CN116558038A - Air conditioning system carbon efficiency/energy efficiency management method and system and storage medium - Google Patents

Air conditioning system carbon efficiency/energy efficiency management method and system and storage medium Download PDF

Info

Publication number
CN116558038A
CN116558038A CN202310501076.1A CN202310501076A CN116558038A CN 116558038 A CN116558038 A CN 116558038A CN 202310501076 A CN202310501076 A CN 202310501076A CN 116558038 A CN116558038 A CN 116558038A
Authority
CN
China
Prior art keywords
chiller
operation mode
nth
carbon emission
mode
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310501076.1A
Other languages
Chinese (zh)
Inventor
许朝阳
李明
王振宇
李妍
庄重
肖楚鹏
许静
阮文骏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Jiangsu Electric Power Co ltd Marketing Service Center
Wuhan Energy Efficiency Evaluation Co Ltd Of State Grid Electric Power Research Institute
State Grid Corp of China SGCC
State Grid Jiangsu Electric Power Co Ltd
State Grid Electric Power Research Institute
Original Assignee
State Grid Jiangsu Electric Power Co ltd Marketing Service Center
Wuhan Energy Efficiency Evaluation Co Ltd Of State Grid Electric Power Research Institute
State Grid Corp of China SGCC
State Grid Jiangsu Electric Power Co Ltd
State Grid Electric Power Research Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Jiangsu Electric Power Co ltd Marketing Service Center, Wuhan Energy Efficiency Evaluation Co Ltd Of State Grid Electric Power Research Institute, State Grid Corp of China SGCC, State Grid Jiangsu Electric Power Co Ltd, State Grid Electric Power Research Institute filed Critical State Grid Jiangsu Electric Power Co ltd Marketing Service Center
Priority to CN202310501076.1A priority Critical patent/CN116558038A/en
Publication of CN116558038A publication Critical patent/CN116558038A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • 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
    • 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
    • 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
    • F24F11/65—Electronic processing for selecting an operating mode
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
    • G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/32—Operator till task planning
    • G05B2219/32252—Scheduling production, machining, job shop

Abstract

The invention relates to a method, a system and a storage medium for managing the carbon efficiency/energy efficiency of an air conditioning system, wherein the method adopts a mode operation analysis algorithm, a carbon emission coefficient learning algorithm, a mode identification algorithm and an operation optimization algorithm to be combined, and the algorithm is trained based on system history operation data, so that the algorithm accuracy is improved; the system operation mode is determined based on the system real-time operation data, the dynamic evaluation parameters of the system carbon emission are calculated, the intuitiveness of the system carbon emission efficiency evaluation is improved, and the algorithm has the capability of continuous optimization of operation accumulation through data driving.

Description

Air conditioning system carbon efficiency/energy efficiency management method and system and storage medium
Technical Field
The invention relates to the technical field of power systems, in particular to a method and a system for managing carbon efficiency/energy efficiency of an air conditioning system and a storage medium.
Background
With the development of society, the energy consumption of an air conditioning system is half of that of a building. The central air conditioner has wide application, and the energy saving of the air conditioner operation is more and more important for reducing the energy consumption of an air conditioner system and improving the carbon efficiency of the system. The automatic control strategy adopted in the current mainstream air conditioning system is still simpler, the control scheme is mostly based on the energy consumption of the system, the calculation and evaluation of the carbon efficiency are not embodied, the modeling technology and the adjustment scheme are not fully applied to the data driving method, and the model precision is not sufficient.
Disclosure of Invention
Aiming at the problem of optimizing the carbon emission efficiency under the complex operation working condition of the cold machine at present, the invention provides a carbon efficiency/energy efficiency management method of an air conditioning system. The method is characterized in that driving learning is performed based on historical operation data of the air conditioning system, the division of the operation modes of the chiller is realized, equivalent carbon emission generated by converting operation energy consumption in different modes is realized, an algorithm model can cope with common operation scenes of the central air conditioning system, after the operation data are collected, the operation of optimizing the chiller aiming at reducing the carbon emission is achieved, and the accuracy of the algorithm model is improved along with the accumulation of the historical data in the system.
The scheme for solving the technical problems is as follows: a carbon efficiency/energy efficiency management method of an air conditioning system comprises the following steps:
performing mode operation classification based on historical operation data of each chiller in the air conditioning system to obtain an operation mode label of the chiller; the operational data includes a plurality of operational parameters;
the operation parameters mainly comprise the actual power consumption of the chiller, the actual refrigerating capacity of the unit, the unit load rate, the operation frequency of the compressor, the indoor temperature and the like; and weather information of the system, including outdoor dry bulb temperature, wet bulb temperature. The data should be a time-by-time data record of the isochronous acquisition interval and the recording interval is within 30 minutes.
Based on relevant parameters of the cold machine and the operation mode labels, carbon emission coefficient learning is carried out, and carbon emission coefficients corresponding to the operation mode labels are determined;
based on the operation mode label and the historical operation data, performing mode recognition learning to obtain a trained mode recognition algorithm;
based on the real-time operation data of each cold machine, randomly generating new designated parameters, and inputting other parameters in the real-time operation data and the new designated parameters into a mode identification algorithm to obtain real-time operation mode labels of each cold machine; acquiring corresponding carbon emission coefficients based on the labels of the real-time running modes of the cold machines; optimizing running parameters through a pre-constructed optimization model based on carbon emission coefficients corresponding to the real-time running mode labels of the cold machines;
and feeding back the optimized running parameters of each cooling machine to the air conditioning system and regulating and controlling the real-time running state of each cooling machine.
Preferably, the method for classifying the mode operation based on the historical operation data of each chiller in the air conditioning system to obtain an operation mode tag of the chiller specifically includes:
and carrying out mode operation classification through a K-means model based on historical operation data of each cold machine in the air conditioning system to obtain an operation mode label of the cold machine.
Preferably, based on historical operation data of each chiller in the air conditioning system, mode operation analysis learning is performed through a K-means model to obtain an operation mode tag of the chiller, which specifically comprises:
historical operation data of each chiller in the air conditioning system is input into a K-means model to generate a sample set T= { x u } 1≤u≤N ，x u ∈R n Feature vectors for the u-th sample in the sample set; k samples are randomly selected from a sample set T to serve as initial clustering centers, then the distance between each sample and each clustering center is calculated, each sample is distributed to the clustering center closest to the sample set T, each clustering center represents a category, and the initial operation mode label of the sample set u is distributed as y '' u ∈{c 1 ，c 2 ，...c K }；
The sum D of the distances from all samples to the center point of the cluster to which the samples belong is calculated, and the calculation formula is as follows:
wherein C is i Centroid for the ith cluster; dist function is a set distance measurement method; when all samples are assigned an initial run mode label, each clusterThe cluster center is recalculated according to the existing objects in the clusters;
returning to the step of calculating the distance between each sample and the respective cluster center until no more change occurs in the cluster center of each cluster, each sample being assigned to the final run mode label y u ∈{c 1 ，c 2 ，...c K }。
Preferably, the learning of the carbon emission coefficient is performed based on the relevant parameters and the operation mode labels of the chiller, and the carbon emission coefficient corresponding to each operation mode label is determined, and a specific calculation formula is as follows:
wherein, beta i is the carbon emission coefficient corresponding to the ith operation mode label; i is an operation mode label, βr is a reference operation mode carbon emission coefficient, COP r Referencing energy efficiency for baseline mode of operation, COP i Is the reference energy efficiency of the ith operating mode label.
Wherein, COP i The calculation formula of (2) is as follows:
wherein u is the serial number of the running data record of the sample system of the ith, Q j And (3) for the actual cooling capacity of the system recorded in the j th item, the actual power of the system recorded in the P th item, and h being the total number of records divided into the ith operation mode labels.
Wherein, COP r The setting method of (1) is as follows: according to nominal refrigerating capacity and energy efficiency grade calibrated by a cold machine nameplate, reading the energy efficiency grade COP of each cold machine according to the national standard (GB 19577-2004) of unit refrigerating capacity and energy efficiency, and taking the minimum value obtained by reading the table of each cold machine as the reference energy efficiency COP r 。
Wherein beta is r The setting method of (1) is as follows: referring to the equivalent carbon emissions per degree of electricity provided by the local power sector, or referring to the provincial greenhouse gas inventory The index proposed in south is calculated in Kg/(kW.h).
Preferably, the mode recognition learning is performed based on the operation mode tag and the historical operation data to obtain a trained mode recognition algorithm, which specifically includes:
construction of a set training sample set t= { (x) based on operation mode tags and historical operation data u ，y u )} 1≤u≤N ，y u ∈{+1，-1}，x u ∈R n ，R n Refers to real number vector space;
the SVM model adopts a radial basis function, a training sample set is input to optimize and train the SVM model with maximized soft interval and core skills, and the following parameter ranges are used as constraint conditions:
s.t.y u (<w，φ(x u )>+b)-1≥0，u＝1，2，...，N
ξ u ≥0，u＝1，2，...，N
wherein x is u Feature vectors of a u-th sample in the training set; y is u The operation mode label of the ith sample in the training set is used, and N is the total number of categories of the samples; phi () is the nonlinear mapping of the original input space to the high-dimensional feature space, through which the nonlinear support vector machine maps the input to a feature vector, w is the normal vector of the hyperplane of the feature space, b is the bias of the hyperplane,<，>representing the inner product, ζ, of the two vectors u C is a penalty parameter for relaxation variables;
the trained pattern recognition algorithm SVM model is as follows:
i＝SVM(x,θ)
wherein i is an operation mode label, x is a load factor parameter in the cold machine operation data, and θ is a weather parameter and other operation parameters in the cold machine operation data.
Preferably, the method randomly generates new designated parameters based on the real-time operation data of each cold machine, and inputs other parameters in the real-time operation data and the new designated parameters into a mode identification algorithm to obtain the real-time operation mode labels of each cold machine; acquiring carbon emission coefficients corresponding to the real-time operation mode labels according to the real-time operation mode labels of the cold machines; optimizing running parameters through a pre-constructed optimization model based on carbon emission coefficients corresponding to real-time running mode labels of all the cold machines; the method specifically comprises the following steps of;
an optimization model aiming at minimizing carbon emission is constructed, and a Loss function Loss expression in the optimization model is as follows:
wherein n is the serial number of the cold machine, m is the total number of the cold machines, i is an output result operation mode label based on SVM (x', theta), and k is the label i,n Corresponding to the carbon emission coefficient, P, of the nth chiller device under the ith operating mode label n Rated power of the cold machine for the nth cold machine equipment, x' n Randomly generating a load factor for the n-th chiller selected by brushing;
randomly generating w new cold machine load rates x' near the real-time load rate x parameter of the nth cold machine equipment; other parameters in real-time operation data of the nth cold machine equipment and w new load factors x 'are input into a mode identification algorithm SVM (x', theta) in a grouping mode to obtain an operation mode label i of the nth cold machine equipment in w groups, and a corresponding carbon emission coefficient k is obtained according to the operation mode label i i,n ；
Inputting carbon emission coefficients corresponding to the running mode labels i of the nth cooling machine equipment in w groups to an optimization model, and brushing and selecting a load rate x 'meeting the minimum of the Loss function Loss of the nth cooling machine equipment from w load rates x'; n and outputs x' n As an optimized and adjusted operating parameter of the nth chiller plant.
Preferably, the carbon emission coefficient corresponding to the operation mode label i of the nth chiller device in the w groups is input to an optimization model, and the load factor x 'meeting the minimum of the Loss function Loss of the nth chiller device is brushed from the w load factors x': n and outputs x' n As the nthOperating parameters of the chiller after optimization and adjustment; the method specifically comprises the following steps:
inputting carbon emission coefficients corresponding to the running mode labels i of the w groups of nth chiller equipment to an optimization model;
selecting a load factor x 'meeting the minimum of the Loss function Loss of the nth chiller plant from the w load factor x' brushes " n And x' n Finishing output adjustment load factor x' n The limiting condition that the total cooling capacity of all cooling machines output is unchanged in the front and back air conditioning systems is output " n As the optimized and adjusted operation parameters of the nth chiller equipment; wherein, the constraint expression is as follows:
wherein Q is n Is the rated cooling capacity of the nth cooler, x n The preload factor, x' is adjusted for the nth chiller " n The nth chiller is the adjusted post load rate.
By setting the limiting condition, the overall cooling capacity of the system is not changed before and after the load rate is adjusted, so that the environment comfort level of the tail end of the system is basically ensured to be in a proper range.
The invention also provides a carbon efficiency/energy efficiency management system of the air conditioning system, comprising:
the mode operation analysis learning module is used for classifying the operation modes based on the historical operation data of each chiller in the air conditioning system to obtain an operation mode label of the chiller; the operational data includes a plurality of operational parameters;
the carbon emission coefficient learning module is used for learning the carbon emission coefficient based on the relevant parameters of the refrigerator and the operation mode labels and determining the carbon emission coefficient corresponding to each operation mode label;
the mode recognition algorithm training module is used for carrying out mode recognition learning based on the operation mode label and the historical operation data to obtain a trained mode recognition algorithm;
the optimization algorithm operation module is used for randomly generating new designated parameters based on the real-time operation data of each cold machine, and inputting other parameters in the real-time operation data and the new designated parameters into the mode identification algorithm to obtain the real-time operation mode labels of each cold machine; acquiring corresponding carbon emission coefficients based on the labels of the real-time running modes of the cold machines; optimizing running parameters through a pre-constructed optimization model based on carbon emission coefficients corresponding to the real-time running mode labels of the cold machines;
And the system regulation and control module is used for feeding back the optimized running parameters of each cold machine to the air conditioning system and regulating and controlling the real-time running state of each cold machine.
Preferably, the method for classifying the mode operation based on the historical operation data of each chiller in the air conditioning system to obtain an operation mode tag of the chiller specifically includes:
and carrying out mode operation classification through a K-means model based on historical operation data of each cold machine in the air conditioning system to obtain an operation mode label of the cold machine.
Preferably, based on historical operation data of each chiller in the air conditioning system, mode operation analysis learning is performed through a K-means model to obtain an operation mode tag of the chiller, which specifically comprises:
historical operation data of each chiller in the air conditioning system is input into a K-means model to generate a sample set T= { x u } 1≤u≤N ，x u ∈R n Feature vectors for the u-th sample in the sample set; k samples are randomly selected from a sample set T to serve as initial clustering centers, then the distance between each sample and each clustering center is calculated, each sample is distributed to the clustering center closest to the sample set T, each clustering center represents a category, and the initial operation mode label of the sample set u is distributed as y '' u ∈{c 1 ，c 2 ，...c K }；
The sum D of the distances from all samples to the center point of the cluster to which the samples belong is calculated, and the calculation formula is as follows:
Wherein C is i Centroid for the ith cluster; dist function is a set distance measurement method; when all samples are assigned an initial operation mode label, the cluster center of each cluster is recalculated according to the existing objects in the clusters;
returning to the step of calculating the distance between each sample and the respective cluster center until no more change occurs in the cluster center of each cluster, each sample being assigned to the final run mode label y u ∈{c 1 ，c 2 ，...c K }。
Preferably, the learning of the carbon emission coefficient is performed based on the relevant parameters and the operation mode labels of the chiller, and the carbon emission coefficient corresponding to each operation mode label is determined, and a specific calculation formula is as follows:
wherein, beta i is the carbon emission coefficient corresponding to the ith operation mode label; i is an operation mode label, βr is a reference operation mode carbon emission coefficient, COP r Referencing energy efficiency for baseline mode of operation, COP i Is the reference energy efficiency of the ith operating mode label.
Wherein, COP i The calculation formula of (2) is as follows:
wherein u is the serial number of the running data record of the sample system of the ith, Q j And (3) for the actual cooling capacity of the system recorded in the j th item, the actual power of the system recorded in the P th item, and h being the total number of records divided into the ith operation mode labels.
Preferably, the mode recognition learning is performed based on the operation mode tag and the historical operation data to obtain a trained mode recognition algorithm, which specifically includes:
construction of a set training sample set t= { (x) based on operation mode tags and historical operation data u ，y u )} 1≤u≤N ，y u ∈{+1，-1}，x u ∈R n ，R n Refers to real number vector space;
the SVM model adopts a radial basis function, a training sample set is input to optimize and train the SVM model with maximized soft interval and core skills, and the following parameter ranges are used as constraint conditions:
s.t.y u (<w，φ(x u )>+b)-1≥0，u＝1，2，...，N
ξ u ≥0，u＝1，2，...，N
wherein x is u Feature vectors of a u-th sample in the training set; y is u The operation mode label of the ith sample in the training set is used, and N is the total number of categories of the samples; phi () is the nonlinear mapping of the original input space to the high-dimensional feature space, through which the nonlinear support vector machine maps the input to a feature vector, w is the normal vector of the hyperplane of the feature space, b is the bias of the hyperplane,<，>representing the inner product, ζ, of the two vectors u C is a penalty parameter for relaxation variables;
the trained pattern recognition algorithm SVM model is as follows:
i＝SVM(x,θ)
wherein i is an operation mode label, x is a load factor parameter in the cold machine operation data, and θ is a weather parameter and other operation parameters in the cold machine operation data.
Preferably, the method randomly generates new designated parameters based on the real-time operation data of each cold machine, and inputs other parameters in the real-time operation data and the new designated parameters into a mode identification algorithm to obtain the real-time operation mode labels of each cold machine; acquiring carbon emission coefficients corresponding to the real-time operation mode labels according to the real-time operation mode labels of the cold machines; optimizing running parameters through a pre-constructed optimization model based on carbon emission coefficients corresponding to real-time running mode labels of all the cold machines; the method specifically comprises the following steps of;
an optimization model aiming at minimizing carbon emission is constructed, and a Loss function Loss expression in the optimization model is as follows:
wherein n is the serial number of the cold machine, m is the total number of the cold machines, i is an output result operation mode label based on SVM (x', theta), and k is the label i,n Corresponding to the carbon emission coefficient, P, of the nth chiller device under the ith operating mode label n Rated power of the cold machine for the nth cold machine equipment, x' n Randomly generating a load factor for the n-th chiller selected by brushing;
randomly generating w new cold machine load rates x' near the real-time load rate x parameter of the nth cold machine equipment; other parameters in real-time operation data of the nth cold machine equipment and w new load factors x 'are input into a mode identification algorithm SVM (x', theta) in a grouping mode to obtain an operation mode label i of the nth cold machine equipment in w groups, and a corresponding carbon emission coefficient k is obtained according to the operation mode label i i,n ；
Inputting carbon emission coefficients corresponding to the running mode labels i of the nth cooling machine equipment in w groups to an optimization model, and brushing and selecting a load rate x 'meeting the minimum of the Loss function Loss of the nth cooling machine equipment from w load rates x'; n and outputs x' n As an optimized and adjusted operating parameter of the nth chiller plant.
Preferably, the carbon emission coefficient corresponding to the operation mode label i of the nth chiller device in the w groups is input to an optimization model, and the load factor x 'meeting the minimum of the Loss function Loss of the nth chiller device is brushed from the w load factors x': n and outputs x' n As the optimized and adjusted operation parameters of the nth chiller equipment; the method specifically comprises the following steps:
inputting carbon emission coefficients corresponding to the running mode labels i of the w groups of nth chiller equipment to an optimization model;
selecting a load factor x 'meeting the minimum of the Loss function Loss of the nth chiller plant from the w load factor x' brushes " n And x' n Finishing output adjustment load factor x' n The limiting condition that the total cooling capacity of all cooling machines output is unchanged in the front and back air conditioning systems is output " n As the optimized and adjusted operation parameters of the nth chiller equipment; wherein, the constraint expression is as follows:
wherein Q is n Is the rated cooling capacity of the nth cooler, x n The preload factor, x' is adjusted for the nth chiller " n The nth chiller is the adjusted post load rate.
The present invention also provides a computer storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the air conditioning system carbon/energy efficiency management method as described above
The invention also provides an electronic device comprising a memory and a processor: the memory is configured to store computer-executable instructions that, when executed by the processor, implement the steps of the air conditioning system carbon/energy efficiency management method described above.
The beneficial effects of the invention are as follows: the method provided by the invention determines the system operation mode based on the system operation data, calculates the dynamic evaluation parameters of the system carbon emission, and increases the intuitiveness of the evaluation of the system carbon emission efficiency. By applying data driving, the operation data in the system is accumulated, so that the algorithm model has the capability of continuously optimizing the operation accumulation, thereby improving the accuracy and the reliability.
The foregoing description is only an overview of the present invention, and is intended to provide a better understanding of the present invention, as it is embodied in the following description, with reference to the preferred embodiments of the present invention and the accompanying drawings. Specific embodiments of the present invention are given in detail by the following examples and the accompanying drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a schematic flow diagram of the method of example 1 of the present invention;
FIG. 2 is a flow chart of the method operation and optimization according to embodiment 1 of the present invention;
FIG. 3 is a schematic flow chart of the operation of the system according to example 2 of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
Example 1
As shown in fig. 1-2, a method for managing carbon efficiency/energy efficiency of an air conditioning system includes the following steps:
based on historical operation data of each chiller in the air conditioning system, performing mode operation classification to obtain an operation mode label of the chiller, wherein the operation mode label comprises the following specific steps:
historical operation data of each chiller in the air conditioning system is input into a K-means model to generate a sample set T= { x u } 1≤u≤N ，x u ∈R n Feature vectors for the u-th sample in the sample set; k samples are randomly selected from a sample set T to serve as initial clustering centers, then the distance between each sample and each clustering center is calculated, each sample is distributed to the clustering center closest to the sample set T, each clustering center represents a category, and the initial operation mode label of the sample set u is distributed as y '' u ∈{c 1 ，c 2 ，...c K }；
The sum D of the distances from all samples to the center point of the cluster to which the samples belong is calculated, and the calculation formula is as follows:
wherein C is i Centroid for the ith cluster; dist function is set toA fixed distance measurement method; when all samples are assigned an initial operation mode label, the cluster center of each cluster is recalculated according to the existing objects in the clusters;
returning to the step of calculating the distance between each sample and the respective cluster center until no more change occurs in the cluster center of each cluster, each sample being assigned to the final run mode label y u ∈{c 1 ，c 2 ，...c K }。
The system operation data comprises a plurality of different cold machine operation key parameters. The method mainly comprises the steps of actual power consumption of a chiller, actual refrigerating capacity of a unit, unit load rate, compressor running frequency, indoor temperature and the like; and weather information of the system, including outdoor dry bulb temperature, wet bulb temperature. The data should be a time-by-time data record of the isochronous acquisition interval and the recording interval is within 30 minutes.
Based on relevant parameters of the chiller and the operation mode labels, carbon emission coefficient learning is carried out, and carbon emission coefficients corresponding to the operation mode labels are determined, wherein a specific calculation formula is as follows:
wherein, beta i is the carbon emission coefficient corresponding to the ith operation mode label; i is an operation mode label, βr is a reference operation mode carbon emission coefficient, COP r Referencing energy efficiency for baseline mode of operation, COP i Is the reference energy efficiency of the ith operating mode label.
Wherein, COP i The calculation formula of (2) is as follows:
wherein u is the serial number of the running data record of the sample system of the ith, Q j And (3) for the actual cooling capacity of the system recorded in the j th item, the actual power of the system recorded in the P th item, and h being the total number of records divided into the ith operation mode labels.
Wherein, COP r The setting method of (1) is as follows: according to nominal refrigerating capacity and energy efficiency grade calibrated by a cold machine nameplate, reading the energy efficiency grade COP of each cold machine according to the national standard (GB 19577-2004) of unit refrigerating capacity and energy efficiency, and taking the minimum value obtained by reading the table of each cold machine as the reference energy efficiency COP r 。
Wherein beta is r The setting method of (1) is as follows: the unit of index calculation is Kg/(kW.h) which is provided by referring to the equivalent carbon emission of electricity per degree provided by the local power generation department or the provincial greenhouse gas list establishment guideline.
Finally, coefficients were calculated for the obtained patterned carbon emission coefficients, recorded as table 1 below:
TABLE 1
Mode of operation Carbon emission coefficient
Mode 1 k 1
Mode 2 k 2
Mode 3 k 3
... ...
Based on the operation mode label and the historical operation data, performing mode recognition learning to obtain a trained mode recognition algorithm, wherein the specific steps are as follows:
Construction of a set training sample set t= { (x) based on operation mode tags and historical operation data u ，y u )} 1≤u≤N ，y u ∈{+1，-1}，x u ∈R n ，R n Refers to real number vector space;
the SVM model adopts a radial basis function, a training sample set is input to optimize and train the SVM model with maximized soft interval and core skills, and the following parameter ranges are used as constraint conditions:
s.t.y u (<w，φ(x u )>+b)-1≥0，u＝1，2，...，N
ξ u ≥0，u＝1，2，...，N
wherein x is u Feature vectors of a u-th sample in the training set; y is u The operation mode label of the ith sample in the training set is used, and N is the total number of categories of the samples; phi () is the nonlinear mapping of the original input space to the high-dimensional feature space, through which the nonlinear support vector machine maps the input to a feature vector, w is the normal vector of the hyperplane of the feature space, b is the bias of the hyperplane,<，>representing the inner product of the two vectors, ζ u C is a penalty parameter for relaxation variables;
the trained pattern recognition algorithm SVM model is as follows:
i＝SVM(x,θ)
wherein i is an operation mode label, x is a load factor parameter in the cold machine operation data, and θ is a weather parameter and other operation parameters in the cold machine operation data.
Based on the real-time operation data of each cold machine, randomly generating new designated parameters, and inputting other parameters in the real-time operation data and the new designated parameters into a mode identification algorithm to obtain real-time operation mode labels of each cold machine; acquiring carbon emission coefficients corresponding to the real-time operation mode labels according to the real-time operation mode labels of the cold machines; running parameters are optimized through a pre-built optimization model based on carbon emission coefficients corresponding to real-time running mode labels of all cold machines
The method comprises the following specific steps of;
an optimization model aiming at minimizing carbon emission is constructed, and a Loss function Loss expression in the optimization model is as follows:
wherein n is the serial number of the cold machine, m is the total number of the cold machines, i is an output result operation mode label based on SVM (x', theta), and k is the label i,n Corresponding to the carbon emission coefficient, P, of the nth chiller device under the ith operating mode label n Rated power of the cold machine for the nth cold machine equipment, x' n Randomly generating a load factor for the n-th chiller selected by brushing;
randomly generating w new cold machine load rates x' near the real-time load rate x parameter of the nth cold machine equipment; other parameters in real-time operation data of the nth cold machine equipment and w new load factors x 'are input into a mode identification algorithm SVM (x', theta) in a grouping mode to obtain an operation mode label i of the nth cold machine equipment in w groups, and a corresponding carbon emission coefficient k is obtained according to the operation mode label i i,n ；
Inputting carbon emission coefficients corresponding to the running mode labels i of the nth cooling machine equipment in w groups to an optimization model, and brushing and selecting a load rate x 'meeting the minimum of the Loss function Loss of the nth cooling machine equipment from w load rates x'; n and x' n Finishing output adjustment load factor x' n Limiting conditions that the total cold output by all coolers in the air conditioning system is unchanged; wherein, the constraint expression is as follows:
Wherein Q is n Is the rated cooling capacity of the nth cooler, x n The preload factor, x' is adjusted for the nth chiller " n The nth chiller is the adjusted post load rate.
Output x' n As an optimized and adjusted operating parameter of the nth chiller plant.
And feeding back the optimized running parameters of each cooling machine to the air conditioning system and regulating and controlling the real-time running state of each cooling machine.
Example 2
An air conditioning system carbon/energy efficiency management system, as shown in fig. 3, comprising:
the mode operation analysis learning module is used for classifying the operation modes based on the historical operation data of each chiller in the air conditioning system to obtain an operation mode label of the chiller; the operational data includes a plurality of operational parameters;
the carbon emission coefficient learning module is used for learning the carbon emission coefficient based on the relevant parameters of the refrigerator and the operation mode labels and determining the carbon emission coefficient corresponding to each operation mode label;
the mode recognition algorithm training module is used for carrying out mode recognition learning based on the operation mode label and the historical operation data to obtain a trained mode recognition algorithm;
the optimization algorithm operation module is used for randomly generating new designated parameters based on the real-time operation data of each cold machine, and inputting other parameters in the real-time operation data and the new designated parameters into the mode identification algorithm to obtain the real-time operation mode labels of each cold machine; acquiring corresponding carbon emission coefficients based on the labels of the real-time running modes of the cold machines; optimizing running parameters through a pre-constructed optimization model based on carbon emission coefficients corresponding to the real-time running mode labels of the cold machines;
And the system regulation and control module is used for feeding back the optimized running parameters of each cold machine to the air conditioning system and regulating and controlling the real-time running state of each cold machine.
Based on historical operation data of each chiller in the air conditioning system, performing mode operation classification to obtain an operation mode label of the chiller, and specifically comprising the following steps:
and carrying out mode operation classification through a K-means model based on historical operation data of each cold machine in the air conditioning system to obtain an operation mode label of the cold machine.
Based on the historical operation data of each chiller in the air conditioning system, performing mode operation analysis and learning through a K-means model to obtain an operation mode label of the chiller, and specifically comprising the following steps:
historical operation data of each chiller in the air conditioning system is input into a K-means model to generate a sample set T= { x u } 1≤u≤N ，x u ∈R n Feature vectors for the u-th sample in the sample set; k samples are randomly selected from a sample set T to serve as initial clustering centers, then the distance between each sample and each clustering center is calculated, each sample is distributed to the clustering center closest to the sample set T, each clustering center represents a category, and the initial operation mode label of the sample set u is distributed as y '' u ∈{c 1 ，c 2 ，...c K }；
The sum D of the distances from all samples to the center point of the cluster to which the samples belong is calculated, and the calculation formula is as follows:
Wherein C is i Centroid for the ith cluster; dist function is a set distance measurement method; when all samples are assigned an initial operation mode label, the cluster center of each cluster is recalculated according to the existing objects in the clusters;
returning to the step of calculating the distance between each sample and the respective cluster center until no more change occurs in the cluster center of each cluster, each sample being assigned to the final run mode label y u ∈{c 1 ，c 2 ，...c K }。
The carbon emission coefficient learning is carried out based on relevant parameters and operation mode labels of the cooling machine, and the carbon emission coefficient corresponding to each operation mode label is determined, wherein the specific calculation formula is as follows:
wherein, beta i is the carbon emission coefficient corresponding to the ith operation mode label; i.eFor the run mode label, βr is the reference run mode carbon emission coefficient, COP r Referencing energy efficiency for baseline mode of operation, COP i Is the reference energy efficiency of the ith operating mode label.
Wherein, COP i The calculation formula of (2) is as follows:
wherein u is the serial number of the running data record of the sample system of the ith, Q j And (3) for the actual cooling capacity of the system recorded in the j th item, the actual power of the system recorded in the P th item, and h being the total number of records divided into the ith operation mode labels.
The method comprises the steps of performing pattern recognition learning based on the operation pattern tag and historical operation data to obtain a trained pattern recognition algorithm, and specifically comprises the following steps:
construction of a set training sample set t= { (x) based on operation mode tags and historical operation data u ，y u )} 1≤u≤N ，y u ∈{+1，-1}，x u ∈R n ，R n Refers to real number vector space;
the SVM model adopts a radial basis function, a training sample set is input to optimize and train the SVM model with maximized soft interval and core skills, and the following parameter ranges are used as constraint conditions:
s.t.y u (<w，φ(x u )>+b)-1≥0，u＝1，2，...，N
ξ u ≥0，u＝1，2，...，N
wherein x is u Feature vectors of a u-th sample in the training set; y is u The operation mode label of the ith sample in the training set is used, and N is the total number of categories of the samples; phi () is the nonlinear mapping of the original input space to the high-dimensional feature space, through which the nonlinear support vector machine maps the input into feature vectorsW is the normal vector of the hyperplane of the feature space, b is the offset of the hyperplane,<，>representing the inner product, ζ, of the two vectors u C is a penalty parameter for relaxation variables;
the trained pattern recognition algorithm SVM model is as follows:
i＝SVM(x,θ)
wherein i is an operation mode label, x is a load factor parameter in the cold machine operation data, and θ is a weather parameter and other operation parameters in the cold machine operation data.
The method comprises the steps that new designated parameters are randomly generated based on real-time operation data of each cold machine, and other parameters in the real-time operation data and the new designated parameters are input into a mode identification algorithm to obtain real-time operation mode labels of each cold machine; acquiring carbon emission coefficients corresponding to the real-time operation mode labels according to the real-time operation mode labels of the cold machines; optimizing running parameters through a pre-constructed optimization model based on carbon emission coefficients corresponding to real-time running mode labels of all the cold machines; the method specifically comprises the following steps of;
An optimization model aiming at minimizing carbon emission is constructed, and a Loss function Loss expression in the optimization model is as follows:
wherein n is the serial number of the cold machine, m is the total number of the cold machines, i is an output result operation mode label based on SVM (x', theta), and k is the label i,n Corresponding to the carbon emission coefficient, P, of the nth chiller device under the ith operating mode label n Rated power of the cold machine for the nth cold machine equipment, x' n Randomly generating a load factor for the n-th chiller selected by brushing;
randomly generating w new cold machine load rates x' near the real-time load rate x parameter of the nth cold machine equipment; other parameters in real-time operation data of the nth cold machine equipment and w new load factors x 'are input into a mode identification algorithm SVM (x', theta) in a grouping mode to obtain an operation mode label i of the nth cold machine equipment in w groups, and a corresponding carbon emission coefficient k is obtained according to the operation mode label i i,n ；
Inputting carbon emission coefficients corresponding to the running mode labels i of the nth cooling machine equipment in w groups to an optimization model, and brushing and selecting a load rate x 'meeting the minimum of the Loss function Loss of the nth cooling machine equipment from w load rates x'; n and outputs x' n As an optimized and adjusted operating parameter of the nth chiller plant.
The carbon emission coefficient corresponding to the operation mode label i of the nth cold machine equipment in the w groups is input to an optimization model, and the load rate x 'meeting the minimum of the Loss function Loss of the nth cold machine equipment is brushed from the w load rates x': n And outputs x' n As the optimized and adjusted operation parameters of the nth chiller equipment; the method specifically comprises the following steps:
inputting carbon emission coefficients corresponding to the running mode labels i of the w groups of nth chiller equipment to an optimization model;
selecting a load factor x 'meeting the minimum of the Loss function Loss of the nth chiller plant from the w load factor x' brushes " n And x' n Finishing output adjustment load factor x' n The limiting condition that the total cooling capacity of all cooling machines output is unchanged in the front and back air conditioning systems is output " n As the optimized and adjusted operation parameters of the nth chiller equipment; wherein, the constraint expression is as follows:
wherein Q is n Is the rated cooling capacity of the nth cooler, x n The preload factor, x' is adjusted for the nth chiller " n The nth chiller is the adjusted post load rate.
Example 3
A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the air conditioning system carbon/energy efficiency management method of embodiment 1.
Example 4
An electronic device comprising a memory and a processor: the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, wherein the computer executable instructions when executed by the processor implement the steps of the air conditioning system carbon/energy efficiency management method as described in embodiment 1.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The solutions in the embodiments of the present application may be implemented in various computer languages, for example, object-oriented programming language Java, and an transliterated scripting language JavaScript, etc. The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.

Claims (16)

1. The carbon efficiency/energy efficiency management method for the air conditioning system is characterized by comprising the following steps of:
classifying operation modes based on historical operation data of each chiller in the air conditioning system to obtain operation mode labels of the chillers; the operational data includes a plurality of operational parameters;
based on relevant parameters of the cold machine and the operation mode labels, carbon emission coefficient learning is carried out, and carbon emission coefficients corresponding to the operation mode labels are determined;
based on the operation mode label and the historical operation data, performing mode recognition learning to obtain a trained mode recognition algorithm;
based on the real-time operation data of each cold machine, randomly generating new designated parameters, and inputting other parameters in the real-time operation data and the new designated parameters into a mode identification algorithm to obtain real-time operation mode labels of each cold machine; acquiring corresponding carbon emission coefficients based on the labels of the real-time running modes of the cold machines; optimizing running parameters through a pre-constructed optimization model based on carbon emission coefficients corresponding to the real-time running mode labels of the cold machines;
and feeding back the optimized running parameters of each cooling machine to the air conditioning system and regulating and controlling the real-time running state of each cooling machine.
2. The method for managing the carbon efficiency/energy efficiency of an air conditioning system according to claim 1, wherein the classifying the operation modes based on the historical operation data of each chiller in the air conditioning system to obtain the operation mode label of the chiller specifically comprises:
And carrying out mode operation classification through a K-means model based on historical operation data of each cold machine in the air conditioning system to obtain an operation mode label of the cold machine.
3. The method for managing the carbon efficiency/energy efficiency of an air conditioning system according to claim 2, wherein the method for managing the carbon efficiency/energy efficiency of the air conditioning system is characterized by performing mode operation analysis learning through a K-means model based on historical operation data of each chiller in the air conditioning system to obtain an operation mode tag of the chiller, and specifically comprises the following steps:
historical operation data of each chiller in the air conditioning system is input into a K-means model to generate a sample set T= { x u } 1≤u≤N ，x u ∈R n Feature vectors for the u-th sample in the sample set;
k samples are randomly selected from a sample set T to serve as initial clustering centers, then the distance between each sample and each clustering center is calculated, each sample is distributed to the clustering center closest to the sample set T, each clustering center represents a category, and the initial operation mode label of the sample set u is distributed as y '' u ∈{c 1 ，c 2 ，...c K }；
The sum D of the distances from all samples to the center point of the cluster to which the samples belong is calculated, and the calculation formula is as follows:
wherein C is i Centroid for the ith cluster; dist function is a set distance measurement method;
when all samples are assigned an initial operation mode label, the cluster center of each cluster is recalculated according to the existing objects in the clusters;
Returning to the step of calculating the distance between each sample and the respective cluster center until no more change occurs in the cluster center of each cluster, each sample being assigned to the final run mode label y u ∈{c 1 ，c 2 ，...c K }。
4. The method for managing the carbon efficiency/energy efficiency of the air conditioning system according to claim 1, wherein the carbon emission coefficient learning is performed based on the relevant parameters and the operation mode labels of the chiller, and the carbon emission coefficient corresponding to each operation mode label is determined according to the specific calculation formula:
wherein, beta i is the carbon emission coefficient corresponding to the ith operation mode label; i is an operation mode label, βr is a reference operation mode carbon emission coefficient, COP r Referencing energy efficiency for baseline mode of operation, COP i The reference energy efficiency of the ith operation mode label;
wherein, COP i The calculation formula of (2) is as follows:
wherein u is the serial number of the running data record of the sample system of the ith, Q j And (3) for the actual cooling capacity of the system recorded in the j th item, the actual power of the system recorded in the P th item, and h being the total number of records divided into the ith operation mode labels.
5. The method for managing the carbon efficiency/energy efficiency of the air conditioning system according to claim 1, wherein the performing pattern recognition learning based on the operation pattern tag and the historical operation data to obtain a trained pattern recognition algorithm specifically comprises:
Construction of a set training sample set t= { (x) based on operation mode tags and historical operation data u ，y u )} 1≤u≤N ，y u ∈{+1，-1}，x u ∈R n ，R n Refers to real number vector space;
the SVM model adopts a radial basis function, a training sample set is input to optimize and train the SVM model with maximized soft interval and core skills, and the following parameter ranges are used as constraint conditions:
s.t.y u (<w，φ(x u )>+b)-1≥0，u＝1，2，...，N
ξ u ≥0，u＝1，2，...，N
wherein x is u Feature vectors of a u-th sample in the training set; y is u The operation mode label of the ith sample in the training set is used, and N is the total number of categories of the samples; phi () is the nonlinear mapping of the original input space to the high-dimensional feature space, through which the nonlinear support vector machine maps the input to a feature vector, w is the normal vector of the hyperplane of the feature space, b is the bias of the hyperplane,<，>representing the inner product, ζ, of the two vectors u C is a penalty parameter for relaxation variables;
the trained pattern recognition algorithm SVM model is as follows:
i＝SVM(x,θ)
wherein i is an operation mode label, x is a load factor parameter in the cold machine operation data, and θ is a weather parameter and other operation parameters in the cold machine operation data.
6. The method for managing the carbon efficiency/energy efficiency of an air conditioning system according to claim 5, wherein the method is characterized in that new specified parameters are randomly generated based on real-time operation data of each chiller, and other parameters in the real-time operation data and the new specified parameters are input into a pattern recognition algorithm to obtain real-time operation pattern labels of each chiller; acquiring carbon emission coefficients corresponding to the real-time operation mode labels according to the real-time operation mode labels of the cold machines; optimizing running parameters through a pre-constructed optimization model based on carbon emission coefficients corresponding to the real-time running mode labels of the cold machines; the method specifically comprises the following steps of;
An optimization model aiming at minimizing carbon emission is constructed, and a Loss function Loss expression in the optimization model is as follows:
wherein n is the serial number of the cold machine, m is the total number of the cold machines, i is an output result operation mode label based on SVM (x', theta), and k is the label i,n Corresponding to the carbon emission coefficient, P, of the nth chiller device under the ith operating mode label n Rated power of the cold machine for the nth cold machine equipment, x' n Randomly generating a load factor for the n-th chiller selected by brushing;
randomly generating w new cold machine load rates x' near the real-time load rate x parameter of the nth cold machine equipment; other parameters in real-time operation data of the nth cold machine equipment and w new load factors x 'are input into a mode identification algorithm SVM (x', theta) in a grouping mode to obtain an operation mode label i of the nth cold machine equipment in w groups, and a corresponding carbon emission coefficient k is obtained according to the operation mode label i i,n ；
Inputting carbon emission coefficients corresponding to the running mode labels i of the nth cooling machine equipment in w groups to an optimization model, and brushing and selecting a load rate x 'meeting the minimum of the Loss function Loss of the nth cooling machine equipment from w load rates x'; n and outputs x' n As an optimized and adjusted operating parameter of the nth chiller plant.
7. The method for managing the carbon/energy efficiency of an air conditioning system according to claim 6, wherein the carbon emission coefficient corresponding to the operation mode label i of the nth chiller device of the w groups is input to the optimization model, and the load factor x "satisfying the minimization of the Loss function Loss of the nth chiller device is brushed from the w load factors x': n And outputs x' n As the optimized and adjusted operation parameters of the nth chiller equipment; the method specifically comprises the following steps:
inputting carbon emission coefficients corresponding to the running mode labels i of the w groups of nth chiller equipment to an optimization model;
selecting a load factor x 'meeting the minimum of the Loss function Loss of the nth chiller plant from the w load factor x' brushes " n And x' n Finishing output adjustment load factor x' n The limiting condition that the total cooling capacity of all cooling machines output is unchanged in the front and back air conditioning systems is output " n As the optimized and adjusted operation parameters of the nth chiller equipment; wherein, the constraint expression is as follows:
wherein Q is n Is the rated cooling capacity of the nth cooler, x n The preload factor, x' is adjusted for the nth chiller " n The nth chiller is the adjusted post load rate.
8. A carbon/energy efficiency management system for an air conditioning system, comprising:
the mode operation analysis learning module is used for classifying the operation modes based on the historical operation data of each chiller in the air conditioning system to obtain an operation mode label of the chiller; the operational data includes a plurality of operational parameters;
the carbon emission coefficient learning module is used for learning the carbon emission coefficient based on the relevant parameters of the refrigerator and the operation mode labels and determining the carbon emission coefficient corresponding to each operation mode label;
The mode recognition algorithm training module is used for carrying out mode recognition learning based on the operation mode label and the historical operation data to obtain a trained mode recognition algorithm;
the optimization algorithm operation module is used for randomly generating new designated parameters based on the real-time operation data of each cold machine, and inputting other parameters in the real-time operation data and the new designated parameters into the mode identification algorithm to obtain the real-time operation mode labels of each cold machine; acquiring corresponding carbon emission coefficients based on the labels of the real-time running modes of the cold machines; optimizing running parameters through a pre-constructed optimization model based on carbon emission coefficients corresponding to the real-time running mode labels of the cold machines;
and the system regulation and control module is used for feeding back the optimized running parameters of each cold machine to the air conditioning system and regulating and controlling the real-time running state of each cold machine.
9. The system according to claim 8, wherein the operation mode classification is performed based on historical operation data of each chiller in the air conditioning system to obtain an operation mode tag of the chiller, and the method specifically comprises:
and carrying out mode operation classification through a K-means model based on historical operation data of each cold machine in the air conditioning system to obtain an operation mode label of the cold machine.
10. The system according to claim 9, wherein the learning of the mode operation analysis is performed by a K-means model based on the historical operation data of each chiller in the air conditioning system to obtain an operation mode tag of the chiller, specifically comprising:
historical operation data of each chiller in the air conditioning system is input into a K-means model to generate a sample set T= { x u } 1≤u≤N ，x u ∈R n Feature vectors for the u-th sample in the sample set;
k samples are randomly selected from a sample set T to serve as initial clustering centers, then the distance between each sample and each clustering center is calculated, each sample is distributed to the clustering center closest to the sample set T, each clustering center represents a category, and the initial operation mode label of the sample set u is distributed as y '' u ∈{c 1 ，c 2 ，...c K }；
The sum D of the distances from all samples to the center point of the cluster to which the samples belong is calculated, and the calculation formula is as follows:
wherein C is i Centroid for the ith cluster; dist function is a set distance measurement method;
when all samples are assigned an initial operation mode label, the cluster center of each cluster is recalculated according to the existing objects in the clusters;
returning to the step of calculating the distance between each sample and the respective cluster center until no more change occurs in the cluster center of each cluster, each sample being assigned to the final run mode label y u ∈{c 1 ，c 2 ，...c K }。
11. The system for managing the carbon efficiency/energy efficiency of an air conditioning system according to claim 8, wherein the specific calculation formula is as follows, based on the relevant parameters of the chiller and the operation mode labels, the carbon emission coefficient is learned, and the carbon emission coefficient corresponding to each operation mode label is determined:
wherein, beta i is the carbon emission coefficient corresponding to the ith operation mode label; i is an operation mode label, βr is a reference operation mode carbon emission coefficient, COP r Referencing energy efficiency for baseline mode of operation, COP i The reference energy efficiency of the ith operation mode label;
wherein, COP i The calculation formula of (2) is as follows:
wherein u is the serial number of the running data record of the sample system of the ith, Q j For the actual cooling capacity of the system recorded in the j th section, the actual power of the system recorded in the P th section, and h is the total number of records divided into the ith running mode labels。
12. The system of claim 8, wherein the performing pattern recognition learning based on the operation pattern tag and the historical operation data to obtain a trained pattern recognition algorithm specifically comprises:
construction of a set training sample set t= { (x) based on operation mode tags and historical operation data u ，y u )} 1≤u≤N ，y u ∈{+1，-1}，x u ∈R n ，R n Refers to real number vector space;
The SVM model adopts a radial basis function, a training sample set is input to optimize and train the SVM model with maximized soft interval and core skills, and the following parameter ranges are used as constraint conditions:
s.t.y u (<w，φ(x u )>+b)-1≥0，u＝1，2，...，N
ξ u ≥0，u＝1，2，...，N
wherein x is u Feature vectors of a u-th sample in the training set; y is u The operation mode label of the ith sample in the training set is used, and N is the total number of categories of the samples; phi () is the nonlinear mapping of the original input space to the high-dimensional feature space, through which the nonlinear support vector machine maps the input to a feature vector, w is the normal vector of the hyperplane of the feature space, b is the bias of the hyperplane,<，>representing the inner product, ζ, of the two vectors u C is a penalty parameter for relaxation variables;
the trained pattern recognition algorithm SVM model is as follows:
i＝SVM(x,θ)
wherein i is an operation mode label, x is a load factor parameter in the cold machine operation data, and θ is a weather parameter and other operation parameters in the cold machine operation data.
13. The system according to claim 12, wherein the new specified parameters are randomly generated based on the real-time operation data of each chiller, and other parameters in the real-time operation data and the new specified parameters are input into a pattern recognition algorithm to obtain real-time operation pattern labels of each chiller; acquiring carbon emission coefficients corresponding to the real-time operation mode labels according to the real-time operation mode labels of the cold machines; optimizing running parameters through a pre-constructed optimization model based on carbon emission coefficients corresponding to the real-time running mode labels of the cold machines; the method specifically comprises the following steps of;
An optimization model aiming at minimizing carbon emission is constructed, and a Loss function Loss expression in the optimization model is as follows:
wherein n is the serial number of the cold machine, m is the total number of the cold machines, i is an output result operation mode label based on SVM (x', theta), and k is the label i,n Corresponding to the carbon emission coefficient, P, of the nth chiller device under the ith operating mode label n Rated power of the cold machine for the nth cold machine equipment, x' n Randomly generating a load factor for the n-th chiller selected by brushing;
randomly generating w new cold machine load rates x' near the real-time load rate x parameter of the nth cold machine equipment; other parameters in real-time operation data of the nth cold machine equipment and w new load factors x 'are input into a mode identification algorithm SVM (x', theta) in a grouping mode to obtain an operation mode label i of the nth cold machine equipment in w groups, and a corresponding carbon emission coefficient k is obtained according to the operation mode label i i,n ；
Inputting carbon emission coefficients corresponding to the running mode labels i of the nth cooling machine equipment in w groups to an optimization model, and brushing and selecting a load rate x 'meeting the minimum of the Loss function Loss of the nth cooling machine equipment from w load rates x'; n and outputs x' n As an optimized and adjusted operating parameter of the nth chiller plant.
14. The system according to claim 13, wherein the carbon emission coefficient corresponding to the operation mode label i of the nth chiller device of the w groups is input to the optimization model, and the load factor x "satisfying the minimization of the Loss function Loss of the nth chiller device is brushed from the w load factors x': n And outputs x' n As the optimized and adjusted operation parameters of the nth chiller equipment; the method specifically comprises the following steps:
inputting carbon emission coefficients corresponding to the running mode labels i of the w groups of nth chiller equipment to an optimization model;
selecting a load factor x 'meeting the minimum of the Loss function Loss of the nth chiller plant from the w load factor x' brushes " n And x' n Finishing output adjustment load factor x' n The limiting condition that the total cooling capacity of all cooling machines output is unchanged in the front and back air conditioning systems is output " n As the optimized and adjusted operation parameters of the nth chiller equipment; wherein, the constraint expression is as follows:
wherein Q is n Is the rated cooling capacity of the nth cooler, x n The preload factor, x' is adjusted for the nth chiller " n The nth chiller is the adjusted post load rate.
15. A computer storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the air conditioning system carbon/energy efficiency management method of any one of claims 1-7.
16. An electronic device comprising a memory and a processor: the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, which when executed by the processor, implement the steps of the air conditioning system carbon/energy efficiency management method of any one of claims 1-7.
CN202310501076.1A 2023-04-28 2023-04-28 Air conditioning system carbon efficiency/energy efficiency management method and system and storage medium Pending CN116558038A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310501076.1A CN116558038A (en) 2023-04-28 2023-04-28 Air conditioning system carbon efficiency/energy efficiency management method and system and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310501076.1A CN116558038A (en) 2023-04-28 2023-04-28 Air conditioning system carbon efficiency/energy efficiency management method and system and storage medium

Publications (1)

Publication Number Publication Date
CN116558038A true CN116558038A (en) 2023-08-08

Family

ID=87491027

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310501076.1A Pending CN116558038A (en) 2023-04-28 2023-04-28 Air conditioning system carbon efficiency/energy efficiency management method and system and storage medium

Country Status (1)

Country Link
CN (1) CN116558038A (en)

Similar Documents

Publication Publication Date Title
CN1047011C (en) State estimating apparatus
CN111237989A (en) Building ventilation air conditioner control method and device based on load prediction
CN105378391A (en) On-line optimization scheme for HVAC demand response
CN112990558B (en) Meteorological temperature and illumination prediction method based on deep migration learning
CN110458340B (en) Building air conditioner cold load autoregressive prediction method based on mode classification
CN110750655B (en) Knowledge base optimization method of intelligent IETM fault maintenance auxiliary system
CN107038100B (en) Real-time capacity display method and system for data center
CN114066071A (en) Power parameter optimization method based on energy consumption, terminal equipment and storage medium
CN111723925A (en) Method, device, equipment and medium for fault diagnosis of on-road intelligent train air conditioning unit
CN116266253A (en) Optimization control method, system and computer readable storage medium for air conditioner parameters
CN116796141A (en) GBDT regression model-based office building energy consumption prediction method
WO2024041409A1 (en) Method and apparatus for determining representative wind generating set, and control method and apparatus
CN116558038A (en) Air conditioning system carbon efficiency/energy efficiency management method and system and storage medium
Masdoua et al. Fault detection and diagnosis in AHU system with data driven approaches
CN112258233A (en) Method and device for site selection and capacity determination of regional comprehensive energy station
CN113821903A (en) Temperature control method and device, modular data center and storage medium
CN111723085A (en) Electric energy consumption data cleaning method and system for air conditioner of public building
CN115712976A (en) Heat energy and electric load optimization method based on multi-element heat supply unit and related equipment
CN112364999B (en) Training method and device for water chiller adjustment model and electronic equipment
Genkin et al. Using reinforcement learning with transfer learning to overcome smart building cold start
CN116235188A (en) Method, apparatus and storage medium for generating predictive model of analysis object
CN113792778B (en) Wind power plant partition and output correlation coefficient calculation method and system thereof
CN112966707B (en) Automatic identification method and system for universal heating ventilation air conditioning equipment model
Li et al. Study on clustering analysis of building energy consumption data
CN117175595B (en) Power grid regulation and control method and system based on multi-level data

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