Energy-saving optimization control method of regional cooling system based on tribe intelligent evolutionary algorithm

Abstract

The invention provides an energy-saving optimization control method and system of a regional cooling system based on a tribe intelligent evolutionary algorithm, and relates to the technical field of regional cooling system optimization control, and the method comprises the steps: obtaining the operation data of the regional cooling system; based on the operation data, constructing a comprehensive energy consumption model of the regional cooling system with non-control parameters and control parameters of the regional cooling system as inputs; determining an objective function and constraint conditions of the comprehensive energy consumption model; under the constraint of the constraint condition, with the minimum function value of the target function value as the target, optimizing the control parameters of the comprehensive energy consumption model by using a tribe intelligent evolutionary algorithm, and outputting the optimal control parameters; and performing energy-saving optimization control on the regional cooling system according to the optimal control parameters. According to the method, the model can be effectively prevented from falling into local optimum by utilizing the tribe intelligent evolutionary algorithm, the generated optimal control parameters can realize energy-saving optimization of the system, the optimization requirements of the complex cooling system are met, and the energy-saving optimization capability is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of district cooling system optimization control, and in particular to an energy-saving optimization control method and system for a district cooling system based on a tribal intelligent evolutionary algorithm. Background Art

[0002] A district cooling system is a centralized system that generates and delivers cooling energy to meet the cooling needs of multiple buildings or regions. Its efficient refrigeration equipment and optimized energy management can significantly reduce energy consumption, making it more economical and environmentally friendly than traditional decentralized air-conditioning systems. Since long-distance water transmission and distribution require higher pump pressures, district cooling systems are usually equipped with secondary chilled water pumps on the refrigeration side. With the significant increase in energy consumption of large central air-conditioning systems, optimized control of district cooling systems is essential for energy conservation, emission reduction and promoting sustainable development.

[0003] Meta-heuristic random search algorithms have shown excellent performance in solving optimal control problems for complex air conditioning systems, and this method is becoming increasingly popular. Chinese patent CN113761807B uses a genetic algorithm to perform global optimization of the objective function and output the air conditioning control parameters of the Feng Shui system; Chinese patent (application number) CN119196880A uses an improved gray wolf optimization algorithm to solve the total objective function, obtain the optimal control parameters, and realize multi-objective control of the indoor radiant floor system based on load prediction; effectively achieving a balance between system energy saving and comfort.

[0004] However, in the energy-saving optimization of existing district cooling systems, the optimization algorithm fails to fully combine the actual operating data, resulting in the output control parameters lacking pertinence and engineering feasibility, limiting the energy-saving optimization capability; at the same time, the existing algorithm lacks global search capabilities, is prone to fall into local optimality, has poor stability and robustness, and is difficult to meet the optimization needs of complex cooling systems. Summary of the invention

[0005] In order to solve the technical problems that in the energy-saving optimization of existing regional cooling systems, the optimization algorithm fails to fully combine the actual operation data, resulting in the output control parameters lacking pertinence and engineering feasibility, which limits the energy-saving optimization capability; at the same time, the existing algorithm has insufficient global search capability, is prone to fall into local optimality, has poor stability and robustness, and is difficult to cope with the optimization needs of complex cooling systems, the present invention provides an energy-saving optimization control method and system for a regional cooling system based on a tribal intelligent evolutionary algorithm.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect:

[0008] An energy-saving optimization control method for a district cooling system based on a tribal intelligent evolutionary algorithm is provided in an embodiment of the present invention, comprising:

[0009] S1: Obtaining the operation data of the district cooling system;

[0010] The regional cooling system includes a control host, a refrigeration unit, a cooling tower, a cooling water pump, a primary side chilled water pump, a secondary side chilled water pump, an air handling unit and an air conditioning terminal;

[0011] The operation data specifically includes:

[0012] Ambient temperature, ambient humidity, current system cooling load, total system power, total system power, equipment on / off status, water temperature, equipment power, equipment power, chilled water supply temperature and water pump flow;

[0013] The cooling tower is connected to the refrigeration unit via the cooling water pump;

[0014] The refrigeration unit is connected to the secondary side chilled water pump via the primary side chilled water pump;

[0015] The secondary side chilled water pump is connected to the air conditioning terminal through the air handling unit;

[0016] S2: constructing a comprehensive energy consumption model of the district cooling system based on the operation data;

[0017] Wherein, the input data of the comprehensive internal friction model includes non-control parameters and control parameters of the district cooling system;

[0018] The control parameters specifically include: the water supply temperature of the primary side chilled water, the water flow rate of the cooling water pump, and the flow rate of the secondary side chilled water pump;

[0019] The non-control parameters specifically include: ambient temperature, ambient humidity, real-time cooling load, and secondary side chilled water return temperature;

[0020] The comprehensive energy consumption model includes the energy consumption model of the chiller, the energy consumption model of the water pump and the fan, the heat transfer model of the cooling tower, and the heat transfer model of the manifold and the plate heat exchanger;

[0021] The energy consumption of the chiller is specifically:

[0022]

[0023] Among them, Q e,i represents the cooling capacity of the i-th chiller, COP i (t e,i ,t c,i ,r i) represents the performance coefficient of the i-th chiller, t e,i represents the evaporation temperature of the i-th chiller, t c,i represents the condensing temperature of the i-th chiller, r i represents the partial load rate of the i-th chiller;

[0024] The performance coefficient of the i-th chiller is specifically:

[0025]

[0026] Among them, α 1,i represents the first fitting coefficient of the i-th chiller, α 2,i represents the second fitting coefficient of the i-th chiller;

[0027] The partial load rate of the i-th chiller is specifically:

[0028]

[0029] Among them, Q e,rated,i represents the rated cooling capacity of the i-th chiller;

[0030] The evaporation temperature of the i-th chiller is specifically:

[0031]

[0032] Among them, t w,e,E,i represents the water temperature of the chilled water entering the evaporator of the i-th chiller, c w G w,e,i Indicates that K e,i represents the heat transfer coefficient of the evaporator of the i-th chiller, A e,i represents the heat exchange area of ​​the evaporator of the i-th chiller, c w represents the specific heat capacity of water, G w,e,i represents the chilled water flow rate of the evaporator of the i-th chiller;

[0033] The condensing temperature of the i-th chiller is specifically:

[0034]

[0035] Among them, t w,c,E,i represents the temperature of chilled water entering the condenser of the i-th chiller, Q c,i represents the condensation heat of the i-th chiller, G w,c,i represents the cooling water flow rate of the condenser of the i-th chiller, K c,i represents the heat transfer coefficient of the condenser of the i-th chiller, A c,i represents the heat exchange area of ​​the condenser of the i-th chiller;

[0036] The cooling capacity of the i-th chiller and the condensation heat of the i-th chiller are specifically:

[0037] Q e,i =c w G w,e,i (t w,e,E,i -t w,e,L,i )i∈[1,N chiller ]

[0038] Q c,i =c w G w,c,i (t w,c,L,i -t w,c,E,i )i∈[1,N chiller ]

[0039] Q c =P chiller +Q e

[0040] Among them, t w,e,L,i represents the chilled water outlet temperature of the evaporator of the i-th chiller, t w,c,L,i represents the cooling water outlet temperature of the condenser of the i-th chiller, Q c Represents the total condensation heat of the condenser, P chiller Indicates the input power of the chiller, Q e Indicates the total cooling capacity of the evaporator;

[0041] Among them, the energy consumption of the water pump is specifically:

[0042]

[0043] Among them, P pump represents the energy consumption of the water pump, β i represents the i-th fitting coefficient of the water pump equipment model, i=1,2,3, G w Indicates the water flow rate of the cooling water pump;

[0044] The energy consumption of the fan is specifically:

[0045]

[0046] Among them, P fan represents the energy consumption of the fan, χ f represents the fth fitting coefficient of the fan equipment model, f=1,2,3, G a Indicates the air flow rate of the cooling tower;

[0047] S3: Determine the objective function and constraint conditions of the comprehensive energy consumption model;

[0048] The objective function is specifically:

[0049]

[0050] Where F() is the total energy consumption function of the district cooling system, w represents water, e represents evaporator, L represents leaving a certain device, a represents air, CLWP represents cooling water pump, CHWP represents primary side chilled water pump, SCHWP represents secondary side chilled water pump, t w,e,L Indicates the water temperature leaving the chiller evaporator, G w,CLWP Indicates the water flow rate of the cooling water pump, G w,CHWP Indicates the water flow rate of the primary side chilled water pump and cooling water pump, G w,SCHWP Indicates the water flow of the two-side chilled water pump and cooling water pump, G a Indicates the air flow rate of the cooling tower, N chiller Indicates the number of chillers, P chiller,i represents the energy consumption of the i-th chiller, N CLWP Indicates the number of cooling water pumps, P CLWP,j represents the energy consumption of the jth cooling water pump, N CHWP Indicates the number of primary side chilled water pumps, P CHWP,k represents the energy consumption of the kth primary side chilled water pump, N SCHWP Indicates the number of secondary side chilled water pumps, P SCHWP,m represents the energy consumption of the mth secondary side chilled water pump, N tower Indicates the number of cooling towers, P tower,n represents the energy consumption of the nth cooling tower;

[0051] The constraints are:

[0052] t w,e,L,i,min ≤t w,e,L,i ≤t w,e,L,i,max i∈[1,N chiller ]

[0053] G w,CLWP,j,min ≤G w,CLWP,j ≤G w,CLWP,j,max j∈[1,N CLWP ]

[0054] G w,CHWP,k,min ≤G w,CHWP,k ≤G w,CHWP,k,max k∈[1,N CHWP ]

[0055] G w,SCHWP,m,min ≤G w,SCHWP,m ≤G w,SCHWP,m,max m∈[1,N SCHWP ]

[0056] Ga,n,min ≤G a,n ≤G a,n,max n∈[1,N tower ]

[0057]

[0058] Among them, t w,e,L,i represents the chilled water temperature leaving the evaporator of the i-th chiller, t w,e,L,i,min represents the lower limit of the chilled water temperature leaving the evaporator of the i-th chiller, t w,e,L,i,min represents the upper limit of the chilled water temperature leaving the evaporator of the i-th chiller, G w,CLWP,j represents the water flow rate of the jth cooling water pump, G w,CLWP,j,min represents the lower limit of the water flow rate of the jth cooling water pump, G w,CLWP,j,max represents the upper limit of the water flow rate of the jth cooling water pump, G w,CHWP,k represents the water flow rate of the kth primary side chilled water pump, G w,CHWP,k,min represents the lower limit of the water flow rate of the kth primary side chilled water pump, G w,CHWP,k,max represents the upper limit of the water flow rate of the kth secondary chilled water pump, G w,SCHWP,m represents the water flow rate of the mth secondary side chilled water pump, G w,SCHWP,m,min represents the lower limit of the water flow rate of the mth secondary side chilled water pump, G w,SCHWP,m,max represents the lower limit of the water flow rate of the mth secondary side chilled water pump, G a,n represents the air flow rate of the nth cooling tower, G a,n,min represents the lower limit of the air flow rate of the nth cooling tower, G a,n,max represents the upper limit of the air flow rate of the nth cooling tower, COP i represents the performance coefficient of the i-th chiller, t e,i represents the evaporation temperature of the i-th chiller, t c,i represents the condensing temperature of the i-th chiller, r i represents the partial load rate of the i-th chiller, Q e,demand Total cooling load represented by;

[0059] S4: Under the constraints of the constraints, with the minimum function value of the objective function value as the goal, the control parameters of the comprehensive energy consumption model are optimized by using the tribal intelligent evolutionary algorithm, and the optimal control parameters are output;

[0060] Wherein, the S4 specifically includes:

[0061] S401: Using the objective function as the fitness function of the tribal intelligent evolutionary algorithm;

[0062] S402: Initialize the population and Q table, the population includes multiple individuals, each individual represents a set of feasible control parameter solutions;

[0063] S403: Determine individual parameters by the following formula

[0064] X k =lb k +rand U(0,1) ·(ub k -lb k )

[0065] Where X represents, t w,e,L Indicates the water temperature leaving the chiller evaporator, G w,CLWP Indicates the water flow rate of the cooling water pump, G w,SCHWP represents the water flow of the two-side chilled water pump and cooling water pump, k represents the serial number of the parameter dimension, lb represents the upper limit of the set parameter, ub represents the lower limit of the set parameter, rand U(0,1) Represents a random number that follows a uniform distribution in the interval [0,1];

[0066] S404: using the classification mechanism to classify each individual to form multiple tribes;

[0067] S405: Calculate the fitness value of each individual in each tribe, and select the individual with the lowest fitness value as the leader:

[0068] minf i,j =f(X i,j,1 ,X i,j,2 ,···,X i,j,k ,···,X i,j,K )

[0069] Among them, i represents the serial number of the tribe, j represents the serial number of the individual in the tribe, and f ij represents the fitness value of the jth individual in the i-th tribe, X i,j,k represents the k-th dimension parameter of the j-th individual in the i-th tribe, 1≤i≤n, 2≤n≤N, 1≤j≤m i , 1≤k≤K, n represents the number of tribes formed by the current classification, N is the maximum number of tribes that the algorithm can form, and m i is the total number of individuals in the i-th tribe, K is the number of dimensions of individual parameters;

[0070] S406: Determine whether the minimum fitness value of each tribe is less than the average fitness value of the existing tribes; if so, the tribe is evaluated as a strong tribe; otherwise, the tribe is evaluated as a weak tribe;

[0071] S407: Use the following formula to adjust the individual parameters of each strong tribe autonomously, and adjust the individual parameters of each weak tribe diplomatically or through war;

[0072] The calculation formula for autonomous adjustment is:

[0073]

[0074] σ=|X i,leader,k -X i,j,k +ε|

[0075] Among them, X i,leader,k represents the k-th dimension parameter of the i-th tribe leader, σ represents the variance, X i,j,k ~N(X i,leader,k ,σ 2 ) indicates that the k-th dimension parameter of the j-th individual of the i-th tribe follows the parameter of the corresponding tribe leader as the mean σ 2 is the normal distribution of variance, ε represents a constant;

[0076] The diplomatic adjustment is calculated as:

[0077]

[0078] Among them, rand N(0,1) represents a random number in the interval [0,1], X dip,leader,k represents the parameter of the leader of the Ministry of Foreign Affairs, d represents the Euclidean distance;

[0079] The calculation formula for war adjustment is:

[0080] X lose,captive,k ~N(X win,leader,k ,σ 2 )

[0081] σ=|X win,leader,k -X lose,leader,k +ε|

[0082] Among them, X lose,captive,k represents the individual parameter of the plundered individual, X win,leader,k represents the parameter for defeating the leader of a tribe, and ε represents a constant;

[0083] S408: When the tribe performs an action of autonomy or diplomacy, the first tribe action reward value of the tribe is determined by the following formula:

[0084]

[0085] Among them, R i Indicates that r ij represents the reward value of the jth individual in the i-th tribe, m iis the total number of individuals in the ith tribe;

[0086] S409: When the action performed by each tribe is war, the second tribe action reward value of each tribe is determined by the following formula:

[0087]

[0088] Among them, S i Indicates the status of the i-th tribe, Strong tribe indicates a strong tribe, and Weak tribe indicates a weak tribe;

[0089] S410: According to the first tribe action reward value and the second tribe action reward value, update the Q table by the following formula:

[0090]

[0091] Among them, Q′(s i ,a i ) represents the updated Q value under the current state and action, Q(s i ,a i ) represents the Q value before update under the current state and action, λ represents the learning rate, γ represents the discount factor, Indicates the action with the largest Q value in the state after executing the action;

[0092] S411: According to the Q table, using the accumulated reward value data, guiding the update of each individual in the existing tribe;

[0093] S412: based on the updated individual information, re-determine the leaders of each tribe, compare the fitness values ​​of the leaders of each tribe, and select the leader with the lowest fitness value as the best leader;

[0094] S413: Determine whether the number of iterations reaches the maximum number of iterations or whether the convergence accuracy reaches the preset convergence accuracy. If so, output the parameter solution represented by the best leader as the best control parameter; otherwise, proceed to the next step;

[0095] S414: Determine whether there is only one tribe; if so, proceed to 404; otherwise proceed to S407 and use the objective function as the fitness function of the tribal intelligent evolution algorithm;

[0096] S5: Performing energy-saving optimization control on the regional cooling system according to the optimal control parameters.

[0097] Second aspect:

[0098] An energy-saving optimization control system for a district cooling system based on a tribal intelligent evolutionary algorithm provided by an embodiment of the present invention includes:

[0099] processor;

[0100] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the energy-saving optimization control method for the regional cooling system based on the tribal intelligent evolutionary algorithm as described in the first aspect is implemented.

[0101] The third aspect:

[0102] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the energy-saving optimization control method for a regional cooling system based on a tribal intelligent evolutionary algorithm as described in the first aspect is implemented.

[0103] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0104] (1) In the embodiment of the present invention, by collecting the operating data of the district cooling system, a comprehensive energy consumption model of the district cooling system is constructed based on the operating data, and the comprehensive influence of non-control parameters and control parameters is combined to improve the accuracy and pertinence of the comprehensive energy consumption model, thereby providing basic support for achieving more efficient energy-saving optimization.

[0105] (2) In the embodiment of the present invention, the control parameters of the comprehensive energy consumption model are optimized by using the tribal intelligent evolutionary algorithm under the constraints of the constraints and taking the minimum function value of the objective function value as the goal, and the optimal control parameters are output. The energy-saving optimization control of the regional cooling system is performed according to the optimal control parameters. The use of the tribal intelligent evolutionary algorithm can effectively avoid the risk of the comprehensive energy consumption model falling into the local optimum, and the generated optimal control parameters can achieve system energy-saving optimization, meet the optimization needs of the complex cooling system, and significantly improve the energy-saving optimization capability. BRIEF DESCRIPTION OF THE DRAWINGS

[0106] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0107] Figure 1 A flow chart of an energy-saving optimization control method for a district cooling system based on a tribal intelligent evolutionary algorithm provided by an embodiment of the present invention;

[0108] Figure 2 A schematic diagram of the structure of an energy-saving optimization control system for a regional cooling system based on a tribal intelligent evolutionary algorithm provided by an embodiment of the present invention;

[0109] Figure 3 A schematic diagram of a process flow of a tribal intelligent evolutionary algorithm provided by an embodiment of the present invention;

[0110] Figure 4 A schematic structural diagram of another energy-saving optimization control system for a regional cooling system based on a tribal intelligent evolutionary algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0111] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0112] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0113] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0114] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0115] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0116] Reference Manual Attached Figure 1 , showing a flow chart of an energy-saving optimization control method for a regional cooling system based on a tribal intelligent evolutionary algorithm provided in an embodiment of the present invention.

[0117] Reference Manual Attached Figure 2 , showing a structural schematic diagram of an energy-saving optimization control system of a regional cooling system based on a tribal intelligent evolutionary algorithm provided by an embodiment of the present invention.

[0118] The embodiment of the present invention provides an energy-saving optimization control method for a regional cooling system based on a tribal intelligent evolutionary algorithm. The method can be implemented by an energy-saving optimization control device for a regional cooling system based on a tribal intelligent evolutionary algorithm. The energy-saving optimization control device for a regional cooling system based on a tribal intelligent evolutionary algorithm can be a terminal or a server. The processing flow of the energy-saving optimization control method for a regional cooling system based on a tribal intelligent evolutionary algorithm may include the following steps:

[0119] S1: Obtaining the operation data of the district cooling system;

[0120] In a possible implementation, the regional cooling system includes a control host, a refrigeration unit, a cooling tower, a cooling water pump, a primary side chilled water pump, a secondary side chilled water pump, an air handling unit, and an air conditioning terminal.

[0121] The cooling tower is connected to the refrigeration unit through a cooling water pump;

[0122] The refrigeration unit is connected to the secondary side chilled water pump through the primary side chilled water pump;

[0123] The secondary side chilled water pump is connected to the air conditioning terminal through the air handling unit.

[0124] Optionally, temperature and humidity sensors are installed in the district cooling system to collect environmental variables, and temperature sensors and water flow sensors are installed on the pipeline. The data collected by the sensors is transmitted to the AI ​​edge computing processor through the equipment controller and the intelligent PLC main controller.

[0125] The AI ​​edge computing processor is deployed with a district cooling system energy consumption model and a tribal intelligent evolutionary algorithm to calculate and output control parameters. The tribal intelligent evolutionary algorithm provides an optimal operating parameter system for chillers, pumps, and cooling towers, aiming to maximize overall energy efficiency. The regularly optimized operating parameters are automatically distributed to various equipment controllers through the intelligent PLC master controller and connected to each device through the analog signal input interface.

[0126] The variables collected by the sensors include ambient temperature and humidity, overall system parameters, and specific device parameters. Overall system parameters include total cooling load, total system power, and total power. Parameters for each device include device on / off status, water temperature, device power, and device power. Control output parameters include device on / off status, chilled water supply temperature, and pump flow after optimization by the Tribe Intelligent Evolutionary Algorithm.

[0127] In a possible implementation manner, the operation data specifically includes:

[0128] Ambient temperature, ambient humidity, current system cooling load, total system power, total system power, equipment on / off status, water temperature, equipment power, equipment power, chilled water supply temperature and water pump flow.

[0129] In the present invention, the collection of parameters such as ambient temperature, humidity, cooling load, water temperature, etc. can clearly reflect the dynamic operation of the system and provide necessary input for the construction of the subsequent comprehensive energy consumption model.

[0130] S2: constructing a comprehensive energy consumption model of the district cooling system based on the operation data, wherein the input data of the comprehensive internal consumption model includes non-control parameters and control parameters of the district cooling system;

[0131] In a possible implementation, the comprehensive energy consumption model includes a chiller energy consumption model, a water pump and fan energy consumption model, a cooling tower heat transfer model, and a manifold and plate heat exchanger heat transfer model;

[0132] Among them, the chiller energy consumption model is used to describe the energy consumption characteristics and operating performance of the chiller. The model comprehensively considers parameters such as cooling capacity, performance coefficient, evaporation temperature, condensation temperature and partial load rate to accurately calculate the power consumption of the chiller.

[0133] The water pump and fan energy consumption model is used to describe the energy consumption characteristics of the water pump and cooling tower fan. The model accurately calculates the power consumption of the water pump and fan by considering the flow rate of the water pump, the air flow rate of the fan and the fitting coefficient of the equipment.

[0134] Among them, the cooling tower heat transfer model is used to describe the heat exchange process between cooling water and air in the cooling tower. By calculating parameters such as the cooling water inlet and outlet temperature difference, wet air enthalpy value and heat exchange efficiency, it reflects the thermal performance and operating energy consumption of the cooling tower.

[0135] Among them, the manifold and plate heat exchanger are the core components for realizing the primary and secondary chilled water distribution and heat exchange in the district cooling system. The heat exchange models of the two are modeled based on the principles of energy conservation and heat transfer respectively.

[0136] The energy consumption of the chiller is as follows:

[0137]

[0138] Among them, Q e,i represents the cooling capacity of the i-th chiller, COP i (t e,i ,t c,i ,r i ) represents the performance coefficient of the i-th chiller, t e,i represents the evaporation temperature of the i-th chiller, t c,i represents the condensing temperature of the i-th chiller, r i represents the partial load rate of the i-th chiller;

[0139] The performance coefficient of the i-th chiller is:

[0140]

[0141] Among them, α 1,i Indicates that α 2,i express;

[0142] The specific partial load rate of the i-th chiller is:

[0143]

[0144] Among them, Q e,rated,i represents the rated cooling capacity of the i-th chiller;

[0145] The evaporation temperature of the i-th chiller is:

[0146]

[0147] Among them, t w,e,E,i represents the water temperature of the chilled water entering the evaporator of the i-th chiller, c w G w,e,i Indicates that K e,i represents the heat transfer coefficient of the evaporator of the i-th chiller, A e,i represents the heat exchange area of ​​the evaporator of the i-th chiller, c w represents the specific heat capacity of water, G w,e,i represents the chilled water flow rate of the evaporator of the i-th chiller;

[0148] The condensing temperature of the i-th chiller is:

[0149]

[0150] Among them, t w,c,E,i represents the temperature of chilled water entering the condenser of the i-th chiller, Q c,i represents the condensation heat of the i-th chiller, G w,c,i represents the cooling water flow rate of the condenser of the i-th chiller, K c,i represents the heat transfer coefficient of the condenser of the i-th chiller, A c,i represents the heat exchange area of ​​the condenser of the i-th chiller;

[0151] The cooling capacity of the i-th chiller and the condensation heat of the i-th chiller are specifically:

[0152] Q e,i =c w G w,e,i (t w,e,E,i -t w,e,L,i )i∈[1,N chiller ]

[0153] Q c,i =c w G w,c,i (t w,c,L,i -t w,c,E,i )i∈[1,N chiller ]

[0154] Q c =P chiller +Q e

[0155] Among them, t w,e,L,i represents the chilled water outlet temperature of the evaporator of the i-th chiller, t w,c,L,i represents the cooling water outlet temperature of the condenser of the i-th chiller, Q c Represents the total condensation heat of the condenser, P chiller Indicates the input power of the chiller, Q e Indicates the total cooling capacity of the evaporator.

[0156] In a possible implementation manner, the energy consumption of the water pump is specifically:

[0157]

[0158] Among them, P pump represents the energy consumption of the water pump, β i represents the i-th fitting coefficient of the water pump equipment model, i=1,2,3, G w Indicates the water flow rate of the cooling water pump;

[0159] The energy consumption of the fan is as follows:

[0160]

[0161] Among them, P fan represents the energy consumption of the fan, χ f represents the fth fitting coefficient of the fan equipment model, f=1,2,3, G a Indicates the air flow rate of the cooling tower.

[0162] Optionally, the condensing temperature needs to be determined by a cooling tower heat exchange model. The inlet and outlet temperature difference of the cooling water flowing through the cooling tower is determined by the following formula. After obtaining the temperature difference, the cooling water temperature can be iteratively calculated:

[0163]

[0164] h=1.005t+(2501+1.84t)d

[0165]

[0166] Among them, Δtw,tower Indicates that G a It means that η tower represents the efficiency of the cooling tower, h sa It represents the enthalpy of saturated air at the water temperature entering the cooling tower, h a It represents the enthalpy of moist air at ambient temperature and humidity, c w represents the specific heat capacity of water, G w,tower represents the mass flow rate of cooling water flowing through the cooling tower, c a It represents the constant pressure specific heat capacity of air at 300K. NTU represents the number of heat transfer units, m * represents the heat capacity ratio of air and water, f1 and f2 represent the fitting coefficients of the cooling tower model, d represents the moisture content of humid air, h represents the enthalpy value of humid air, Relative humidity of ambient air, P s It represents the partial pressure of water vapor in saturated moist air, B represents the atmospheric pressure, and t represents the temperature of the environment.

[0167] It should be noted that the chilled water cycle in the district cooling system is divided into a primary side and a secondary side, which are connected by a manifold or a plate heat exchanger. The manifold collects the primary side chilled water and redistributes it to the secondary side, thereby ensuring the effective transmission of quality and energy.

[0168] Alternatively, according to the law of conservation of energy and mass, the relationship between the flow rate and temperature difference of the chilled water on both sides can be obtained, which is determined by the following formula:

[0169]

[0170] Where Φ represents the heat transfer per unit time;

[0171] Alternatively, the plate heat exchanger transfers energy by convective heat transfer between the primary and secondary chilled water without mass exchange, and the heat transfer law can be used to obtain the heat transfer amount, which is determined by the following formula:

[0172] Φ=KAΔt m

[0173]

[0174] Among them, Δt m represents the logarithmic mean temperature difference of the plate heat exchanger, K represents the total heat transfer coefficient of the heat exchanger, A represents the heat exchange area of ​​the heat exchanger, Δt′ represents the temperature difference between the cold and hot fluids at the inlet, and Δt″ represents the temperature difference between the cold and hot fluids at the outlet;

[0175] when When LMTD is used, the arithmetic mean temperature difference (AMTD) can be used instead of LMTD, and the error can be ignored, which is determined by the following formula:

[0176]

[0177] in, represents the average temperature; Indicates the inlet temperature of the secondary side chilled water flowing into the heat exchanger, Indicates the inlet temperature of the primary side chilled water flowing into the heat exchanger. Indicates the water temperature at the chilled water outlet on the secondary side of the heat exchanger. Indicates the water temperature at the chilled water outlet on the primary side of the heat exchanger, N chiller represents the total number of chillers, t w,e,L(E),i represents the outlet or inlet temperature of the chilled water of the evaporator of the i-th chiller, Represents the average temperature of the secondary side chilled water, N SCHWP Represents the total number of secondary side chilled water pumps, t w,e,L(E),sec,m Indicates the chilled water outlet or inlet temperature corresponding to the mth secondary side chilled water pump.

[0178] In a possible implementation, the control parameters specifically include: the supply temperature of the primary-side chilled water, the water flow rate of the cooling water pump, and the flow rate of the secondary-side chilled water pump;

[0179] Optionally, it also includes: the start and stop status of the cooling water pump parameters and the chilled water pump parameters, the start and stop status of the cooling tower and the fan speed, the start and stop status of the refrigeration unit and the chilled water supply temperature.

[0180] The non-control parameters specifically include: ambient temperature, ambient humidity, real-time cooling load, and secondary side chilled water return temperature.

[0181] In the present invention, the adjustable system operating variables are clearly defined to ensure that the model can accurately describe the operating status of the system. At the same time, external factors such as ambient temperature and humidity, and real-time cooling load are taken into consideration to make the model closer to actual working conditions and enhance the prediction accuracy and adaptability of the model.

[0182] Furthermore, the modular design of the comprehensive energy consumption model enables it to adapt to the complex needs of regional cooling systems. The model includes multiple sub-models such as the chiller energy consumption model, the water pump energy consumption model, and the cooling tower heat transfer model. It can be adjusted and expanded for different equipment or operating conditions. This design is not only suitable for a single scenario, but also can meet the optimization needs of multiple scenarios and multiple conditions; at the same time, the model can quickly respond to the dynamic changes of the cooling load and adjust control parameters such as the chilled water supply temperature and the cooling water pump flow to ensure that the system operation is optimized while meeting the needs. By optimizing the distribution of cooling capacity, the performance coefficient of the chiller can be improved, energy waste can be reduced, and the overall operating efficiency of the cooling system can be improved.

[0183] S3: Determine the objective function and constraints of the comprehensive energy consumption model;

[0184] In a possible implementation, the objective function is specifically:

[0185]

[0186] Where F() is the total energy consumption function of the district cooling system, w represents water, e represents evaporator, L represents leaving a certain device, a represents air, CLWP represents cooling water pump, CHWP represents primary side chilled water pump, SCHWP represents secondary side chilled water pump, t w,e,L Indicates the water temperature leaving the chiller evaporator, G w,CLWP Indicates the water flow rate of the cooling water pump, G w,CHWP Indicates the water flow rate of the primary side chilled water pump and cooling water pump, G w,SCHWP Indicates the water flow of the two-side chilled water pump and cooling water pump, G a Indicates the air flow rate of the cooling tower, N chiller Indicates the number of chillers, P chiller,i represents the energy consumption of the i-th chiller, N CLWP Indicates the number of cooling water pumps, P CLWP,j represents the energy consumption of the jth cooling water pump, N CHWP Indicates the number of primary side chilled water pumps, P CHWP,k represents the energy consumption of the kth primary side chilled water pump, N SCHWP Indicates the number of secondary side chilled water pumps, P SCHWP,m represents the energy consumption of the mth secondary side chilled water pump, N tower Indicates the number of cooling towers, P tower,n Represents the energy consumption of the nth cooling tower.

[0187] In a possible implementation, the constraints are:

[0188] t w,e,L,i,min ≤t w,e,L,i ≤t w,e,L,i,max i∈[1,N chiller ]

[0189] G w,CLWP,j,min ≤G w,CLWP,j ≤G w,CLWP,j,max j∈[1,N CLWP ]

[0190] G w,CHWP,k,min ≤G w,CHWP,k ≤G w,CHWP,k,max k∈[1,N CHWP ]

[0191] G w,SCHWP,m,min ≤G w,SCHWP,m ≤G w,SCHWP,m,max m∈[1,NSCHWP ]

[0192] G a,n,min ≤G a,n ≤G a,n,max n∈[1,N tower ]

[0193]

[0194] Among them, t w,e,L,i represents the chilled water temperature leaving the evaporator of the i-th chiller, t w,e,L,i,min represents the lower limit of the chilled water temperature leaving the evaporator of the i-th chiller, t w,e,L,i,min represents the upper limit of the chilled water temperature leaving the evaporator of the i-th chiller, G w,CLWP,j represents the water flow rate of the jth cooling water pump, G w,CLWP,j,min represents the lower limit of the water flow rate of the jth cooling water pump, G w,CLWP,j,max represents the upper limit of the water flow rate of the jth cooling water pump, G w,CHWP,k represents the water flow rate of the kth primary side chilled water pump, G w,CHWP,k,min represents the lower limit of the water flow rate of the kth primary side chilled water pump, G w,CHWP,k,max represents the upper limit of the water flow rate of the kth secondary chilled water pump, G w,SCHWP,m represents the water flow rate of the mth secondary side chilled water pump, G w,SCHWP,m,min represents the lower limit of the water flow rate of the mth secondary side chilled water pump, G w,SCHWP,m,max represents the lower limit of the water flow rate of the mth secondary side chilled water pump, G a,n represents the air flow rate of the nth cooling tower, G a,n,min represents the lower limit of the air flow rate of the nth cooling tower, G a,n,max represents the upper limit of the air flow rate of the nth cooling tower, COP i represents the performance coefficient of the i-th chiller, t e,i represents the evaporation temperature of the i-th chiller, t c,i represents the condensing temperature of the i-th chiller, r i represents the partial load rate of the i-th chiller, Q e,demand Represents the total cooling load.

[0195] In the present invention, the objective function is defined as the total energy consumption of the regional cooling system, covering the energy consumption of major equipment such as chillers, water pumps, cooling towers, etc. By minimizing energy consumption, the system can be guided to achieve the lowest overall energy consumption while meeting demand, thereby significantly reducing operating costs and improving energy efficiency; at the same time, the constraints set the upper and lower limits of each key parameter (such as water flow, chilled water temperature, cooling tower air flow, etc.) to avoid parameters operating beyond the design range of the equipment. By limiting key variables such as chilled water temperature, flow, and air flow, equipment failures caused by overload or improper operation can be effectively avoided, and the safety and reliability of system operation can be improved.

[0196] Furthermore, the constraints in the comprehensive energy consumption model introduce the limitation of the total cooling load of the system to ensure that the system can meet the cooling demand of users under various working conditions. Whether it is peak load or low load operation state, the optimization results can ensure that the chiller and water pump operate in the optimal state on the basis of meeting the cooling load.

[0197] S4: Under the constraints of the constraints, with the minimum function value of the objective function value as the goal, the control parameters of the comprehensive energy consumption model are optimized using the tribal intelligent evolutionary algorithm, and the optimal control parameters are output;

[0198] In a possible implementation, the objective function is used as the fitness function of the tribal intelligent evolutionary algorithm.

[0199] Referring to the accompanying drawing of the specification, a schematic flow chart of a tribal intelligent evolution algorithm provided by an embodiment of the present invention is shown.

[0200] Specifically, the tribal intelligent evolution algorithm is as follows:

[0201] S401: Using the objective function as the fitness function of the tribal intelligent evolutionary algorithm;

[0202] In the present invention, the objective function is used as the fitness function, and the algorithm can directly optimize the total energy consumption of the system to ensure that the output control parameter combination can significantly reduce the energy consumption of the system.

[0203] S402: Initialize the population and Q table, the population includes multiple individuals, each individual represents a set of feasible control parameter solutions;

[0204] S403: Determine individual parameters by the following formula

[0205] X k =lb k +rand U(0,1) ·(ub k -lb k )

[0206] Where X represents, t w,e,L Indicates the water temperature leaving the chiller evaporator, G w,CLWP Indicates the water flow rate of the cooling water pump, G w,SCHWP represents the water flow of the two-side chilled water pump and cooling water pump, k represents the serial number of the parameter dimension, lb represents the upper limit of the set parameter, ub represents the lower limit of the set parameter, rand U(0,1) Represents a random number that follows a uniform distribution in the interval [0,1];

[0207] S404: using the classification mechanism to classify each individual to form multiple tribes;

[0208] S405: Calculate the fitness value of each individual in each tribe, and select the individual with the lowest fitness value as the leader:

[0209] minf i,j =f(X i,j,1 ,X i,j,2 ,···,X i,j,k ,···,X i,j,K )

[0210] Among them, i represents the serial number of the tribe, j represents the serial number of the individual in the tribe, and f ij represents the fitness value of the jth individual in the i-th tribe, X i,j,k represents the k-th dimension parameter of the j-th individual in the i-th tribe, 1≤i≤n, 2≤n≤N, 1≤j≤m i , 1≤k≤K, n represents the number of tribes formed by the current classification, N is the maximum number of tribes that the algorithm can form, and m i is the total number of individuals in the i-th tribe, K is the number of dimensions of individual parameters;

[0211] In the present invention, through multi-tribe classification and leader selection mechanism, the tribal intelligent evolutionary algorithm can avoid excessive reliance on a single solution.

[0212] S406: Determine whether the minimum fitness value of each tribe is less than the average fitness value of the existing tribes; if so, the tribe is evaluated as a strong tribe; otherwise, the tribe is evaluated as a weak tribe;

[0213] S407: Use the following formula to adjust the individual parameters of each strong tribe autonomously, and adjust the individual parameters of each weak tribe diplomatically or through war;

[0214] The calculation formula for autonomous adjustment is:

[0215]

[0216] σ=|X i,leader,k -Xi,j,k +ε|

[0217] Among them, X i,leader,k represents the k-th dimension parameter of the i-th tribe leader, σ represents the variance, X i,j,k ~N(X i,leader,k ,σ 2 ) indicates that the k-th dimension parameter of the j-th individual of the i-th tribe follows the parameter of the corresponding tribe leader as the mean σ 2 is the normal distribution of variance, ε represents a constant;

[0218] The diplomatic adjustment is calculated as:

[0219]

[0220] Among them, rand N(0,1) represents a random number in the interval [0,1], X dip,leader,k represents the parameter of the leader of the Ministry of Foreign Affairs, d represents the Euclidean distance;

[0221] The calculation formula for war adjustment is:

[0222] X lose,captive,k ~N(X win,leader,k ,σ 2 )

[0223] σ=|X win,leader,k -X lose,leader,k +ε|

[0224] Among them, X lose,captive,k represents the individual parameter of the plundered individual, X win,leader,k represents the parameter for defeating the leader of a tribe, and ε represents a constant;

[0225] In the present invention, the tribal intelligent evolution algorithm combines reinforcement learning and multi-objective optimization mechanisms, and dynamically adjusts individual parameters through various strategies such as autonomy, diplomacy, and war, effectively improving the algorithm's global search ability and convergence speed. By dynamically updating the Q table and guiding tribal classification, the optimal solution can be quickly located, reducing ineffective calculations and explorations.

[0226] S408: When the tribe performs an action of autonomy or diplomacy, the first tribe action reward value of the tribe is determined by the following formula:

[0227]

[0228] Among them, Ri represents r ij represents the reward value of the jth individual in the i-th tribe, m i is the total number of individuals in the ith tribe;

[0229] S409: When the action performed by each tribe is war, the second tribe action reward value of each tribe is determined by the following formula:

[0230]

[0231] Among them, S i Indicates the status of the i-th tribe, Strong tribe indicates a strong tribe, and Weak tribe indicates a weak tribe;

[0232] S410: According to the first tribe action reward value and the second tribe action reward value, update the Q table by the following formula:

[0233]

[0234] Among them, Q′(s i ,a i ) represents the updated Q value under the current state and action, Q(s i ,a i ) represents the Q value before update under the current state and action, λ represents the learning rate, γ represents the discount factor, Indicates the action with the largest Q value in the state after executing the action;

[0235] In this invention, by introducing the Q-learning reinforcement learning mechanism, the tribal intelligent evolution algorithm can learn the optimal strategy from each action and continuously optimize the choices of autonomy, diplomacy and war. This learning mechanism makes the algorithm gradually intelligent during the iteration process and significantly improves the optimization performance.

[0236] S411: According to the Q table, using the accumulated reward value data, guiding the update of each individual in the existing tribe;

[0237] S412: based on the updated individual information, re-determine the leaders of each tribe, compare the fitness values ​​of the leaders of each tribe, and select the leader with the lowest fitness value as the best leader;

[0238] It should be noted that when the number of individuals in a tribe reaches zero, the tribe will perish. Each surviving tribe will re-elect a new leader based on its fitness value.

[0239] S413: Determine whether the number of iterations reaches the maximum number of iterations or whether the convergence accuracy reaches the preset convergence accuracy. If so, output the parameter solution represented by the best leader as the best control parameter; otherwise, proceed to the next step;

[0240] S414: Determine whether there is only one tribe; if so, go to 404; otherwise, go to S407.

[0241] In summary, optimizing the comprehensive energy consumption model by using the tribal intelligent evolutionary algorithm not only improves the optimization efficiency and stability, but also enhances the global search capability and dynamic adaptability. This method can effectively solve the energy-saving optimization problem of complex systems and ensure the operability of the optimization results.

[0242] S5: Perform energy-saving optimization control on the district cooling system according to the optimal control parameters.

[0243] Specifically, experimental comparisons show the convergence curves of the Tribal Intelligent Evolutionary Algorithm (TIEO) and seven common algorithms when optimizing 16 test functions. In this process, the total number of individuals of all algorithms is 50, the optimization parameter dimension is 30, and the maximum number of iterations is 300. The highest convergence accuracy is achieved.

[0244] The specific embodiments are two types of district cooling systems including a manifold and a plate heat exchanger.

[0245] Table 1 Equipment parameters of the district cooling system with manifolds

[0246]

[0247] The district cooling system with manifolds provides centralized cooling for a hospital, which requires 24 / 7 operation and continuous cooling, representing a highly dynamic, constant-load system. The number and parameters of the equipment included in the specific embodiment are shown in Table 1.

[0248] Table 2 Equipment parameters of the district cooling system with plate heat exchanger

[0249]

[0250] The district cooling system with plate heat exchanger described above provides cooling for a bank, which has periodic cooling demand and represents a moderate, intermittent load system. The equipment quantity and parameters of the specific embodiment are shown in Table 2.

[0251] All pumps in both systems run at variable frequency, while cooling tower fans also run at fixed frequency.

[0252] Table 3 Basic parameters of the district cooling system in the simulation test

[0253]

[0254] In the simulation test of the specific embodiment, three operating conditions (high, medium and low load) are set, and the basic parameters are shown in Table 3. The optimized primary side chilled water supply temperature range is set between 6°C and 12°C. The temperature difference range of the cooling water is set between 1°C and 10°C. The lower limit of the water pump flow is set to 30% of the rated flow, and the upper limit is the rated flow.

[0255] Table 4 Optimization effect of each algorithm on the district cooling system in simulation test

[0256]

[0257] The tribal intelligent evolutionary algorithm (TIEO) and seven other common algorithms are used to simulate and optimize the energy consumption model of the district cooling system. Table 4 shows the performance of all algorithms in the two district cooling systems of the specific embodiment under different working conditions. The tribal intelligent evolutionary algorithm achieves the best energy saving rate, the smallest standard deviation and the shortest calculation time in both systems. Compared with the district cooling system containing the manifold, the overall control parameter dimension of the system containing the plate heat exchanger increases, which has greater optimization difficulty. The particle swarm algorithm (PSO) is prone to fall into the local optimum, and its performance deteriorates with the increase of the dimension of the optimization parameter. Although the differential evolution algorithm (DE) performs well, its calculation time is too long. The overall performance of the wolf pack search algorithm (WPS) and the gravitational search algorithm (GSA) are both poor. Although the Salp Sea Squid Optimization Algorithm (SSA) and the Satin Bowerbird Optimization Algorithm (SBO) show better performance under certain operating conditions, they still have limitations when facing complex and diverse optimization problems. The Tribal Intelligent Evolutionary Algorithm (TIEO) always achieves the best optimization effect and stability when dealing with complex high-dimensional engineering problems, and the calculation time is reasonable.

[0258] Optionally, an energy-saving optimization control method for a district cooling system based on a tribal intelligent evolutionary algorithm is verified in a hospital and a bank. Due to the limitations of actual engineering conditions, 30 working days in the cooling season of 2023 were selected for testing. The first day was optimized and the second day was non-optimized, and so on, forming 15 control groups. In order to evaluate the overall energy-saving performance of the system in actual operation, the seasonal coefficient of performance (SCOP) is used as a measure of energy efficiency. SCOP is defined as the ratio of cooling load to total system energy consumption. The higher the value, the better the system performance.

[0259]

[0260] Where SCOP is the coefficient of performance, Q e Represents cooling load, P total Represents the total energy consumption of the system.

[0261] In the district cooling system with a manifold, during the 30-day test period, the average cooling load without optimization was 41645.28 kW, the average total power was 15183.27 kW, and the average SCOP was 2.74; under optimized control, the average cooling load was 38218.81 kW, the average total power consumption was 12278.90 kW, and the average SCOP was 3.11. Through the optimization strategy, SCOP was improved by 13.56%. The results show that the energy-saving optimization control method for a district cooling system based on a tribal intelligent evolutionary algorithm described in the present invention is feasible in an actual district cooling system with a manifold, and effectively reduces energy consumption while improving operating efficiency.

[0262] In the district cooling system containing plate heat exchangers, during the 30-day test period, under non-optimized conditions, the average cooling load was 13289.49 kW, the average total power consumption was 4447.25 kW, and the average SCOP was 2.99. Under optimized operating conditions, the average cooling load was 13208.16 kW, the average total power consumption was 3967.80 kW, and the average SCOP was 3.33. The SCOP of the system under the optimization strategy increased by 11.40%. The results show that the energy-saving optimization control method for a district cooling system based on a tribal intelligent evolutionary algorithm described in the present invention also brings significant performance improvements to an actual district cooling system with a plate heat exchanger.

[0263] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0264] (1) In the embodiment of the present invention, by collecting the operating data of the district cooling system, a comprehensive energy consumption model of the district cooling system is constructed based on the operating data, and the comprehensive influence of non-control parameters and control parameters is combined to improve the accuracy and pertinence of the comprehensive energy consumption model, thereby providing basic support for achieving more efficient energy-saving optimization.

[0265] (2) In the embodiment of the present invention, the control parameters of the comprehensive energy consumption model are optimized by using the tribal intelligent evolutionary algorithm under the constraints of the constraints and taking the minimum function value of the objective function value as the goal, and the optimal control parameters are output. The energy-saving optimization control of the regional cooling system is performed according to the optimal control parameters. The use of the tribal intelligent evolutionary algorithm can effectively avoid the risk of the comprehensive energy consumption model falling into the local optimum, and the generated optimal control parameters can achieve system energy-saving optimization, meet the optimization needs of the complex cooling system, and significantly improve the energy-saving optimization capability.

[0266] Reference Manual Attached Figure 4 , showing a structural schematic diagram of another energy-saving optimization control system of a regional cooling system based on a tribal intelligent evolutionary algorithm provided by the present invention.

[0267] The present invention also provides another energy-saving optimization control system 20 of a regional cooling system based on a tribal intelligent evolutionary algorithm, which is applied to the energy-saving optimization control method of the regional cooling system based on the tribal intelligent evolutionary algorithm, comprising:

[0268] Processor 201.

[0269] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the energy-saving optimization control method of the regional cooling system based on the tribal intelligent evolutionary algorithm as in the method embodiment is implemented.

[0270] The energy-saving optimization control system 20 of the regional cooling system based on the tribal intelligent evolutionary algorithm provided by the present invention can execute the above-mentioned energy-saving optimization control method of the regional cooling system based on the tribal intelligent evolutionary algorithm, and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0271] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0272] (1) In the embodiment of the present invention, by collecting the operating data of the district cooling system, a comprehensive energy consumption model of the district cooling system is constructed based on the operating data, and the comprehensive influence of non-control parameters and control parameters is combined to improve the accuracy and pertinence of the comprehensive energy consumption model, thereby providing basic support for achieving more efficient energy-saving optimization.

[0273] (2) In the embodiment of the present invention, the control parameters of the comprehensive energy consumption model are optimized by using the tribal intelligent evolutionary algorithm under the constraints of the constraints and taking the minimum function value of the objective function value as the goal, and the optimal control parameters are output. The energy-saving optimization control of the regional cooling system is performed according to the optimal control parameters. The use of the tribal intelligent evolutionary algorithm can effectively avoid the risk of the comprehensive energy consumption model falling into the local optimum, and the generated optimal control parameters can achieve system energy-saving optimization, meet the optimization needs of the complex cooling system, and significantly improve the energy-saving optimization capability.

[0274] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0275] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0276] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0277] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0278] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can be represented by: a, b, c, ab, ac, bc or abc, where a, b, c can be single or plural.

[0279] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0280] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0281] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0282] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0283] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0284] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0285] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0286] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the energy-saving optimization control method for a regional cooling system based on a tribal intelligent evolutionary algorithm as described in the method embodiment is implemented.

[0287] A computer-readable storage medium provided by the present invention can implement the steps and effects of the energy-saving optimization control method of the regional cooling system based on the tribal intelligent evolutionary algorithm of the above-mentioned method embodiment. To avoid repetition, the present invention will not go into details.

[0288] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0289] (1) In the embodiment of the present invention, by collecting the operating data of the district cooling system, a comprehensive energy consumption model of the district cooling system is constructed based on the operating data, and the comprehensive influence of non-control parameters and control parameters is combined to improve the accuracy and pertinence of the comprehensive energy consumption model, thereby providing basic support for achieving more efficient energy-saving optimization.

[0290] (2) In the embodiment of the present invention, the control parameters of the comprehensive energy consumption model are optimized by using the tribal intelligent evolutionary algorithm under the constraints of the constraints and taking the minimum function value of the objective function value as the goal, and the optimal control parameters are output. The energy-saving optimization control of the regional cooling system is performed according to the optimal control parameters. The use of the tribal intelligent evolutionary algorithm can effectively avoid the risk of the comprehensive energy consumption model falling into the local optimum, and the generated optimal control parameters can achieve system energy-saving optimization, meet the optimization needs of the complex cooling system, and significantly improve the energy-saving optimization capability.

[0291] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0292] There are a few points to note:

[0293] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0294] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0295] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0296] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An energy-saving optimization control method for a district cooling system based on a tribal intelligent evolutionary algorithm, characterized in that: include: S1: Obtaining the operation data of the district cooling system; The regional cooling system includes a control host, a refrigeration unit, a cooling tower, a cooling water pump, a primary side chilled water pump, a secondary side chilled water pump, an air handling unit and an air conditioning terminal; The operation data specifically includes: Ambient temperature, ambient humidity, current system cooling load, total system power, total system power, equipment on / off status, water temperature, equipment power, equipment power, chilled water supply temperature and water pump flow; The cooling tower is connected to the refrigeration unit via the cooling water pump; The refrigeration unit is connected to the secondary side chilled water pump via the primary side chilled water pump; The secondary side chilled water pump is connected to the air conditioning terminal through the air handling unit; S2: constructing a comprehensive energy consumption model of the district cooling system based on the operation data; Wherein, the input data of the comprehensive internal friction model includes non-control parameters and control parameters of the district cooling system; The control parameters specifically include: the water supply temperature of the primary side chilled water, the water flow rate of the cooling water pump, and the flow rate of the secondary side chilled water pump; The non-control parameters specifically include: ambient temperature, ambient humidity, real-time cooling load, and secondary side chilled water return temperature; The comprehensive energy consumption model includes the energy consumption model of the chiller, the energy consumption model of the water pump and the fan, the heat transfer model of the cooling tower, and the heat transfer model of the manifold and the plate heat exchanger; The energy consumption of the chiller is specifically: Among them, Q e,i represents the cooling capacity of the i-th chiller, COP i (t e,i ,t c,i ,r i ) represents the performance coefficient of the i-th chiller, t e,i represents the evaporation temperature of the i-th chiller, t c,i represents the condensing temperature of the i-th chiller, r i represents the partial load rate of the i-th chiller; The performance coefficient of the i-th chiller is specifically: Among them, α 1,i represents the first fitting coefficient of the i-th chiller, α 2,i represents the second fitting coefficient of the i-th chiller; The partial load rate of the i-th chiller is specifically: Among them, Q e,rated,i represents the rated cooling capacity of the i-th chiller; The evaporation temperature of the i-th chiller is specifically: Among them, t w,e,E,i represents the water temperature of the chilled water entering the evaporator of the i-th chiller, c w G w,e,i Indicates that K e,i represents the heat transfer coefficient of the evaporator of the i-th chiller, A e,i represents the heat exchange area of ​​the evaporator of the i-th chiller, c w represents the specific heat capacity of water, G w,e,i represents the chilled water flow rate of the evaporator of the i-th chiller; The condensing temperature of the i-th chiller is specifically: Among them, t w,c,E,i represents the temperature of chilled water entering the condenser of the i-th chiller, Q c,i represents the condensation heat of the i-th chiller, G w,c,i represents the cooling water flow rate of the condenser of the i-th chiller, K c,i represents the heat transfer coefficient of the condenser of the i-th chiller, A c,i represents the heat exchange area of ​​the condenser of the i-th chiller; The cooling capacity of the i-th chiller and the condensation heat of the i-th chiller are specifically: Q e,i =c w G w,e,i (t w,e,E,i -t w,e,L,i )i∈[1,N chiller ] Q c,i =c w G w,c,i (t w,c,L,i -t w,c,E,i )i∈[1,N chiller ] Q c =P chiller +Q e Among them, t w,e,L,i represents the chilled water outlet temperature of the evaporator of the i-th chiller, t w,c,L,i represents the cooling water outlet temperature of the condenser of the i-th chiller, Q c Represents the total condensation heat of the condenser, P chiller Indicates the input power of the chiller, Q e Indicates the total cooling capacity of the evaporator; Among them, the energy consumption of the water pump is specifically: Among them, P pump represents the energy consumption of the water pump, β i represents the i-th fitting coefficient of the water pump equipment model, i=1,2,3, G w Indicates the water flow rate of the cooling water pump; The energy consumption of the fan is specifically: Among them, P fan represents the energy consumption of the fan, χ f represents the fth fitting coefficient of the fan equipment model, f=1,2,3, G a Indicates the air flow rate of the cooling tower; S3: Determine the objective function and constraint conditions of the comprehensive energy consumption model; The objective function is specifically: Where F() is the total energy consumption function of the district cooling system, w represents water, e represents evaporator, L represents leaving a certain device, a represents air, CLWP represents cooling water pump, CHWP represents primary side chilled water pump, SCHWP represents secondary side chilled water pump, t w,e,L Indicates the water temperature leaving the chiller evaporator, G w,CLWP Indicates the water flow rate of the cooling water pump, G w,CHWP Indicates the water flow rate of the primary side chilled water pump and cooling water pump, G w,SCHWP Indicates the water flow of the two-side chilled water pump and cooling water pump, G a Indicates the air flow rate of the cooling tower, N chiller Indicates the number of chillers, P chiller,i represents the energy consumption of the i-th chiller, N CLWP Indicates the number of cooling water pumps, P CLWP,j represents the energy consumption of the jth cooling water pump, N CHWP Indicates the number of primary side chilled water pumps, P CHWP,k represents the energy consumption of the kth primary side chilled water pump, N SCHWP Indicates the number of secondary side chilled water pumps, P SCHWP,m represents the energy consumption of the mth secondary side chilled water pump, N tower Indicates the number of cooling towers, P tower,n represents the energy consumption of the nth cooling tower; The constraints are: t w,e,L,i,min ≤t w,e,L,i ≤t w,e,L,i,max i∈[1,N chiller ] G w,CLWP,j,min ≤G w,CLWP,j ≤G w,CLWP,j,max j∈[1,N CLWP ] G w,CHWP,k,min ≤G w,CHWP,k ≤G w,CHWP,k,max k∈[1,N CHWP ] G w,SCHWP,m,min ≤G w,SCHWP,m ≤G w,SCHWP,m,max m∈[1,N SCHWP ] G a,n,min ≤G a,n ≤G a,n,max n∈[1,N tower ] Among them, t w,e,L,i represents the chilled water temperature leaving the evaporator of the i-th chiller, t w,e,L,i,min represents the lower limit of the chilled water temperature leaving the evaporator of the i-th chiller, t w,e,L,i,min represents the upper limit of the chilled water temperature leaving the evaporator of the i-th chiller, G w,CLWP,j represents the water flow rate of the jth cooling water pump, G w,CLWP,j,min represents the lower limit of the water flow rate of the jth cooling water pump, G w,CLWP,j,max represents the upper limit of the water flow rate of the jth cooling water pump, G w,CHWP,k represents the water flow rate of the kth primary side chilled water pump, G w,CHWP,k,min represents the lower limit of the water flow rate of the kth primary side chilled water pump, G w,CHWP,k,max represents the upper limit of the water flow rate of the kth secondary chilled water pump, G w,SCHWP,m represents the water flow rate of the mth secondary side chilled water pump, G w,SCHWP,m,min represents the lower limit of the water flow rate of the mth secondary side chilled water pump, G w,SCHWP,m,max represents the lower limit of the water flow rate of the mth secondary side chilled water pump, G a,n represents the air flow rate of the nth cooling tower, G a,n,min represents the lower limit of the air flow rate of the nth cooling tower, G a,n,max represents the upper limit of the air flow rate of the nth cooling tower, COP i represents the performance coefficient of the i-th chiller, t e,i represents the evaporation temperature of the i-th chiller, t c,i represents the condensing temperature of the i-th chiller, r i represents the partial load rate of the i-th chiller, Q e,demand Total cooling load represented by; S4: Under the constraints of the constraints, with the minimum function value of the objective function value as the goal, the control parameters of the comprehensive energy consumption model are optimized by using the tribal intelligent evolutionary algorithm, and the optimal control parameters are output; Wherein, the S4 specifically includes: S401: Using the objective function as the fitness function of the tribal intelligent evolutionary algorithm; S402: Initialize the population and Q table, the population includes multiple individuals, each individual represents a set of feasible control parameter solutions; S403: Determine individual parameters by the following formula X k =lb k +rand U(0,1) ·(ub k -lb k ) Where X represents, t w,e,L Indicates the water temperature leaving the chiller evaporator, G w,CLWP Indicates the water flow rate of the cooling water pump, G w,SCHWP represents the water flow of the two-side chilled water pump and cooling water pump, k represents the serial number of the parameter dimension, lb represents the upper limit of the set parameter, ub represents the lower limit of the set parameter, rand U(0,1) Represents a random number that follows a uniform distribution in the interval [0,1]; S404: Using the classification mechanism to classify each individual to form multiple tribes; S405: Calculate the fitness value of each individual in each tribe, and select the individual with the lowest fitness value as the leader: minf i,j =f(X i,j,1 ,X i,j,2 ,···,X i,j,k ,···,X i,j,K ) Among them, i represents the serial number of the tribe, j represents the serial number of the individual in the tribe, and f ij represents the fitness value of the jth individual in the i-th tribe, X i,j,k represents the k-th dimension parameter of the j-th individual in the i-th tribe, 1≤i≤n, 2≤n≤N, 1≤j≤m i , 1≤k≤K, n represents the number of tribes formed by the current classification, N is the maximum number of tribes that the algorithm can form, and m i is the total number of individuals in the i-th tribe, K is the number of dimensions of individual parameters; S406: Determine whether the minimum fitness value of each tribe is less than the average fitness value of the existing tribes; if so, the tribe is evaluated as a strong tribe; otherwise, the tribe is evaluated as a weak tribe; S407: Use the following formula to adjust the individual parameters of each strong tribe autonomously, and adjust the individual parameters of each weak tribe diplomatically or through war; The calculation formula for autonomous adjustment is: σ=|X i,leader,k -X i,j,k +e| Among them, X i,leader,k represents the k-th dimension parameter of the i-th tribe leader, σ represents the variance, X i,j,k ~N(X i,leader,k ,σ 2 ) indicates that the k-th dimension parameter of the j-th individual of the i-th tribe follows the parameter of the corresponding tribe leader as the mean σ 2 is the normal distribution of variance, ε represents a constant; The diplomatic adjustment is calculated as: Among them, rand N(0,1) represents a random number in the interval [0,1], X dip,leader,k represents the parameter of the leader of the Ministry of Foreign Affairs, d represents the Euclidean distance; The calculation formula for war adjustment is: X lose,captive,k ~N(X win,leader,k ,s 2 ) σ=|X win,leader,k -X lose,leader,k +e| Among them, X lose,captive,k represents the individual parameter of the plundered individual, X win,leader,k represents the parameter for defeating the leader of a tribe, and ε represents a constant; S408: When the tribe performs an action of autonomy or diplomacy, the reward value of the tribe’s first tribal action is determined by the following formula: Among them, R i Indicates that r ij represents the reward value of the jth individual in the i-th tribe, m i is the total number of individuals in the ith tribe; S409: When the action performed by each tribe is war, the second tribe action reward value of each tribe is determined by the following formula: Among them, S i Indicates the status of the i-th tribe, Strong tribe indicates a strong tribe, and Weak tribe indicates a weak tribe; S410: According to the first tribe action reward value and the second tribe action reward value, update the Q table by the following formula: Among them, Q′(s i ,a i ) represents the updated Q value under the current state and action, Q(s i ,a i ) represents the Q value before update under the current state and action, λ represents the learning rate, γ represents the discount factor, Indicates the action with the largest Q value in the state after executing the action; S411: According to the Q table, using the accumulated reward value data, guiding the update of each individual in the existing tribe; S412: based on the updated individual information, re-determine the leaders of each tribe, compare the fitness values ​​of the leaders of each tribe, and select the leader with the lowest fitness value as the best leader; S413: Determine whether the number of iterations reaches the maximum number of iterations or whether the convergence accuracy reaches the preset convergence accuracy. If so, output the parameter solution represented by the best leader as the best control parameter; otherwise, proceed to the next step; S414: Determine whether there is only one tribe; if so, proceed to 404; otherwise proceed to S407 and use the objective function as the fitness function of the tribal intelligent evolution algorithm; S5: Performing energy-saving optimization control on the regional cooling system according to the optimal control parameters.

2. An energy-saving optimization control system for a regional cooling system based on a tribal intelligent evolutionary algorithm, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the energy-saving optimization control method for a regional cooling system based on a tribal intelligent evolutionary algorithm as claimed in claim 1 is implemented.

Images