virtual power plant load prediction method - Google Patents
Building-based virtual power plant load prediction method Download PDFInfo
- Publication number
- CN116187598B CN116187598B CN202310477585.5A CN202310477585A CN116187598B CN 116187598 B CN116187598 B CN 116187598B CN 202310477585 A CN202310477585 A CN 202310477585A CN 116187598 B CN116187598 B CN 116187598B
- Authority
- CN
- China
- Prior art keywords
- power plant
- central air
- virtual power
- air conditioner
- building
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000004378 air conditioning Methods 0.000 claims abstract description 66
- 238000011156 evaluation Methods 0.000 claims abstract description 39
- 238000010219 correlation analysis Methods 0.000 claims abstract description 18
- 230000000694 effects Effects 0.000 claims abstract description 12
- 238000012360 testing method Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 4
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 239000004973 liquid crystal related substance Substances 0.000 claims 2
- 230000005611 electricity Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000005265 energy consumption Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 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
- 230000005484 gravity Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- 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
- 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
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
-
- 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
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Power Engineering (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a building-based virtual power plant load prediction method, which relates to the technical field of virtual power plants, and is used for collecting central air conditioner operation data and establishing a corresponding air conditioner digital twin model and a building model; establishing a central air conditioner parameter data set, constructing a correlation analysis model, and determining the influence degree of variables in the central air conditioner parameter data set on the actual temperature; establishing a load change data set and acquiring a central air-conditioning state evaluation value Ktz to form a central air-conditioning load correlation coefficient Fxs; establishing a weather state data set and a corresponding weather influence coefficient Txs, and establishing a virtual power plant load prediction set and a virtual power plant load prediction model; and predicting possible running risks of the virtual power plant dispatching system, matching corresponding countermeasures and outputting. The strategy for adjusting the temperature in the building has a guiding effect, and the load of the virtual power plant is effectively reduced and the pressure of the dispatching system is reduced when the optimal temperature is obtained by combining the change of the load of the virtual power plant.
Description
Technical Field
The invention relates to the technical field of virtual power plants, in particular to a building-based virtual power plant load prediction method.
Background
The key technologies of the virtual power plant mainly comprise a coordination control technology, an intelligent metering technology and an information communication technology, and the most attractive function of the virtual power plant is to be capable of aggregating DER to participate in the operation of an electric power market and an auxiliary service market and provide management and auxiliary services for a power distribution network and a transmission network.
The virtual power plant is gradually widely applied in cities, particularly for various office buildings, and because of the large number of people in the office buildings, at least on the level of a central air conditioner, the power consumption of the virtual power plant is large, so that a large load is brought to the dispatching and the operation of the virtual power plant. However, in the power system, accurate load prediction is one of important means for ensuring safe and stable operation of the system, and meanwhile, an important basis is provided for power dispatching, power facility construction and the like of power supply enterprises.
In the prior art, the prediction is to predict the load of the power system under different conditions through each sub-load prediction model, adjust the specific gravity occupied by the prediction results of each sub-load prediction model based on the weight adjustment model, and synthesize each sub-prediction result, thereby obtaining the load prediction result, improving the prediction precision and guiding the dispatching system.
However, the prediction mode lacks judgment on weather influence, is difficult to make more accurate response when the external weather of the building is suddenly changed, cannot form a guiding effect on a strategy for adjusting the temperature in the building by using a central air conditioner, and cannot effectively reduce the pressure of a dispatching system of a virtual power plant.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a virtual power plant load prediction method based on a building, which establishes a corresponding air-conditioning digital twin model and a building model by collecting central air-conditioning operation data; establishing a central air conditioner parameter data set, constructing a correlation analysis model, and determining the influence degree of variables in the central air conditioner parameter data set on the actual temperature; establishing a load change data set and acquiring a central air-conditioning state evaluation value Ktz to form a central air-conditioning load correlation coefficient Fxs; establishing a weather state data set and a corresponding weather influence coefficient Txs, and establishing a virtual power plant load prediction set and a virtual power plant load prediction model; and predicting possible running risks of the virtual power plant dispatching system, matching corresponding countermeasures and outputting.
The strategy for adjusting the temperature in the building has a guiding effect, and the load of the virtual power plant is effectively reduced when the optimal temperature is obtained by combining the change of the load of the virtual power plant, so that the pressure of a dispatching system is reduced, and the problem in the background technology is solved.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme: a building-based virtual power plant load prediction method comprises the following steps: when a central air conditioner in a building is in a working state, collecting central air conditioner operation data, establishing a corresponding air conditioner digital twin model and a building model, and setting a marking position in the building; according to the actual temperature at the marked position and the central air-conditioning parameter, a central air-conditioning parameter data set is established, a correlation analysis model is established, the influence degree of variables in the central air-conditioning parameter data set on the actual temperature is determined, and when the optimum temperature exists in the building, the preset temperature which is required to be set by the central air-conditioner is determined;
when the central air conditioner is in a continuous working state, a load change data set is established and a central air conditioner state evaluation value Ktz is obtained; according to the analysis of the correlation analysis model, a central air conditioner load correlation coefficient Fxs is formed;
when the weather outside the building changes, a weather state data set and a corresponding weather influence coefficient Txs are established, a digital twin model of an air conditioner is combined, a virtual power plant load prediction set is established on the basis of a central air conditioner state evaluation value Ktz and the change of the virtual power plant load, and a virtual power plant load prediction model is established on the basis of a BP neural network prediction algorithm;
and predicting a time node when the virtual power plant load exceeds a threshold value in an operation period according to the virtual power plant load prediction model, predicting possible operation risk of the virtual power plant scheduling system on the time node, and matching and outputting corresponding response schemes according to the operation risk.
Further, when the central air conditioner in the building is in a working state, on the basis of combining building structures, the running state data of the central air conditioner are collected; at least the acquired data includes: presetting temperature, opening of a valve hole of a throttle valve, rotating speed of a fan and circulating air quantity, and summarizing to form a central air conditioner operation data set;
establishing a digital twin model of the air conditioner according to the equipment parameters and the operation parameters of the central air conditioner; after testing and training, outputting the air conditioner digital twin model; building models are built according to building structures, temperature detection modules are uniformly arranged in a plurality of areas with the most dense crowd distribution inside the building, and marking is carried out on the building models to form marking positions.
Further, when the central air conditioner is in a normal use state, acquiring the actual temperature at the marked position, judging the temperature difference between the actual temperature and the preset temperature, and acquiring the valve opening, the fan rotating speed, the circulating air quantity and the load of the virtual power plant at the moment of the central air conditioner; after the test, acquiring the actual temperature at the marked position and the parameters of the central air conditioner, and establishing a central air conditioner parameter data set; when the system is used, the correlation between the central air conditioning parameters and the load of the virtual power plant can be judged through collecting the central air conditioning parameters.
Further, based on a Monte Carlo simulation algorithm, after training and testing, a correlation analysis model is constructed, and based on data in a central air conditioner parameter data set, the influence degree of operation parameters on the actual temperature at a marked position is judged; wherein at least the variables are determined: the valve opening, the fan rotating speed and the circulating air quantity influence factors on the actual temperature;
searching to obtain the optimum temperature in the building, adjusting central air-conditioning parameters based on the air-conditioning digital twin model, combining the temperature difference values, determining the preset temperature which the central air-conditioning should set when the optimum temperature is reached after testing, and marking the preset temperature in the building model.
Further, combining with an air-conditioning digital twin model, acquiring load change of a virtual power plant by changing a preset temperature when the central air conditioner is in a continuous working state, establishing a load change data set, and correlating to form a central air-conditioning state evaluation value Ktz;
when the central air-conditioning state evaluation value Ktz is larger than the threshold value, according to the analysis of the correlation analysis model, when the preset temperature is reached, the correlation between the central air-conditioning state evaluation value Ktz and the virtual power plant load is determined, and a central air-conditioning load correlation coefficient Fxs is formed.
Further, the valve opening Kd, the fan rotating speed Fj, the circulating air quantity Xf and corresponding influence factors are obtained: the opening factor Ad, the fan factor Af and the air quantity factor Az are related to form a central air conditioning state evaluation value Ktz;
the acquisition load of the central air-conditioning status evaluation value Ktz is as follows:
wherein->
Is a constant correction coefficient.
Further, the received weather forecast determines the following weather change, a weather state data set is established according to the air temperature Kt, the wind speed Fs and the relative humidity RH obtained by the weather forecast, and after dimensionless processing, weather influence coefficients Txs are formed by correlation, wherein the weather influence coefficients Txs are obtained in the following manner:
Further, in combination with the air-conditioning digital twin model, when the central air conditioner is in a use state, changing a weather influence coefficient Txs, and when the central air conditioner state evaluation value Ktz is unchanged, acquiring the actual temperature of the marking position in the building; constructing a temperature change model according to the change of the weather effect coefficient Txs and the corresponding change trend of the actual temperature; when the actual temperature is unchanged, performing simulation analysis by taking a weather influence coefficient Txs as an independent variable to obtain a change trend of a central air-conditioning state evaluation value Ktz and a change trend of an affected virtual power plant load;
acquiring a change trend of a weather influence coefficient Txs, an actual temperature change trend, a change trend of a central air conditioning state evaluation value Ktz and a virtual power plant load change trend, and constructing a virtual power plant load prediction set; according to the BP neural network prediction algorithm, the sample data in the virtual power plant load prediction set are combined, and after training and testing, a virtual power plant load prediction model is constructed.
Further, when the virtual power plant is in the operation state, acquiring a weather influence coefficient Txs at each time point in a next operation period from the weather forecast; according to the virtual power plant load prediction model, the load of the virtual power plant and the corresponding central air conditioning state evaluation value Ktz when the optimum temperature is maintained at each time node in the operation cycle are predicted.
Further, known risks and corresponding risk characteristics which can occur when the load of the virtual power plant dispatching system exceeds a threshold value are obtained, a risk characteristic library is constructed, and a corresponding scheme corresponding to the known risks is retrieved and obtained based on the known risks, so that a scheme library is constructed;
predicting that the scheduling system of the virtual power plant may generate risk and corresponding risk characteristics on the next time node when the load of the virtual power plant exceeds the corresponding threshold; and matching known risks from the risk feature library according to the risk features, and matching corresponding schemes from the scheme library according to the matched known risks and outputting the corresponding schemes.
(III) beneficial effects
The invention provides a building-based virtual power plant load prediction method. The beneficial effects are as follows:
and judging the influence degree of the operation parameters on the actual temperature at the marked position through the established correlation analysis model, forming a guiding effect on a strategy for adjusting the temperature in the building, and combining the change of the load of the virtual power plant, effectively reducing the load of the virtual power plant, reducing the electric energy consumption and reducing the pressure of a dispatching system when the optimal temperature is obtained.
Based on the formed central air-conditioning state evaluation value Ktz, the central air-conditioning load correlation coefficient Fxs is determined under the cooperation of the correlation analysis model analysis, and when the load of the power plant is overlarge, the central air-conditioning operation parameters can be adjusted according to the change of the central air-conditioning state evaluation value Ktz, so that the load of the virtual power plant is reduced, the electric energy consumption is reduced, and the refrigerating or heating effect of the central air-conditioning is ensured as much as possible.
The virtual power plant load prediction model is constructed based on the BP neural network prediction algorithm, when the weather influence coefficient Txs changes, the load of the virtual power plant is predicted, particularly when the weather suddenly changes and the electricity consumption in the building is large, the load change of the virtual power plant is predicted, the corresponding electricity consumption requirement is determined, the overload of the virtual power plant is avoided, the building cannot be sufficiently supplied with electricity, and when the virtual power plant load prediction model predicts.
The scheduling risk that the scheduling system is likely to face is predicted, a corresponding treatment scheme is matched according to the scheduling risk, maintenance personnel can rapidly solve risks and problems to be faced, the problems are solved timely, when the virtual power plant exceeds the load, the running risk of the virtual power plant and the scheduling system is reduced, and the negative influence of overload is reduced.
Drawings
FIG. 1 is a flow chart of a method for predicting load of a virtual power plant according to the present invention.
Description of the embodiments
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides a building-based virtual power plant load prediction method, which comprises the following steps:
step one, when a central air conditioner in a building is in a working state, collecting central air conditioner operation data, establishing a corresponding air conditioner digital twin model and a building model, and setting a marking position in the building;
the first step comprises the following steps:
step 101, when a central air conditioner in a building is in a working state, collecting running state data of the central air conditioner on the basis of combining building structures; at least the acquired data includes: presetting temperature, opening of a valve hole of a throttle valve, rotating speed of a fan and circulating air quantity, and summarizing to form a central air conditioner operation data set;
102, establishing an air conditioner digital twin model according to equipment parameters and operation parameters of a central air conditioner; after testing and training, outputting the air conditioner digital twin model;
step 103, building a building model according to the building structure, uniformly arranging temperature detection modules in a plurality of areas with the most dense crowd distribution inside the building, and marking the building model to form marking positions;
in use, the contents of steps 101 to 103 are combined:
and simulating the operation of the central air conditioner according to the established air conditioner digital twin model and the building model and determining the marking position, and judging the temperature data at the marking position in the building when the central air conditioner operates, so that the change of the temperature data is predicted approximately.
Step two, according to the actual temperature at the marked position and the central air-conditioning parameter, a central air-conditioning parameter data set is established, a correlation analysis model is established, the influence degree of the variable in the central air-conditioning parameter data set on the actual temperature is determined, and when the optimum temperature exists in the building, the preset temperature which is required to be set by the central air-conditioner is determined;
the second step comprises the following steps:
step 201, when the central air conditioner is in a normal use state, acquiring the actual temperature at the marked position, judging the temperature difference between the actual temperature and the preset temperature, and acquiring the valve opening, the fan rotating speed, the circulating air quantity and the load of the virtual power plant at the moment of the central air conditioner;
after the test, acquiring the actual temperature at the marked position and the parameters of the central air conditioner, and establishing a central air conditioner parameter data set; when the system is used, the correlation between the central air conditioning parameters and the load of the virtual power plant can be judged through collecting the central air conditioning parameters;
step 202, based on a Monte Carlo simulation algorithm, after training and testing, constructing a correlation analysis model, and based on data in a central air conditioner parameter data set, judging the influence degree of an operation parameter on the actual temperature at a mark position;
wherein at least the variables are determined: the degree of influence of the opening of the valve hole, the rotating speed of the fan and the circulating air quantity on the actual temperature is determined, namely the approximate range of the influence factors is determined;
step 203, searching and obtaining the optimum temperature in the building, adjusting central air-conditioning parameters based on an air-conditioning digital twin model, combining the temperature difference values, determining the preset temperature which the central air-conditioner should set when the optimum temperature is reached after testing, and marking the preset temperature in the building model;
in use, the contents of steps 201 to 203 are combined:
the influence degree of the operation parameters on the actual temperature at the marked position is judged through the established correlation analysis model, so that a guiding effect can be formed on a strategy for adjusting the temperature in the building, and in combination with the change of the load of the virtual power plant, the load of the virtual power plant is effectively reduced, the electric energy consumption is reduced, and the pressure of a dispatching system is reduced when the optimal temperature is obtained.
Step three, when the central air conditioner is in a continuous working state, a load change data set is established, and a central air conditioner state evaluation value Ktz is obtained; according to the analysis of the correlation analysis model, a central air conditioner load correlation coefficient Fxs is formed;
the third step comprises the following steps:
step 301, combining an air conditioner digital twin model, acquiring load change of a virtual power plant by changing a preset temperature when a central air conditioner is in a continuous working state, and establishing a load change data set;
acquiring valve opening Kd, fan rotating speed Fj, circulating air quantity Xf and corresponding influence factors: the opening factor Ad, the fan factor Af and the air quantity factor Az are related to form a central air conditioning state evaluation value Ktz;
the acquisition load of the central air-conditioning status evaluation value Ktz is as follows:
wherein->
Is a constant correction coefficient.
302, when the central air-conditioning state evaluation value Ktz is larger than a threshold value, according to the analysis of a correlation analysis model, determining the correlation between the central air-conditioning state evaluation value Ktz and the load of the virtual power plant when the preset temperature is reached, and forming a central air-conditioning load correlation coefficient Fxs;
when the method is used, the load of the virtual power plant is adjusted according to the state evaluation value Ktz of the central air conditioner, so that the load of the virtual power plant is reduced; an adjusting action can be formed.
In use, the contents of steps 301 and 302 are combined:
based on the formed central air-conditioning state evaluation value Ktz, the central air-conditioning load correlation coefficient Fxs is determined under the cooperation of the correlation analysis model analysis, and when the load of the power plant is overlarge, the central air-conditioning operation parameters can be adjusted according to the change of the central air-conditioning state evaluation value Ktz, so that the load of the virtual power plant is reduced, the electric energy consumption is reduced, and the refrigerating or heating effect of the central air-conditioning is ensured as much as possible.
Step four, when weather outside the building changes, a weather state data set and a corresponding weather influence coefficient Txs are established, a digital twin model of an air conditioner is combined, a virtual power plant load prediction set is established on the basis of a central air conditioner state evaluation value Ktz and the change of the virtual power plant load, and a virtual power plant load prediction model is established on the basis of a BP neural network prediction algorithm;
step 401, determining the following weather changes according to the received weather forecast, establishing a weather state data set according to the air temperature Kt, the wind speed Fs and the relative humidity RH obtained by the weather forecast, and correlating to form a weather influence coefficient Txs after dimensionless processing, wherein the weather influence coefficient Txs is obtained in the following manner:
the meaning and the value of the parameter are as follows:
，/>
and->
，/>
For the weight, its specific value is set by the user adjustment, +.>
Is a constant correction coefficient.
In use, an assessment of weather changes outside the building can be made based on the weather effect coefficients Txs to determine the weather conditions outside.
Step 402, combining with an air conditioner digital twin model, changing a weather influence coefficient Txs when a central air conditioner is in a use state, and obtaining the actual temperature of a marking position in a building when a central air conditioner state evaluation value Ktz is unchanged;
after multiple simulation tests, a temperature change model is constructed according to the change of the weather effect coefficient Txs and the corresponding change trend of the actual temperature;
step 403, when the actual temperature is unchanged, performing simulation analysis by taking a weather influence coefficient Txs as an independent variable to obtain a change trend of a central air-conditioning state evaluation value Ktz and a change trend of an affected virtual power plant load;
step 404, acquiring a change trend of the weather effect coefficient Txs, an actual temperature change trend, a change trend of the central air conditioning state evaluation value Ktz and a virtual power plant load change trend, and constructing a virtual power plant load prediction set;
according to a BP neural network prediction algorithm, combining sample data in a virtual power plant load prediction set, and constructing a virtual power plant load prediction model after training and testing;
in use, the contents of steps 401 to 404 are combined:
after the virtual power plant load prediction set is built, a virtual power plant load prediction model is built based on a BP neural network prediction algorithm, when a weather influence coefficient Txs changes, the load of the virtual power plant is predicted, particularly weather suddenly changes, when the electricity consumption in a building is changed greatly, the load change of the virtual power plant is predicted, corresponding electricity consumption requirements are determined, the overload of the virtual power plant is avoided, the building cannot be fully supplied with electricity, when the virtual power plant load prediction model predicts, reference parameters are more, prediction deviation is lower, and particularly when the weather changes, the influence of the change of the electricity consumption intensity of a central air conditioner on the load of the virtual power plant is predicted.
Step five, predicting a time node of the virtual power plant load exceeding a threshold value in an operation period according to the virtual power plant load prediction model, predicting possible operation risks of a virtual power plant scheduling system on the time node, and matching and outputting corresponding response schemes according to the operation risks;
the fifth step comprises the following steps:
step 501, when the virtual power plant is in an operation state, acquiring weather influence coefficients Txs at each time point (for example, one hour is taken as a time point) from weather forecast in a next operation period, that is, weather change in at least three days;
according to the virtual power plant load prediction model, predicting the load of the virtual power plant when the optimal temperature is maintained at each time node in the operation period and a corresponding central air conditioning state evaluation value Ktz;
step 502, acquiring known risks and corresponding risk characteristics which occur when the load of the virtual power plant dispatching system exceeds a threshold value, constructing a risk characteristic library, and searching and acquiring a corresponding solution corresponding to the known risks based on the known risks to construct a solution library;
predicting that the scheduling system of the virtual power plant may generate risk and corresponding risk characteristics on the next time node when the load of the virtual power plant exceeds the corresponding threshold;
and matching known risks from the risk feature library according to the risk features, and matching corresponding schemes from the scheme library according to the matched known risks and outputting the corresponding schemes.
In use, the contents of steps 501 and 502 are combined:
when the load of the virtual power plant exceeds the expected load, the scheduling risk that the scheduling system is likely to face is predicted, and a corresponding treatment scheme is matched according to the scheduling risk, so that maintenance personnel can quickly solve the risk and the problem which are likely to face, and timely solve the problem.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application.
Claims (7)
1. A building-based virtual power plant load prediction method is characterized by comprising the following steps of: the method comprises the following steps:
when a central air conditioner in a building is in a working state, collecting central air conditioner operation data, establishing a corresponding air conditioner digital twin model and a building model, and setting a marking position in the building; according to the actual temperature at the marked position and the central air-conditioning parameter, a central air-conditioning parameter data set is established, a correlation analysis model is established, the influence degree of variables in the central air-conditioning parameter data set on the actual temperature is determined, and when the optimum temperature exists in the building, the preset temperature which is required to be set by the central air-conditioner is determined; when the central air conditioner is in a continuous working state, a load change data set is established and a central air conditioner state evaluation value Ktz is obtained; according to the analysis of the correlation analysis model, a central air conditioner load correlation coefficient Fxs is formed;
when the weather outside the building changes, a weather state data set and a corresponding weather influence coefficient Txs are established, a digital twin model of an air conditioner is combined, a virtual power plant load prediction set is established on the basis of a central air conditioner state evaluation value Ktz and the change of the virtual power plant load, and a virtual power plant load prediction model is established on the basis of a BP neural network prediction algorithm; according to the virtual power plant load prediction model, predicting a time node when the virtual power plant load exceeds a threshold value in an operation period, predicting possible operation risks of a virtual power plant scheduling system on the time node, and matching and outputting corresponding response schemes according to the operation risks;
acquiring valve opening Kd, fan rotating speed Fj, circulating air quantity Xf and corresponding influence factors: the opening factor Ad, the fan factor Af and the air quantity factor Az are related to form a central air conditioning state evaluation value Ktz; the acquisition load of the central air-conditioning status evaluation value Ktz is as follows:
wherein, the liquid crystal display device comprises a liquid crystal display device,
is a constant correction coefficient;
the received weather forecast judges the following weather change, a weather state data set is established according to the air temperature Kt, the wind speed Fs and the relative humidity RH obtained by the weather forecast, and after dimensionless processing, weather influence coefficients Txs are formed in a correlation mode, wherein the weather influence coefficients Txs are obtained in the following mode:
the meaning and the value of the parameters are as follows:
，/>
and->
，
Is a weight, which hasThe body value is set by the user adjustment,/->
Is a constant correction coefficient;
combining with the air conditioner digital twin model, changing a weather influence coefficient Txs when the central air conditioner is in a use state, and obtaining the actual temperature of the marking position in the building when the central air conditioner state evaluation value Ktz is unchanged; constructing a temperature change model according to the change of the weather effect coefficient Txs and the corresponding change trend of the actual temperature; when the actual temperature is unchanged, performing simulation analysis by taking a weather influence coefficient Txs as an independent variable to obtain a change trend of a central air-conditioning state evaluation value Ktz and a change trend of an affected virtual power plant load; acquiring a change trend of a weather influence coefficient Txs, an actual temperature change trend, a change trend of a central air conditioning state evaluation value Ktz and a virtual power plant load change trend, and constructing a virtual power plant load prediction set; according to the BP neural network prediction algorithm, the sample data in the virtual power plant load prediction set are combined, and after training and testing, a virtual power plant load prediction model is constructed.
2. The building-based virtual power plant load prediction method according to claim 1, wherein:
when a central air conditioner in a building is in a working state, collecting running state data of the central air conditioner on the basis of combining building structures; at least the acquired data includes: presetting temperature, opening of a valve hole of a throttle valve, rotating speed of a fan and circulating air quantity, and summarizing to form a central air conditioner operation data set;
establishing a digital twin model of the air conditioner according to the equipment parameters and the operation parameters of the central air conditioner; after testing and training, outputting the air conditioner digital twin model; building models are built according to building structures, temperature detection modules are uniformly arranged in a plurality of areas with the most dense crowd distribution inside the building, and marking is carried out on the building models to form marking positions.
3. The building-based virtual power plant load prediction method according to claim 1, wherein:
when the central air conditioner is in a normal use state, acquiring the actual temperature at the marked position, judging the temperature difference between the actual temperature and the preset temperature, and acquiring the opening of a valve hole, the rotating speed of a fan, the circulating air quantity and the load of a virtual power plant at the moment of the central air conditioner; after the test, acquiring the actual temperature at the marked position and the parameters of the central air conditioner, and establishing a central air conditioner parameter data set; when the system is used, the correlation between the central air conditioning parameters and the load of the virtual power plant can be judged through collecting the central air conditioning parameters.
4. A building-based virtual power plant load prediction method according to claim 3, wherein:
based on a Monte Carlo simulation algorithm, after training and testing, constructing a correlation analysis model, and based on data in a central air conditioner parameter data set, judging the influence degree of an operation parameter on the actual temperature at a mark position; wherein at least the variables are determined: the valve opening, the fan rotating speed and the circulating air quantity influence factors on the actual temperature;
searching to obtain the optimum temperature in the building, adjusting central air-conditioning parameters based on the air-conditioning digital twin model, combining the temperature difference values, determining the preset temperature which the central air-conditioning should set when the optimum temperature is reached after testing, and marking the preset temperature in the building model.
5. The building-based virtual power plant load prediction method of claim 4, wherein:
combining with an air conditioner digital twin model, acquiring load change of a virtual power plant by changing preset temperature when a central air conditioner is in a continuous working state, establishing a load change data set, and correlating to form a central air conditioner state evaluation value Ktz;
when the central air-conditioning state evaluation value Ktz is larger than the threshold value, according to the analysis of the correlation analysis model, when the preset temperature is reached, the correlation between the central air-conditioning state evaluation value Ktz and the virtual power plant load is determined, and a central air-conditioning load correlation coefficient Fxs is formed.
6. The building-based virtual power plant load prediction method of claim 5, wherein:
acquiring weather influence coefficients Txs at each time point in a next operation period from weather forecast when the virtual power plant is in an operation state; according to the virtual power plant load prediction model, the load of the virtual power plant and the corresponding central air conditioning state evaluation value Ktz when the optimum temperature is maintained at each time node in the operation cycle are predicted.
7. The building-based virtual power plant load prediction method of claim 6, wherein:
acquiring known risks and corresponding risk characteristics which occur when the load of the virtual power plant dispatching system exceeds a threshold value, constructing a risk characteristic library, and searching and acquiring a corresponding solution corresponding to the known risks based on the known risks to construct a solution library;
predicting that the scheduling system of the virtual power plant may generate risk and corresponding risk characteristics on the next time node when the load of the virtual power plant exceeds the corresponding threshold; and matching known risks from the risk feature library according to the risk features, and matching corresponding schemes from the scheme library according to the matched known risks and outputting the corresponding schemes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310477585.5A CN116187598B (en) | 2023-04-28 | 2023-04-28 | Building-based virtual power plant load prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310477585.5A CN116187598B (en) | 2023-04-28 | 2023-04-28 | Building-based virtual power plant load prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116187598A CN116187598A (en) | 2023-05-30 |
| CN116187598B true CN116187598B (en) | 2023-07-04 |
Family
ID=86452714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310477585.5A Active CN116187598B (en) | 2023-04-28 | 2023-04-28 | Building-based virtual power plant load prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116187598B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116663863B (en) * | 2023-07-28 | 2023-10-20 | 石家庄科林电气股份有限公司 | Virtual power plant load prediction method based on scheduling plan |
| CN117249537B (en) * | 2023-11-20 | 2024-03-19 | 南京南自华盾数字技术有限公司 | Virtual power plant scheduling and control system and method based on central air conditioner |
| CN117490185B (en) * | 2023-12-29 | 2024-03-22 | 天津英泰华机电技术有限公司 | Intelligent central air conditioner control system and method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102052739A (en) * | 2010-12-27 | 2011-05-11 | 重庆大学 | Central air conditioner intelligent control system based on wireless sensor network and method |
| CN104778503A (en) * | 2015-03-16 | 2015-07-15 | 国家电网公司 | Method for forecasting public building air conditioner short-time base wire load with consideration of real-time weather factors |
| CN105990838A (en) * | 2016-05-17 | 2016-10-05 | 杭州电子科技大学 | Sea island microgrid optimization scheduling method considering schedulable and translatable loads |
| CN110322056A (en) * | 2019-06-19 | 2019-10-11 | 河海大学 | It is a kind of meter and central air conditioner system the random ADAPTIVE ROBUST Optimization Scheduling of virtual plant |
| CN111639823A (en) * | 2020-06-10 | 2020-09-08 | 天津大学 | Building cold and heat load prediction method constructed based on feature set |
| CN113240184A (en) * | 2021-05-21 | 2021-08-10 | 浙江大学 | Building space unit cold load prediction method and system based on federal learning |
| CN113255968A (en) * | 2021-04-30 | 2021-08-13 | 中国能源建设集团天津电力设计院有限公司 | Commercial office building refined load prediction method based on equipment and behavior information |
| CN113887127A (en) * | 2021-09-15 | 2022-01-04 | 杭州英集动力科技有限公司 | Virtual power plant optimal scheduling method and system based on building thermal inertia |
| CN114370696A (en) * | 2021-12-27 | 2022-04-19 | 杭州英集动力科技有限公司 | Method for controlling outlet water temperature of cooling tower of central air conditioner based on D-S evidence theory |
-
2023
- 2023-04-28 CN CN202310477585.5A patent/CN116187598B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102052739A (en) * | 2010-12-27 | 2011-05-11 | 重庆大学 | Central air conditioner intelligent control system based on wireless sensor network and method |
| CN104778503A (en) * | 2015-03-16 | 2015-07-15 | 国家电网公司 | Method for forecasting public building air conditioner short-time base wire load with consideration of real-time weather factors |
| CN105990838A (en) * | 2016-05-17 | 2016-10-05 | 杭州电子科技大学 | Sea island microgrid optimization scheduling method considering schedulable and translatable loads |
| CN110322056A (en) * | 2019-06-19 | 2019-10-11 | 河海大学 | It is a kind of meter and central air conditioner system the random ADAPTIVE ROBUST Optimization Scheduling of virtual plant |
| CN111639823A (en) * | 2020-06-10 | 2020-09-08 | 天津大学 | Building cold and heat load prediction method constructed based on feature set |
| CN113255968A (en) * | 2021-04-30 | 2021-08-13 | 中国能源建设集团天津电力设计院有限公司 | Commercial office building refined load prediction method based on equipment and behavior information |
| CN113240184A (en) * | 2021-05-21 | 2021-08-10 | 浙江大学 | Building space unit cold load prediction method and system based on federal learning |
| CN113887127A (en) * | 2021-09-15 | 2022-01-04 | 杭州英集动力科技有限公司 | Virtual power plant optimal scheduling method and system based on building thermal inertia |
| CN114370696A (en) * | 2021-12-27 | 2022-04-19 | 杭州英集动力科技有限公司 | Method for controlling outlet water temperature of cooling tower of central air conditioner based on D-S evidence theory |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116187598A (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116187598B (en) | Building-based virtual power plant load prediction method | |
| Fan et al. | Cooling load prediction and optimal operation of HVAC systems using a multiple nonlinear regression model | |
| CN104303203B (en) | Energy search engine method and system | |
| Reddy | Literature Review on Calibration of Building Energy Simulation Programs: Uses, Problems, Procedures, Uncertainty, and Tools. | |
| CN102705957B (en) | Method and system for predicting hourly cooling load of central air-conditioner in office building on line | |
| EP2858015A1 (en) | System and method for simulation, control and performance monitoring of energy systems | |
| CN106779129A (en) | A kind of Short-Term Load Forecasting Method for considering meteorologic factor | |
| CN110458340B (en) | Building air conditioner cold load autoregressive prediction method based on mode classification | |
| Lu et al. | Operational optimization of district heating system based on an integrated model in TRNSYS | |
| Castaldo et al. | Uses of dynamic simulation to predict thermal‐energy performance of buildings and districts: a review | |
| Ledva et al. | Real-time energy disaggregation of a distribution feeder's demand using online learning | |
| CN108388962A (en) | A kind of wind power forecasting system and method | |
| CN105046595A (en) | Internet-of-things technology based energy efficiency assessment and diagnosis cloud system and method | |
| CN108197404A (en) | A kind of building load Forecasting Methodology based on time hereditary capacity | |
| Biyik et al. | Cloud-based model predictive building thermostatic controls of commercial buildings: Algorithm and implementation | |
| CN106403162A (en) | Local heat comfort control method, local heat comfort controller and control system | |
| CN115481918A (en) | Active sensing and predictive analysis system for unit state based on source network load storage | |
| Yang et al. | Strategy of constructing virtual peaking unit by public buildings' central air conditioning loads for day-ahead power dispatching | |
| CN117091242A (en) | Evaluation method, temperature setting method and system for air conditioner temperature control load cluster | |
| CN108345996A (en) | A kind of system and method reducing wind power checking energy | |
| CN115330280A (en) | Method and system for evaluating adjustable potential of air conditioner load demand response in aggregated load | |
| Yang et al. | Modeling and validation of a novel load model considering uncertain thermal disturbance in the district heating system | |
| CN115271168A (en) | Method and device for predicting response potential of electrical load and storage medium | |
| CN113341792A (en) | Building data acquisition method and system based on BIM | |
| CN112671036A (en) | Micro-grid scheduling method considering demand response |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |