CN110410942A - A kind of Cooling and Heat Source machine room energy-saving optimal control method and system - Google Patents
A kind of Cooling and Heat Source machine room energy-saving optimal control method and system Download PDFInfo
- Publication number
- CN110410942A CN110410942A CN201910691078.5A CN201910691078A CN110410942A CN 110410942 A CN110410942 A CN 110410942A CN 201910691078 A CN201910691078 A CN 201910691078A CN 110410942 A CN110410942 A CN 110410942A
- Authority
- CN
- China
- Prior art keywords
- host
- prediction
- parameter
- load
- pump
- 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.)
- Granted
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/46—Improving electric energy efficiency or saving
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2130/00—Control inputs relating to environmental factors not covered by group F24F2110/00
- F24F2130/10—Weather information or forecasts
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2140/00—Control inputs relating to system states
- F24F2140/50—Load
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2140/00—Control inputs relating to system states
- F24F2140/60—Energy consumption
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The present invention provides a kind of Cooling and Heat Source machine room energy-saving optimal control method and systems, its method includes: to establish neural network load forecasting model, neural network host parameter model and neural network parameters of pump model according to the historical data of the Cooling and Heat Source the computer room each system and equipment operating parameter that store in database；The outdoor weather Prediction Parameters for obtaining prediction time obtain prediction air conditioner load using neural network load forecasting model；Prediction air conditioner load is transferred to host, freezing side and cold side water pump, obtains host constraint condition and water pump constraint condition；Host energy consumption range and pump energy consumption range are obtained according to neural network host parameter Model Neural parameters of pump model；The output parameter of host and water pump is determined after successive ignition calculates.The present invention reaches better energy-saving effect to predict that load instructs the output of Cooling and Heat Source computer room refrigerating capacity, while the output parameters such as energy saving group control algorithm control host, water pump established using historical data.
Description
Technical field
The present invention relates to air conditioner energy saving control technology field, espespecially a kind of Cooling and Heat Source machine room energy-saving optimal control method and it is
System.
Background technique
In recent years, artificial intelligence had great development in fields such as image procossing, natural-sounding processing, robots, than
More typical application has image recognition, artificial customer service and the smart home to link with intelligent sound box etc..In answering for industrial circle
With also having gradually developed, such as equipment fault diagnosis, automatic Pilot.In field of central air-conditioning, have many using neural
The means of the artificial intelligence such as network predict the case of following one day air-conditioning load trend variation, but come with artificial intelligence technology
The case for controlling the Cooling and Heat Source machine room energy-saving control of central air-conditioning is less.
The equipment of the system of air-conditioning is according to peak load come type selecting, to cope with the highest temperature or lowest temperature in 1 year
Weather, and fewer and fewer in such weather 1 year, oepration at full load in few situation, therefore the surplus capacity of equipment is very big.According to
Statistics, the energy consumption of air-conditioning system account about the 40% of whole building energy consumption, and accounting is larger, therefore air-conditioning system has very big section
It can space.Most of energy consumptions of central air conditioner system concentrate on Cooling and Heat Source computer room, therefore Cooling and Heat Source computer room is energy-efficient emphasis.
Substantially there are three the stage, the first stage realizes that basic equipment can for the development of Cooling and Heat Source computer room automatic control control system
Prison is controllably and the automatic adding machine function of equipment, second stage increase Energy Saving Strategy (such as Multimode Control), realize system
Team control, phase III realize the centralized management and energy conservation team control mode of entry based on big data, cloud platform.
With greatly developing for computer technology, the present invention proposes a kind of Cooling and Heat Source machine room energy-saving optimal control method and is
System.
Summary of the invention
The object of the present invention is to provide a kind of Cooling and Heat Source machine room energy-saving optimal control method and system, realization is made full use of
There is the value of historical data, the parameter characteristic of depth excavating equipment realizes Cooling and Heat Source in conjunction with energy-saving run theory and device characteristics
Machine room energy-saving control.
Technical solution provided by the invention is as follows:
The present invention provides a kind of Cooling and Heat Source machine room energy-saving optimal control method, comprising:
Establish the historical data of database purchase Cooling and Heat Source computer room each system and equipment operating parameter；
Off-line training is carried out using the load parameter in the database as training data, establishes neural network load prediction
Model；
Off-line training is carried out using the host parameter in the database as training data, establishes neural network host parameter
Model；
Off-line training is carried out using the parameters of pump in the database as training data, establishes neural network parameters of pump
Model；
The outdoor weather Prediction Parameters for obtaining prediction time, according to the neural network load forecasting model and the outdoor
Weather prognosis parameter obtains prediction air conditioner load；
The prediction air conditioner load is transferred to host and water pump, respectively obtains corresponding host constraint condition and water pump about
Beam condition, the water pump include freezing side and cold side water pump；
Host energy consumption range is obtained according to the neural network host parameter model and the host constraint condition；
Water is obtained according to the neural network parameters of pump model and the water pump constraint condition and host constraint condition
Pump energy consumption range；
It is calculated according to the host energy consumption range and the pump energy consumption range by successive ignition and determines energy saving of system group
The prediction output parameter of host and water pump under control strategy.
Further, it is calculated according to the host energy consumption range and the pump energy consumption range by successive ignition and determines system
After the prediction output parameter of the host and water pump united under energy saving automation strategy further include:
The parameter information of prediction time is obtained by sensor；
The reality output parameter of practical air conditioner load and host and water pump is calculated according to the parameter information；
The prediction air conditioner load, prediction output parameter, practical air conditioner load and reality output parameter are uploaded to institute
State database.
Further, the outdoor weather Prediction Parameters for obtaining prediction time, according to the neural network load forecasting model
Prediction air conditioner load is obtained with the outdoor weather Prediction Parameters to specifically include:
Obtain the outdoor weather Prediction Parameters of prediction time；
It is negative that tentative prediction air-conditioning is obtained according to the neural network load forecasting model and the outdoor weather Prediction Parameters
Lotus；
Obtain the prediction air conditioner load and actual load parameter of preset time before prediction time in the database；
According to the error of the prediction air conditioner load and actual load parameter of the preset time, to the tentative prediction air-conditioning
Load is modified, and obtains the prediction air conditioner load of prediction time.
Further, host energy consumption model is obtained according to the neural network host parameter model and the host constraint condition
It encloses and specifically includes:
Preliminary host energy consumption range is obtained according to the neural network host parameter model and the host constraint condition；
Obtain in the database host output parameter in the prediction output parameter of preset time before prediction time and
Host reality output parameter in reality output parameter；
According to the error of the host output parameter of the preset time and host reality output parameter, to the preliminary host
Energy consumption range is modified, and obtains the host energy consumption range of prediction time.
Further, according to the neural network parameters of pump model and the water pump constraint condition and host constraint condition
Pump energy consumption range is obtained to specifically include:
It is obtained according to the neural network parameters of pump model and the water pump constraint condition and host constraint condition preliminary
Pump energy consumption range；
Obtain in the database water pump output parameter in the prediction output parameter of preset time before prediction time and
Water pump reality output parameter in reality output parameter；
According to the error of the water pump output parameter of the preset time and water pump reality output parameter, to the preliminary water pump
Energy consumption range is modified, and obtains the pump energy consumption range of prediction time.
The present invention also provides a kind of Cooling and Heat Source machine room energy-saving Optimal Control Systems, comprising:
Database module establishes the historical data of database purchase Cooling and Heat Source computer room each system and equipment operating parameter；
Model module is carried out the load parameter in the database that the database module is established as training data
Off-line training establishes neural network load forecasting model；
The model module, using the host parameter in the database that the database module is established as training data
Off-line training is carried out, neural network host parameter model is established；
The model module, using the parameters of pump in the database that the database module is established as training data
Off-line training is carried out, neural network parameters of pump model is established；
Load prediction module obtains the outdoor weather Prediction Parameters of prediction time, the institute established according to the model module
It states neural network load forecasting model and the outdoor weather Prediction Parameters obtains prediction air conditioner load；
The prediction air conditioner load that the load prediction module obtains is transferred to host and water by load transfer module
Pump, respectively obtains corresponding host constraint condition and water pump constraint condition, and the water pump includes freezing side and cold side water pump；
Host parameter analysis module, the neural network host parameter model and described established according to the model module
The host constraint condition that load transfer module determines obtains host energy consumption range；
Parameters of pump analysis module, the neural network parameters of pump model and described established according to the model module
The water pump constraint condition that load transfer module and host constrained parameters determine obtains pump energy consumption range；
Output parameter analysis module, the host energy consumption range and described determined according to the host parameter analysis module
The pump energy consumption range that parameters of pump analysis module determines is calculated by successive ignition and is determined under energy saving of system automation strategy
Host and water pump prediction output parameter.
Further, further includes:
Parameter information obtains module, and the parameter information of prediction time is obtained by sensor；
Actual parameter analysis module obtains the parameter information that module obtains according to the parameter information and reality is calculated
The reality output parameter of border air conditioner load and host and water pump；
Processing module obtains prediction air conditioner load that the load prediction module obtains, the output parameter analysis module
To prediction output parameter, the obtained practical air conditioner load and reality output parameter be uploaded to the database module and build
The vertical database.
Further, the load prediction module specifically includes:
Meteorologic parameter acquiring unit obtains the outdoor weather Prediction Parameters of prediction time；
Load estimation unit is obtained according to the neural network load forecasting model and the meteorologic parameter acquiring unit
The outdoor weather Prediction Parameters obtain tentative prediction air conditioner load；
Load parameter acquiring unit, obtain preset time before prediction time in the database prediction air conditioner load and
Actual load parameter；
Load amending unit, according to the prediction air conditioner load for the preset time that the load parameter acquiring unit obtains
With the error of actual load parameter, the tentative prediction air conditioner load that the load estimation unit obtains is modified, is obtained
To the prediction air conditioner load of prediction time.
Further, the host parameter analysis module specifically includes:
Host energy consumption calculation unit obtains just according to the neural network host parameter model and the host constraint condition
Walk host energy consumption range；
Host parameter acquiring unit obtains in the prediction output parameter of preset time before prediction time in the database
Host output parameter and reality output parameter in host reality output parameter；
The host of host energy consumption amending unit, the preset time obtained according to the host parameter acquiring unit exports
Parameter and host reality output parameter error, the preliminary host energy consumption range that the host energy consumption calculation unit is obtained into
Row amendment, obtains the host energy consumption range of prediction time.
Further, the parameters of pump analysis module specifically includes:
Pump energy consumption computing unit, according to the neural network parameters of pump model and the water pump constraint condition and host
Constraint condition obtains preliminary pump energy consumption range；
Parameters of pump acquiring unit obtains in the prediction output parameter of preset time before prediction time in the database
Water pump output parameter and reality output parameter in water pump reality output parameter；
The water pump of pump energy consumption amending unit, the preset time obtained according to the parameters of pump acquiring unit exports
The error of parameter and water pump reality output parameter, the preliminary pump energy consumption range that the pump energy consumption computing unit is obtained
It is modified, obtains the pump energy consumption range of prediction time.
A kind of Cooling and Heat Source machine room energy-saving optimal control method and system provided through the invention, can bring it is following at least
It is a kind of the utility model has the advantages that
1, in the present invention, it is based on historical data, establishes neural network load forecasting model, Accurate Prediction following each moment
Air conditioner load.
2, in the present invention, it is based on historical data, establishes neural network host parameter model and neural network parameters of pump mould
Type, the accurate parameters relationship obtained between equipment output load ability and consumption power etc..
3, in the present invention, depth combination bonding apparatus actual characteristic and system team control Energy saving theory in guarantee system and are set
Under standby safe operating conditions, operate in Cooling and Heat Source computer room under the load of demand in a manner of most energy-efficient.
Detailed description of the invention
Below by clearly understandable mode, preferred embodiment is described with reference to the drawings, to a kind of Cooling and Heat Source machine room energy-saving
Above-mentioned characteristic, technical characteristic, advantage and its implementation of optimal control method and system are further described.
Fig. 1 is a kind of flow chart of one embodiment of Cooling and Heat Source machine room energy-saving optimal control method of the present invention；
Fig. 2, Fig. 3, Fig. 4, Fig. 5 are a kind of second embodiments of Cooling and Heat Source machine room energy-saving optimal control method of the present invention
Flow chart；
Fig. 6 is a kind of structural schematic diagram of the third embodiment of Cooling and Heat Source machine room energy-saving Optimal Control System of the present invention；
Fig. 7 is that the structure of the 4th embodiment of a kind of Cooling and Heat Source machine room energy-saving optimal control method of the present invention and system is shown
It is intended to；
Fig. 8 is the power of host and the schematic diagram of refrigerating capacity variation tendency；
Fig. 9 is the energy consumption of water pump and the schematic diagram of changes in flow rate trend；
Figure 10 is the schematic diagram of cooling water temperature Yu host and cooling water pump group's variation relation；
Figure 11 is the schematic diagram of cooling water temperature Yu host and chilled water pump group's variation relation.
Specific embodiment
It, below will be to ordinarily in order to clearly illustrate the embodiment of the present invention or technical solution in the prior art
Bright book Detailed description of the invention a specific embodiment of the invention.It should be evident that the accompanying drawings in the following description is only of the invention one
A little embodiments for those of ordinary skill in the art without creative efforts, can also be according to these
Attached drawing obtains other attached drawings, and obtains other embodiments.
In order to make simplified form, part related to the present invention is only schematically shown in each figure, their not generations
Its practical structures as product of table.In addition, there is identical structure or function in some figures so that simplified form is easy to understand
Component, only symbolically depict one of those, or only marked one of those.Herein, "one" not only table
Show " only this ", can also indicate the situation of " more than one ".
The first embodiment of the present invention, as shown in Figure 1, a kind of Cooling and Heat Source machine room energy-saving optimal control method, comprising:
S100 establishes the historical data of database purchase Cooling and Heat Source computer room each system and equipment operating parameter；
Specifically, neural network model is necessarily required to be trained by a large amount of data, therefore establish data inventory
The historical data of Cooling and Heat Source computer room each system and equipment operating parameter is stored up, the data of record should include host operating parameter, water pump
Operating parameter, the operating parameter of system (supply and return water temperature, pressure, flow, valve state etc.), each system loading, time and gas
As parameter etc., the data volume of record should be more as far as possible and detailed, should include at least a nearest 1 year complete Heating Period as far as possible
With for cold period.More for trained data, trained effect is better.Therefore, above-mentioned parameter was only done for example, not generation
Above-mentioned data are only included in database in table the present embodiment, the present embodiment does not do specific limit to data included in database
It is fixed, depending on establishing the needs of neural network model.
Based on a large amount of historical datas of Cooling and Heat Source computer room operation, load prediction, host, chilled water pump and cooling water pump are established
Neural network model, and carry out off-line training.
The load parameter in the database is carried out off-line training by S200, establishes neural network load
Prediction model；
Specifically, neural network load forecasting model is used to predict the load condition of the following sometime building, building
Load it is related with outdoor weather conditions, fabric structure and building interior equipment, personnel, building structure immobilizes, building
Internal unit usually has certain rule with personnel and can follow, and rule is extracted by the way of neural network, and combines outdoor
Environment parament carries out load prediction.
Therefore, off-line training is carried out using the load parameter in database as training data, it is pre- establishes neural network load
Survey model.For example, extracting the data such as the historical time load of each system, out door climatic parameter, training data, load value are established
As label, suitable study is arranged as training sample, the appropriate number and neuron number for selecting hidden layer in other data
Rate carries out off-line training, establishes neural network load forecasting model.
The host parameter in the database is carried out off-line training by S300, establishes neural network host
Parameter model；
Return specifically, neural network host parameter model is used for the realization operation power to host with load condition
It receives, for host under different inlet and outlet temperatures, the load and consumed power that can be provided are different, therefore are needed
It is trained using historical data various dimensions.
Therefore, off-line training is carried out using the host parameter in database as training data, establishes neural network host ginseng
Exponential model.For example, the output load of host, power, evaporator, condenser inlet and outlet temperature etc. are extracted from database, with
Power is output, and other parameters establish corresponding sample and label as input layer, select number, the mind of hidden layer appropriate
Through first number, activation primitive, learning rate, off-line calculation is carried out.Each host should individually establish model, for can heat it is cold and heating
Heat pump main frame, the model under refrigeration and heating condition should be established respectively.
The parameters of pump in the database is carried out off-line training by S400, establishes neural network water pump
Parameter model；
Specifically, neural network parameters of pump model is for concluding water pump water pump under different number of units and different frequency
Flow and power consumption situation, the operating condition of a water pump and two water pumps differ greatly, need to extract from historical data
Situation is trained under various states.The neural network model of every class equipment is obstructed.
Therefore, off-line training is carried out using the parameters of pump in database as training data, establishes neural network water pump ginseng
Exponential model substantially extracts the drag characteristic of pump characteristic and pipe network.Under different water pump number of units, host number of units,
The drag characteristic of pipe network is different, only in the case where all devices unlatching quantity is constant, valve opening is constant, pipe network
Resistance coefficient it is constant.Therefore the parameter of input is more, and parameters of pump model cannot establish model with separate unit water pump, should be with one
The water pump group of system establishes neural network model as a whole.
Neural network model in above-mentioned step S200-S400 can be handled simultaneously, there is no it is substantial when
Between on sequencing.
S500 obtains the outdoor weather Prediction Parameters of prediction time, according to the neural network load forecasting model and described
Outdoor weather Prediction Parameters obtain prediction air conditioner load；
Specifically, obtaining the outdoor weather of prediction time by the approach such as weather forecast or the small-sized weather station voluntarily set up
Prediction Parameters obtain the prediction air conditioner load of corresponding prediction time by neural network load forecasting model.
The prediction air conditioner load is transferred to host and water pump by S600, respectively obtains corresponding host constraint condition and water
Constraint condition is pumped, the water pump includes freezing side and cold side water pump；
Specifically, obtained prediction air conditioner load is transferred to host, freezing side and cold side water pump, correspondence is respectively obtained
Host constraint condition and water pump constraint condition, that is, host and water pump each parameter allowed band.
S700 obtains host energy consumption range according to the neural network host parameter model and the host constraint condition；
S800 is obtained according to the neural network parameters of pump model and the water pump constraint condition and host constraint condition
Pump energy consumption range；
S900 is calculated by successive ignition according to the host energy consumption range and the pump energy consumption range and is determined system section
The prediction output parameter of host and water pump under energy automation strategy.
Specifically, neural network host parameter model and neural network parameters of pump model are called, respectively according to corresponding
Host constraint condition and water pump constraint condition calculate energy consumption range, comprehensively consider host energy consumption range and pump energy consumption range, really
The parameter of the minimum corresponding host of whole system comprehensive energy consumption under energy saving of system automation strategy and water pump is determined as output parameter.
In the present embodiment, to predict that air conditioner load instructs the output of Cooling and Heat Source computer room refrigerating capacity, real-time load is matched, it will not
Cause the waste of refrigerating capacity, while the output parameters such as energy saving group control algorithm control host, water pump established using historical data, In
Under the premise of meeting load and equipment safety operation, system COP is maximized, better energy-saving effect is reached.
Second embodiment of the invention is the optimal enforcement example of above-mentioned first embodiment, as shown in Fig. 2, Fig. 3, Fig. 4, Fig. 5,
The present embodiment is compared with above-mentioned first embodiment, and main improve is, according to the host energy consumption range and the pump energy consumption
Range is also wrapped after calculating the prediction output parameter for determining host and water pump under energy saving of system automation strategy by successive ignition
It includes:
S950 obtains the parameter information of prediction time by sensor；
The reality output parameter of practical air conditioner load and host and water pump is calculated according to the parameter information by S960；
S970 uploads the prediction air conditioner load, prediction output parameter, practical air conditioner load and reality output parameter
To the database.
Specifically, obtaining prediction time by sensor when the time reaching prediction time described in first embodiment
Parameter information, parameter information includes the parameter informations such as the water temperature of host and water pump, then according to the parameter information of acquisition calculate,
Obtain the reality output parameter of host and water pump.
Prediction air conditioner load, prediction output parameter, practical air conditioner load and reality output parameter are uploaded to database
It is stored, provides amendment foundation for PREDICTIVE CONTROL next time.In addition, the prediction air conditioner load and prediction for prediction time are defeated
Parameter can be uploaded to database in the above-mentioned first time calculated and be stored out, it is not absolutely required to practical air-conditioning
Load and reality output parameter upload simultaneously, it is only necessary to mark in the database to time, property of all data etc.
Note.
S500 obtains the outdoor weather Prediction Parameters of prediction time, according to the neural network load forecasting model and described
Outdoor weather Prediction Parameters obtain prediction air conditioner load and specifically include:
The outdoor weather Prediction Parameters of S510 acquisition prediction time；
S520 obtains tentative prediction sky according to the neural network load forecasting model and the outdoor weather Prediction Parameters
Adjust load；
S530 obtains the prediction air conditioner load and actual load parameter of preset time before prediction time in the database；
S540 according to the preset time prediction air conditioner load and actual load parameter error, to the tentative prediction
Air conditioner load is modified, and obtains the prediction air conditioner load of prediction time；
S700 obtains host energy consumption range tool according to the neural network host parameter model and the host constraint condition
Body includes:
S710 obtains preliminary host energy consumption model according to the neural network host parameter model and the host constraint condition
It encloses；
S720 obtains the host output ginseng in the prediction output parameter of preset time before prediction time in the database
Host reality output parameter in several and reality output parameter；
S730 is according to the host output parameter of the preset time and the error of host reality output parameter, to described preliminary
Host energy consumption range is modified, and obtains the host energy consumption range of prediction time；
S800 is obtained according to the neural network parameters of pump model and the water pump constraint condition and host constraint condition
Pump energy consumption range specifically includes:
S810 is obtained according to the neural network parameters of pump model and the water pump constraint condition and host constraint condition
Preliminary pump energy consumption range；
S820 obtains the water pump output ginseng in the prediction output parameter of preset time before prediction time in the database
Water pump reality output parameter in several and reality output parameter；
S830 is according to the water pump output parameter of the preset time and the error of water pump reality output parameter, to described preliminary
Pump energy consumption range is modified, and obtains the pump energy consumption range of prediction time.
Specifically, based on the basis of step S960, system in real time by load parameter and host, water pump output parameter on
Database is reached to be recorded, then neural network model (including neural network load forecasting model, neural network host parameter
Model and neural network parameters of pump model) application process in, based on external input parameter (outdoor weather prediction ginseng
Number, host constraint condition, water pump constraint condition) it obtains tentatively exporting result (tentative prediction air conditioner load, preliminary host energy consumption model
Enclose, preliminary pump energy consumption range) after, also preliminary output result is modified, obtaining final output result, (prediction is empty
Adjust load, host energy consumption range, pump energy consumption range).Wherein, modified mode is, chose before prediction time any one or
The predicted value and actual value at multiple moment, calculate the error amount between both, (are selected when multiple moment average according to error amount
Error amount or weighted average error value) it is modified.
In the present embodiment, energy saving of system group control algorithm is the realization of Cooling and Heat Source machine room energy-saving team control theory, neural network mould
Type and group control algorithm are cores, therefore neural network model is also needed in application process to output result according to historical forecast number
According to being modified, to improve the accuracy of prediction result.
The third embodiment of the present invention, as shown in fig. 6, a kind of Cooling and Heat Source machine room energy-saving Optimal Control System 100, comprising:
Database module 110 establishes the historical data of database purchase Cooling and Heat Source computer room each system and equipment operating parameter；
Model module 120, the load parameter in the database that the database module 110 is established is as training number
According to off-line training is carried out, neural network load forecasting model is established；
The model module 120, the host parameter in the database that the database module 110 is established is as instruction
Practice data and carry out off-line training, establishes neural network host parameter model；
The model module 120, the parameters of pump in the database that the database module 110 is established is as instruction
Practice data and carry out off-line training, establishes neural network parameters of pump model；
Load prediction module 130 obtains the outdoor weather Prediction Parameters of prediction time, is built according to the model module 120
The vertical neural network load forecasting model and the outdoor weather Prediction Parameters obtain prediction air conditioner load；
The load prediction module 130 specifically includes:
Meteorologic parameter acquiring unit 131 obtains the outdoor weather Prediction Parameters of prediction time；
Load estimation unit 132, according to the neural network load forecasting model and the meteorologic parameter acquiring unit 131
The outdoor weather Prediction Parameters obtained obtain tentative prediction air conditioner load；
Load parameter acquiring unit 133, the prediction air-conditioning for obtaining preset time before prediction time in the database are negative
Lotus and actual load parameter；
Load amending unit 134, according to the prediction sky for the preset time that the load parameter acquiring unit 133 obtains
The error for adjusting load and actual load parameter, the tentative prediction air conditioner load that the load estimation unit 132 is obtained into
Row amendment, obtains the prediction air conditioner load of prediction time；
Load transfer module 140, the prediction air conditioner load that the load prediction module 130 is obtained are transferred to host
And water pump, corresponding host constraint condition and water pump constraint condition are respectively obtained, the water pump includes freezing side and cold side water
Pump；
Host parameter analysis module 150, the neural network host parameter model established according to the model module 120
The host constraint condition determined with the load transfer module 140 obtains host energy consumption range；
The host parameter analysis module 150 specifically includes:
Host energy consumption calculation unit 151 is obtained according to the neural network host parameter model and the host constraint condition
Take preliminary host energy consumption range；
Host parameter acquiring unit 152 obtains the prediction output ginseng of preset time before prediction time in the database
Host reality output parameter in host output parameter and reality output parameter in number；
Host energy consumption amending unit 153, according to the master for the preset time that the host parameter acquiring unit 152 obtains
Machine output parameter is modified the preliminary host energy consumption range that the host actual consumption computing unit obtains, and obtains pre-
Survey the host energy consumption range at moment；
Parameters of pump analysis module 160, the neural network parameters of pump model established according to the model module 120
The water pump constraint condition and host constrained parameters determined with the load transfer module 140 obtains pump energy consumption range；
The parameters of pump analysis module 160 specifically includes:
Pump energy consumption computing unit 161, according to the neural network parameters of pump model and the water pump constraint condition and
Host constraint condition obtains preliminary pump energy consumption range；
Parameters of pump acquiring unit 162 obtains the prediction output ginseng of preset time before prediction time in the database
Water pump reality output parameter in water pump output parameter and reality output parameter in number；
Pump energy consumption amending unit 163, according to the water for the preset time that the parameters of pump acquiring unit 162 obtains
Pump the error of output parameter and water pump reality output parameter, the preliminary water obtained to the pump energy consumption computing unit 161
Pump energy consumption range is modified, and obtains the pump energy consumption range of prediction time；
Output parameter analysis module 170, the host energy consumption range determined according to the host parameter analysis module 150
The pump energy consumption range determined with the parameters of pump analysis module 160 calculates by successive ignition and determines energy saving of system group
The prediction output parameter of host and water pump under control strategy；
Parameter information obtains module 180, and the parameter information of prediction time is obtained by sensor；
Actual parameter analysis module 185 obtains the parameter information that module 180 obtains according to the parameter information and calculates
Obtain the reality output parameter of practical air conditioner load and host and water pump；
Processing module 190, the prediction air conditioner load that the load prediction module 130 is obtained, output parameter analysis
Prediction output parameter, the obtained practical air conditioner load and the reality output parameter that module 170 obtains are uploaded to the number
The database established according to library module 110.
The concrete operations mode of modules in the present embodiment has been carried out in above-mentioned corresponding embodiment of the method
Detailed description, therefore no longer repeated one by one.
The fourth embodiment of the present invention, as shown in fig. 7, a kind of Cooling and Heat Source machine room energy-saving optimal control method and system, packet
It includes: database, neural network load forecasting model, neural network host parameter model, neural network parameters of pump model, system
Energy saving group control algorithm, wherein historical data base is basis, and neural network model and group control algorithm are cores.
Depth bonding apparatus actual characteristic and system team control Energy saving theory are guaranteeing system and equipment safety operation condition
Under, Cooling and Heat Source computer room is operated under the load of demand in a manner of most energy-efficient.Initially set up the neural network mould of load prediction
The neural network parameter model of type and host and water pump carries out off-line training using a large amount of historical data, it is negative to obtain building
Lotus and the accurate characteristic of equipment.Secondly by outdoor weather conditions parameter (such as weather forecast), it is built-in that one day future is calculated in real time
The load built.Then by energy saving automation strategy, host and water pump are allocated, controlled in the constraint condition of safety, and
The output of real-time calculating main frame and water pump, so that the refrigerating capacity of equipment output or heating capacity meet workload demand.It is finally output to
In the controller of equipment, equipment is executed according to the result of calculating, and record data.
Host C OP high is not meant to certain energy conservation.No matter how host C OP changes, under identical operating condition, the function of host
Rate increases with refrigerating capacity and is increased, as shown in figure 8, wasting part system if the refrigerating capacity of host has been more than the load of demand
Cooling capacity, even if COP high, energy consumption may also can be higher than the energy consumption under demand load, and deliberately make host work in the higher area COP
The problem of domain may bring refrigerating capacity to be higher than demand load, causes energy waste.
Similarly, in the case of water pump also has similar, as shown in figure 9, under other conditions same case, the energy consumption of water pump
It is to increase as flow increases, suitable flow should be selected, it is not necessary in order to make water pump operation deliberately improve stream in high efficient district
Amount.
According to inverse Carnot cycle principle, cooling water temperature is lower, and chilled water temperature is higher, the power of host under same load
Lower, host C OP is higher, and shown in Fig. 10 is the relationship of cooling water temperature Yu host and cooling water pump group, and other parameters are constant
When, main engine power is increased with cooling water temperature and is increased, and cooling water pump group power is reduced with cooling water temperature height, and there are one
A optimal cooling water temperature makes the sum of host and water pump group's general power minimum.Similarly also have for freezing side as shown in figure 11
Similar rule.
Energy conservation group control method final output control object provided by the invention includes: the load value of prediction, host number of units, sets
Determine temperature, cooling water number of units, cooling pump frequency, chilled water pump number of units, chilled water pump frequency, bypass valve opening etc..
It should be noted that above-described embodiment can be freely combined as needed.The above is only of the invention preferred
Embodiment, it is noted that for those skilled in the art, in the premise for not departing from the principle of the invention
Under, several improvements and modifications can also be made, these modifications and embellishments should also be considered as the scope of protection of the present invention.
Claims (10)
1. a kind of Cooling and Heat Source machine room energy-saving optimal control method characterized by comprising
Establish the historical data of database purchase Cooling and Heat Source computer room each system and equipment operating parameter；
Off-line training is carried out using the load parameter in the database as training data, establishes neural network load prediction mould
Type；
Off-line training is carried out using the host parameter in the database as training data, establishes neural network host parameter mould
Type；
Off-line training is carried out using the parameters of pump in the database as training data, establishes neural network parameters of pump mould
Type；
The outdoor weather Prediction Parameters for obtaining prediction time, according to the neural network load forecasting model and the outdoor weather
Prediction Parameters obtain prediction air conditioner load；
The prediction air conditioner load is transferred to host and water pump, respectively obtains corresponding host constraint condition and water pump constraint item
Part, the water pump include freezing side and cold side water pump；
Host energy consumption range is obtained according to the neural network host parameter model and the host constraint condition；
Water pump energy is obtained according to the neural network parameters of pump model and the water pump constraint condition and host constraint condition
Consume range；
It is calculated according to the host energy consumption range and the pump energy consumption range by successive ignition and determines energy saving of system team control plan
The prediction output parameter of host and water pump under slightly.
2. Cooling and Heat Source machine room energy-saving optimal control method according to claim 1, which is characterized in that according to the host energy
It consumes range and the pump energy consumption range and calculates the host and water pump determined under energy saving of system automation strategy by successive ignition
After prediction output parameter further include:
The parameter information of prediction time is obtained by sensor；
The reality output parameter of practical air conditioner load and host and water pump is calculated according to the parameter information；
The prediction air conditioner load, prediction output parameter, practical air conditioner load and reality output parameter are uploaded to the number
According to library.
3. Cooling and Heat Source machine room energy-saving optimal control method according to claim 2, which is characterized in that obtain prediction time
It is empty to obtain prediction according to the neural network load forecasting model and the outdoor weather Prediction Parameters for outdoor weather Prediction Parameters
Load is adjusted to specifically include:
Obtain the outdoor weather Prediction Parameters of prediction time；
Tentative prediction air conditioner load is obtained according to the neural network load forecasting model and the outdoor weather Prediction Parameters；
Obtain the prediction air conditioner load and actual load parameter of preset time before prediction time in the database；
According to the error of the prediction air conditioner load and actual load parameter of the preset time, to the tentative prediction air conditioner load
It is modified, obtains the prediction air conditioner load of prediction time.
4. Cooling and Heat Source machine room energy-saving optimal control method according to claim 2, which is characterized in that according to the nerve net
Network host parameter model and the host constraint condition obtain host energy consumption range and specifically include:
Preliminary host energy consumption range is obtained according to the neural network host parameter model and the host constraint condition；
Obtain the host output parameter and reality in the prediction output parameter of preset time before prediction time in the database
Host reality output parameter in output parameter；
According to the error of the host output parameter of the preset time and host reality output parameter, to the preliminary host energy consumption
Range is modified, and obtains the host energy consumption range of prediction time.
5. Cooling and Heat Source machine room energy-saving optimal control method according to claim 2, which is characterized in that according to the nerve net
Network parameters of pump model and the water pump constraint condition and host constraint condition obtain pump energy consumption range and specifically include:
Preliminary water pump is obtained according to the neural network parameters of pump model and the water pump constraint condition and host constraint condition
Energy consumption range；
Obtain the water pump output parameter and reality in the prediction output parameter of preset time before prediction time in the database
Water pump reality output parameter in output parameter；
According to the error of the water pump output parameter of the preset time and water pump reality output parameter, to the preliminary pump energy consumption
Range is modified, and obtains the pump energy consumption range of prediction time.
6. a kind of Cooling and Heat Source machine room energy-saving Optimal Control System characterized by comprising
Database module establishes the historical data of database purchase Cooling and Heat Source computer room each system and equipment operating parameter；
Model module carries out offline using the load parameter in the database that the database module is established as training data
Training, establishes neural network load forecasting model；
The model module is carried out the host parameter in the database that the database module is established as training data
Off-line training establishes neural network host parameter model；
The model module is carried out the parameters of pump in the database that the database module is established as training data
Off-line training establishes neural network parameters of pump model；
Load prediction module obtains the outdoor weather Prediction Parameters of prediction time, the mind established according to the model module
Prediction air conditioner load is obtained through network load prediction model and the outdoor weather Prediction Parameters；
The prediction air conditioner load that the load prediction module obtains is transferred to host and water pump by load transfer module, point
Corresponding host constraint condition and water pump constraint condition are not obtained, and the water pump includes freezing side and cold side water pump；
Host parameter analysis module, the neural network host parameter model and the load established according to the model module
The host constraint condition that transfer module determines obtains host energy consumption range；
Parameters of pump analysis module, the neural network parameters of pump model and the load established according to the model module
The water pump constraint condition and host constrained parameters that transfer module determines obtain pump energy consumption range；
Output parameter analysis module, the host energy consumption range determined according to the host parameter analysis module and the water pump
The pump energy consumption range that Parameter analysis module determines calculates the master determined under energy saving of system automation strategy by successive ignition
The prediction output parameter of machine and water pump.
7. Cooling and Heat Source machine room energy-saving Optimal Control System according to claim 6, which is characterized in that further include:
Parameter information obtains module, and the parameter information of prediction time is obtained by sensor；
Actual parameter analysis module obtains the parameter information that module obtains according to the parameter information and practical sky is calculated
Adjust the reality output parameter of load and host and water pump；
Processing module obtains prediction air conditioner load that the load prediction module obtains, the output parameter analysis module
The practical air conditioner load and reality output parameter that prediction output parameter, the actual parameter analysis module obtain are uploaded to described
The database that database module is established.
8. Cooling and Heat Source machine room energy-saving Optimal Control System according to claim 7, which is characterized in that the load prediction mould
Block specifically includes:
Meteorologic parameter acquiring unit obtains the outdoor weather Prediction Parameters of prediction time；
Load estimation unit, according to the neural network load forecasting model and meteorologic parameter acquiring unit acquisition
Outdoor weather Prediction Parameters obtain tentative prediction air conditioner load；
Load parameter acquiring unit obtains the prediction air conditioner load and reality of preset time before prediction time in the database
Load parameter；
Load amending unit, according to the prediction air conditioner load and reality of the preset time that the load parameter acquiring unit obtains
The error of border load parameter is modified the tentative prediction air conditioner load that the load estimation unit obtains, obtains pre-
Survey the prediction air conditioner load at moment.
9. Cooling and Heat Source machine room energy-saving Optimal Control System according to claim 7, which is characterized in that the host parameter point
Analysis module specifically includes:
Host energy consumption calculation unit obtains preliminary main according to the neural network host parameter model and the host constraint condition
Function consumes range；
Host parameter acquiring unit obtains the master in the prediction output parameter of preset time before prediction time in the database
Host reality output parameter in machine output parameter and reality output parameter；
Host energy consumption amending unit, according to the host output parameter for the preset time that the host parameter acquiring unit obtains
With host reality output parameter error, the preliminary host energy consumption range that the host energy consumption calculation unit obtains is repaired
Just, the host energy consumption range of prediction time is obtained.
10. Cooling and Heat Source machine room energy-saving Optimal Control System according to claim 7, which is characterized in that the parameters of pump
Analysis module specifically includes:
Pump energy consumption computing unit is constrained according to the neural network parameters of pump model and the water pump constraint condition and host
Condition obtains preliminary pump energy consumption range；
Parameters of pump acquiring unit obtains the water in the prediction output parameter of preset time before prediction time in the database
Pump the water pump reality output parameter in output parameter and reality output parameter；
Pump energy consumption amending unit, according to the water pump output parameter for the preset time that the parameters of pump acquiring unit obtains
With the error of water pump reality output parameter, the preliminary pump energy consumption range that the pump energy consumption computing unit obtains is carried out
Amendment, obtains the pump energy consumption range of prediction time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910691078.5A CN110410942B (en) | 2019-07-30 | 2019-07-30 | Energy-saving optimization control method and system for cold and heat source machine room |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910691078.5A CN110410942B (en) | 2019-07-30 | 2019-07-30 | Energy-saving optimization control method and system for cold and heat source machine room |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110410942A true CN110410942A (en) | 2019-11-05 |
| CN110410942B CN110410942B (en) | 2020-12-29 |
Family
ID=68363942
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910691078.5A Active CN110410942B (en) | 2019-07-30 | 2019-07-30 | Energy-saving optimization control method and system for cold and heat source machine room |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110410942B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110779132A (en) * | 2019-11-13 | 2020-02-11 | 垚控科技(上海)有限公司 | Water pump equipment operation control system of air conditioning system based on reinforcement learning |
| CN110878959A (en) * | 2019-11-28 | 2020-03-13 | 济南大学 | Building temperature control method and system based on model predictive control |
| CN111047117A (en) * | 2019-12-31 | 2020-04-21 | 中维通(北京)科技有限公司 | Differential pressure bypass valve energy-saving optimization method based on terminal load prediction |
| CN111043731A (en) * | 2019-12-31 | 2020-04-21 | 中维通(北京)科技有限公司 | Air conditioning system adjusting method based on weather forecast |
| CN111474858A (en) * | 2020-03-31 | 2020-07-31 | 北京天成冠通能源科技有限公司 | Building energy management control system and method |
| CN111735178A (en) * | 2020-07-15 | 2020-10-02 | 西安木牛能源技术服务有限公司 | Air conditioner energy-saving system based on elite meaning and SVR regression algorithm and optimization method |
| CN112283890A (en) * | 2020-10-26 | 2021-01-29 | 济中节能技术（苏州）有限公司 | Cold and heat quantity control method and device suitable for building heating and ventilation equipment monitoring system |
| CN112628956A (en) * | 2020-12-24 | 2021-04-09 | 华中科技大学 | Water chilling unit load prediction control method and system based on edge cloud cooperative framework |
| CN112665123A (en) * | 2020-12-10 | 2021-04-16 | 珠海格力电器股份有限公司 | Building load prediction method and device and central air conditioner |
| CN113739365A (en) * | 2021-08-31 | 2021-12-03 | 广州汇电云联互联网科技有限公司 | Central air-conditioning cold station group control energy-saving control method, device, equipment and storage medium |
| CN113757922A (en) * | 2020-06-03 | 2021-12-07 | 中国移动通信集团浙江有限公司 | Deep learning-based air conditioning system energy-saving control method, device and equipment and computer medium |
| CN113776171A (en) * | 2020-06-10 | 2021-12-10 | 中兴通讯股份有限公司 | Refrigeration equipment control method and device, computer equipment and computer readable medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251291A (en) * | 2008-04-03 | 2008-08-27 | 上海交通大学 | Central air conditioning system global optimization energy-saving control method and device based on model |
| US20160146493A1 (en) * | 2014-11-26 | 2016-05-26 | International Business Machines Corporation | Building thermal control techniques |
| US20170292513A1 (en) * | 2016-04-07 | 2017-10-12 | Schlumberger Technology Corporation | Pump Assembly Health Assessment |
| CN108489012A (en) * | 2018-01-30 | 2018-09-04 | 深圳市新环能科技有限公司 | Cold source of air conditioning energy efficiency model control method based on load prediction and constraint |
| CN109253494A (en) * | 2018-09-05 | 2019-01-22 | 东北大学 | A kind of electric heat-storage device control system and method based on heat load prediction |
| CN109595747A (en) * | 2018-12-24 | 2019-04-09 | 珠海格力电器股份有限公司 | The energy simulation method, apparatus of air-conditioning system |
-
2019
- 2019-07-30 CN CN201910691078.5A patent/CN110410942B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251291A (en) * | 2008-04-03 | 2008-08-27 | 上海交通大学 | Central air conditioning system global optimization energy-saving control method and device based on model |
| US20160146493A1 (en) * | 2014-11-26 | 2016-05-26 | International Business Machines Corporation | Building thermal control techniques |
| US20170292513A1 (en) * | 2016-04-07 | 2017-10-12 | Schlumberger Technology Corporation | Pump Assembly Health Assessment |
| CN108489012A (en) * | 2018-01-30 | 2018-09-04 | 深圳市新环能科技有限公司 | Cold source of air conditioning energy efficiency model control method based on load prediction and constraint |
| CN109253494A (en) * | 2018-09-05 | 2019-01-22 | 东北大学 | A kind of electric heat-storage device control system and method based on heat load prediction |
| CN109595747A (en) * | 2018-12-24 | 2019-04-09 | 珠海格力电器股份有限公司 | The energy simulation method, apparatus of air-conditioning system |
Non-Patent Citations (2)
| Title |
|---|
| 张国华等: "基于动态反馈的多元参数回归空调负荷预测控制方法", 《机电工程技术》 * |
| 蔡盼盼: "基于负荷预测的商场空调冷冻水系统优化运行研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110779132A (en) * | 2019-11-13 | 2020-02-11 | 垚控科技(上海)有限公司 | Water pump equipment operation control system of air conditioning system based on reinforcement learning |
| CN110878959A (en) * | 2019-11-28 | 2020-03-13 | 济南大学 | Building temperature control method and system based on model predictive control |
| CN111047117A (en) * | 2019-12-31 | 2020-04-21 | 中维通(北京)科技有限公司 | Differential pressure bypass valve energy-saving optimization method based on terminal load prediction |
| CN111043731A (en) * | 2019-12-31 | 2020-04-21 | 中维通(北京)科技有限公司 | Air conditioning system adjusting method based on weather forecast |
| CN111474858A (en) * | 2020-03-31 | 2020-07-31 | 北京天成冠通能源科技有限公司 | Building energy management control system and method |
| CN111474858B (en) * | 2020-03-31 | 2024-04-19 | 北京天成冠通能源科技有限公司 | Building energy management control system and method |
| CN113757922A (en) * | 2020-06-03 | 2021-12-07 | 中国移动通信集团浙江有限公司 | Deep learning-based air conditioning system energy-saving control method, device and equipment and computer medium |
| CN113776171B (en) * | 2020-06-10 | 2024-02-13 | 中兴通讯股份有限公司 | Refrigeration equipment control method, refrigeration equipment control device, computer equipment and computer readable medium |
| EP4166862A4 (en) * | 2020-06-10 | 2024-06-26 | ZTE Corporation | Method and apparatus for controlling refrigeration device, computer device, and computer readable medium |
| CN113776171A (en) * | 2020-06-10 | 2021-12-10 | 中兴通讯股份有限公司 | Refrigeration equipment control method and device, computer equipment and computer readable medium |
| CN111735178A (en) * | 2020-07-15 | 2020-10-02 | 西安木牛能源技术服务有限公司 | Air conditioner energy-saving system based on elite meaning and SVR regression algorithm and optimization method |
| CN112283890A (en) * | 2020-10-26 | 2021-01-29 | 济中节能技术（苏州）有限公司 | Cold and heat quantity control method and device suitable for building heating and ventilation equipment monitoring system |
| CN112665123A (en) * | 2020-12-10 | 2021-04-16 | 珠海格力电器股份有限公司 | Building load prediction method and device and central air conditioner |
| CN112665123B (en) * | 2020-12-10 | 2022-04-29 | 珠海格力电器股份有限公司 | Building load prediction method and device and central air conditioner |
| CN112628956B (en) * | 2020-12-24 | 2022-02-15 | 华中科技大学 | Water chilling unit load prediction control method and system based on edge cloud cooperative framework |
| CN112628956A (en) * | 2020-12-24 | 2021-04-09 | 华中科技大学 | Water chilling unit load prediction control method and system based on edge cloud cooperative framework |
| CN113739365A (en) * | 2021-08-31 | 2021-12-03 | 广州汇电云联互联网科技有限公司 | Central air-conditioning cold station group control energy-saving control method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110410942B (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110410942A (en) | A kind of Cooling and Heat Source machine room energy-saving optimal control method and system | |
| CN110288164B (en) | Predictive control method for building air-conditioning refrigeration station system | |
| CN110392515A (en) | A kind of Cooling and Heat Source equipment room energy-conserving control method and system based on historical data | |
| Ma et al. | Predictive control for energy efficient buildings with thermal storage: Modeling, stimulation, and experiments | |
| CN102003772B (en) | Energy-saving optimized control method of water source heat pump | |
| CN111256294A (en) | Model prediction-based optimization control method for combined operation of water chilling unit | |
| Yabanova et al. | Development of ANN model for geothermal district heating system and a novel PID-based control strategy | |
| CN101021914A (en) | Heating ventilating and air conditioner load predicting method and system | |
| CN113091123A (en) | Building unit heat supply system regulation and control method based on digital twin model | |
| CN110458340B (en) | Building air conditioner cold load autoregressive prediction method based on mode classification | |
| CN104633829A (en) | Building cooling station energy-saving control device and method thereof | |
| CN103941591A (en) | System and method to control energy consumption efficiency | |
| CN104898422A (en) | Hierarchical optimization method for united cold supply system | |
| CN109711614A (en) | A kind of the dynamic optimization progress control method and system of distributed busbar protection | |
| Cole et al. | Use of model predictive control to enhance the flexibility of thermal energy storage cooling systems | |
| CN115220351B (en) | Intelligent energy-saving optimization control method for building air conditioning system based on cloud side end | |
| CN114383299B (en) | Central air-conditioning system operation strategy optimization method based on big data and dynamic simulation | |
| CN113739365A (en) | Central air-conditioning cold station group control energy-saving control method, device, equipment and storage medium | |
| US11392095B2 (en) | Building control system with central plant model generation | |
| CN112556103A (en) | Large system energy-saving control mode and system based on load prediction | |
| CN104636800A (en) | Freezing station system neural network optimization unit based on least square weighted and method thereof | |
| CN114154677A (en) | Air conditioner operation load model construction and prediction method, device, equipment and medium | |
| CN115789957A (en) | Energy supply regulation and control method, device, equipment and storage medium | |
| Wei et al. | Data-driven application on the optimization of a heat pump system for district heating load supply: A validation based on onsite test | |
| Zhao et al. | Optimal control for hydraulic balance of secondary network in district heating system under distributed architecture |
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 |