An IoT-based building air-conditioning energy-saving control method and system

Abstract

The present invention discloses a building air-conditioning energy-saving control method and system based on the Internet of Things. The method includes: taking the combination of control parameters of the air-conditioning system as optimization variables and the operation strategy of the air-conditioning system as particles, establishing a population and initializing the position and velocity of each particle; iteratively performing the following operations until the stop condition is satisfied, and outputting the optimal solution that satisfies the constraint conditions of the total energy consumption model: calculating the fitness value of each particle in the population; according to the calculation result of the fitness value, selecting a preset number of particles as relatively excellent particles; performing neighborhood search on the remaining particles except the relatively excellent particles and updating their positions to make them satisfy the normal distribution, and at the same time, the relatively excellent particles update their own positions by means of random search; this method simultaneously adopts the neighborhood search and random search methods, and iteratively obtains the optimal control parameters of the building air-conditioning system according to the particle swarm algorithm, and the obtained result is more accurate and reasonable, and has a good energy-saving effect.

Description

Technical Field

[0001] The present invention relates to the technical field of building air-conditioning control, and particularly to an energy-saving control method and system for building air-conditioning based on the Internet of Things. Background Art

[0002] In traditional intelligent buildings, there is no specific control method for daily power energy consumption. Only the daily and monthly electricity consumption quantities and consumption analysis trends in the building are statistically analyzed through a monitoring system, and clear and accurate energy consumption data are provided to users through a monitoring and management platform. At the same time, the data collection method of the monitoring system for electricity consumption is relatively simple. The electricity consumption of the terminal is collected by means of terminal meter reading, terminal photo transmission, or the terminal meter reading terminal is embedded with a 2G / 4G card to transmit data. These terminals for collecting data are relatively traditional in terms of power consumption, device volume, data transmission networking method, etc., and need to frequently replace batteries and ensure good network signals. At the same time, this building power energy control method is relatively simple, the control of multiple devices is not reasonable enough, and it is still easy to cause waste of electric energy, especially the waste of electric energy of devices with large power consumption in the building, such as the air-conditioning system in the building.

[0003] For the air-conditioning system in a building, the patent document CN107270497A discloses a central air-conditioning control system for a building, including a central air-conditioning outdoor unit, a central air-conditioning indoor unit, a monitoring terminal, a microprocessor, and a signal collection terminal. The monitoring terminal is electrically connected to the central air-conditioning outdoor unit, the central air-conditioning indoor unit, and the signal collection terminal through wires respectively. The input end of the microprocessor is electrically connected to the output end of the signal collection terminal through a wire, and the control output end of the microprocessor is electrically connected to the electric control end of the central air-conditioning indoor unit. The signal collection terminal is used to collect temperature and humidity information and personnel information in the area. This solution uses a computer as the monitoring terminal to monitor the working status of each central air-conditioning outdoor unit and central air-conditioning indoor unit in real time, and stores the working records through a server, supervises each central air-conditioning outdoor unit or central air-conditioning indoor unit, and timely shuts down the current central air-conditioning indoor unit when there is no one in the building, which is beneficial to energy conservation and emission reduction.

[0004] However, in the above solution, only the air-conditioning switch control in the building is carried out based on real-time data collection and simple analysis, and the specific parameters of the working air-conditioning are not controlled, so the energy-saving effect is not good enough. Summary of the Invention

[0005] The present invention provides an energy-saving control method and system for building air-conditioning based on the Internet of Things. By iteratively obtaining the optimal control parameters of the building air-conditioning system according to the particle swarm algorithm, the obtained results are more accurate and reasonable, and the energy-saving effect is good.

[0006] An energy-saving control method for building air-conditioning based on the Internet of Things includes:

[0007] Establish a communication connection between the air conditioning system in the building and the Internet of Things platform;

[0008] The Internet of Things platform establishes a total energy consumption model of the air conditioning system;

[0009] Taking the combination of control parameters of the air conditioning system as the optimization variables and the operation strategy of the air conditioning system as the particles, establish a population and initialize the position and velocity of each particle;

[0010] Iteratively execute the following operations until the stop condition is met, and output the optimal solution that satisfies the constraint conditions of the total energy consumption model:

[0011] Calculate the fitness value of each particle in the population;

[0012] According to the calculation result of the fitness value, select a preset number of particles as the relatively excellent particles;

[0013] Perform neighborhood search on the remaining particles except the relatively excellent particles and update their positions to make them satisfy the normal distribution. At the same time, the relatively excellent particles update their own positions through random search.

[0014] Furthermore, the total energy consumption of the air conditioning system includes the energy consumption of the chiller, the cooling water pump, and the fan.

[0015] Furthermore, the total energy consumption model is as follows:

[0016] min(P total )

[0017] ;

[0018] ;

[0019] ;

[0020] ;

[0021] ;

[0022] Among them, P total is the total energy consumption of the air conditioning system, N represents the number of chillers, P cold,i represents the energy consumption of the i-th chiller, M represents the number of cooling water pumps, P water,j represents the energy consumption of the j-th cooling water pump, Q represents the number of fans, P wind,k represents the energy consumption of the k-th fan, P cold represents the energy consumption of the chiller, a1, a2, a3, a4 represent the performance coefficients of the chiller, PLR represents the load ratio of the chiller, PLR iDenotes the load rate of the $i$-th refrigeration host, $RC$ i Denotes the rated refrigerating capacity of the $i$-th refrigeration host, $CL$ denotes the load demand at the end of the air-conditioning system, $P$ water Denotes the energy consumption of the cooling water pump, $b1$, $b2$, $b3$ denote the fitting coefficients of the cooling water pump, $v$ denotes the cooling water flow rate of the cooling water pump, $P$ wind Denotes the energy consumption of the fan, $c1$, $c2$, $c3$, $c4$ denote the fitting coefficients of the fan, $FR$ denotes the air flow rate, which is the ratio of the air flow to the rated air flow, $P$ e Denotes the rated power of the fan.

[0023] Furthermore, the control parameters include the load rate of the refrigeration host, the cooling water flow rate of the cooling water pump, and the air flow rate.

[0024] Furthermore, the fitness value of each particle is calculated by the following formula:

[0025] ;

[0026] where $F$ is the fitness, $P$ total is the total energy consumption of the air-conditioning system, $C$ is the upper limit value of the air-conditioning system energy consumption, $Z$ is the penalty factor, $PLR$ i denotes the load rate of the $i$-th refrigeration host, $RC$ i denotes the rated refrigerating capacity of the $i$-th refrigeration host, $CL$ denotes the load demand at the end of the air-conditioning system, $N$ denotes the number of refrigeration hosts.

[0027] Furthermore, according to the calculation result of the fitness value, a preset number of particles are selected as superior particles, including:

[0028] Sort the fitness values of each particle in descending order, and select the particles with the top one-half of the fitness values as superior particles.

[0029] Furthermore, perform neighborhood search on the remaining particles except the superior particles and update their positions to make them satisfy the normal distribution, including:

[0030] According to the total energy consumption model, calculate the total energy consumption value corresponding to the remaining particles at the current position;

[0031] According to the total energy consumption value corresponding to the remaining particles at the current position, calculate its mean and variance;

[0032] Perform neighborhood search on the remaining particles, use the total energy consumption value of the remaining particles as a random variable, and update the particle positions to make them satisfy the normal distribution.

[0033] Furthermore, the mean and variance are calculated by the following formula:

[0034] ;

[0035] ;

[0036] where μ is the mean value, K represents the total number of remaining particles, (P total ) q is the total energy consumption value of the air-conditioning system at the current position of the q-th particle, is the variance.

[0037] An energy-saving control system for building air-conditioning based on the Internet of Things includes an Internet of Things platform and an air-conditioning system. The Internet of Things platform includes a processor and a storage device. The storage device stores multiple instructions, and the processor is configured to read the instructions and execute the above method.

[0038] Further, the air-conditioning system includes a plurality of refrigeration hosts, cooling water pumps and fans.

[0039] The energy-saving control method and system for building air-conditioning provided by the present invention at least include the following beneficial effects:

[0040] (1) By establishing a total energy consumption model to analyze the power consumption of the air-conditioning, and at the same time adopting the methods of neighborhood search and random search, iterating the energy consumption model according to the particle swarm algorithm, updating the positions of some particles to meet the normal distribution requirements, obtaining the optimal control parameters of the building air-conditioning system, the obtained results are more accurate and reasonable, and the energy-saving effect of the building air-conditioning system is good.

[0041] (2) By establishing a total energy consumption model and setting control parameters through the parameters of the refrigeration host, cooling water pump and fan, the parameters involve multiple energy-consuming components of the air-conditioning, and the factors are comprehensively considered. Based on this, the optimal solution of the air-conditioning system control method obtained by solving is more accurate, further improving the energy-saving effect.

[0042] (3) When calculating the fitness value, a penalty factor is used to adjust the fitness value of the particles that do not meet the constraint conditions. By using this fitness value calculation method, a more accurate evaluation of the quality of the particles is realized, providing a basis for a more reasonable and accurate classification of the quality of the particles in the next step.

[0043] (4) When performing iterative solution using the particle swarm algorithm, the obtained particles are sorted according to the fitness value and then classified as good or bad. For the better particles, the random search algorithm of the particle swarm algorithm itself is used for iteration, saving computing power, while for the other part of the particles, the domain search algorithm is used for iteration to meet the normal distribution requirements, improving the accuracy of solving the optimal solution. The optimized particle swarm algorithm takes into account both the accuracy and efficiency of the solution, achieving a good building air-conditioning control effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 Flow chart of an embodiment of the building air - conditioning energy - saving control method based on the Internet of Things provided by the present invention.

[0045] Figure 2 Flow chart of an embodiment of the method for updating remaining particles in the building air - conditioning energy - saving control method based on the Internet of Things provided by the present invention.

[0046] Figure 3 Schematic structural diagram of an embodiment of the building air - conditioning energy - saving control device based on the Internet of Things provided by the present invention.

[0047] Figure 4 Schematic structural diagram of an embodiment of the building air - conditioning energy - saving control system based on the Internet of Things provided by the present invention.

[0048] Reference numerals: 100 - air - conditioning system, 101 - refrigeration host, 102 - cooling water pump, 103 - fan, 200 - Internet of Things platform, 2001 - communication establishment module, 2002 - model establishment module, 2003 - initialization module, 2004 - calculation module, 201 - processor, 202 - storage device. Detailed implementation manners

[0049] In order to better understand the above - mentioned technical solution, the above - mentioned technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0050] Reference Figure 1 , in some embodiments, a building air - conditioning energy - saving control method based on the Internet of Things is provided, including:

[0051] S1. Establish a communication connection between the air - conditioning system in the building and the Internet of Things platform;

[0052] S2. The Internet of Things platform establishes a total energy consumption model of the air - conditioning system;

[0053] S3. Use the control parameter combination of the air - conditioning system as the optimization variable, and use the operation strategy of the air - conditioning system as the particle, establish a population and initialize the position and velocity of each particle;

[0054] S4. Iteratively execute the following operations until the stop condition is met, and output the optimal solution that satisfies the constraint conditions of the total energy consumption model:

[0055] S41. Calculate the fitness value of each particle in the population;

[0056] S42. According to the calculation result of the fitness value, select a preset number of particles as relatively good particles;

[0057] S43. Perform neighborhood search on the remaining particles except the relatively optimal particles and update their positions to satisfy the normal distribution. Meanwhile, the relatively optimal particles update their own positions through random search.

[0058] Specifically, the total energy consumption of the air conditioning system includes the energy consumption of the chiller, the energy consumption of the cooling water pump, and the energy consumption of the fan.

[0059] In step S2, the total energy consumption model is as follows:

[0060] min(P total )

[0061] ;

[0062] ;

[0063] ;

[0064] ;

[0065] )

[0066] where P total is the total energy consumption of the air conditioning system, N represents the number of chillers, P cold,i represents the energy consumption of the i-th chiller, M represents the number of cooling water pumps, P water,j represents the energy consumption of the j-th cooling water pump, Q represents the number of fans, P wind,k represents the energy consumption of the k-th fan, P cold represents the energy consumption of the chiller, a1, a2, a3, a4 represent the performance coefficients of the chiller, PLR represents the load ratio of the chiller, PLR i represents the load ratio of the i-th chiller, RC i represents the rated cooling capacity of the i-th chiller, CL represents the load demand at the end of the air conditioning system, P water represents the energy consumption of the cooling water pump, b1, b2, b3 represent the fitting coefficients of the cooling water pump, v represents the cooling water flow rate of the cooling water pump, P wind represents the energy consumption of the fan, c1, c2, c3, c4 represent the fitting coefficients of the fan, FR represents the air flow rate, which is the ratio of the air flow to the rated air flow, P e represents the rated power of the fan.

[0067] The performance coefficients a1, a2, a3, a4 of the chiller, the fitting coefficients b1, b2, b3 of the cooling water pump, and the fitting coefficients c1, c2, c3, c4 of the fan can be calculated by simulating the energy consumption of the air conditioner under different working conditions through relevant simulation software.

[0068] As a preferred implementation, the load ratio PLR of each chiller should be not less than 0.3. Therefore, PLRi satisfies the constraint condition: 0.3 ≤ PLRi ≤ 1 or PLRi = 0.

[0069] In step S3, the control parameters include the load ratio of the refrigeration host, the cooling water flow rate of the cooling water pump, and the air flow rate.

[0070] In step S4, the control parameters of the air-conditioning system related to each particle are represented by the particle position, the change range of each parameter is represented by the particle velocity, and the stop condition is that the number of iterative executions reaches the preset maximum number.

[0071] In step S41, the fitness value of each particle is calculated by the following formula:

[0072] ;

[0073] where F is the fitness, P total is the total energy consumption of the air-conditioning system, C is the upper limit value of the air-conditioning system energy consumption, Z is the penalty factor, PLR i represents the load ratio of the i-th refrigeration host, RC i represents the rated refrigerating capacity of the i-th refrigeration host, CL represents the load demand at the end of the air-conditioning system, and N represents the number of refrigeration hosts.

[0074] In the above formula, the adaptation of the particle to the constraint conditions is used to evaluate the quality of the particle. According to whether each particle can well meet the constraint conditions, the fitness value is adjusted to evaluate the quality of the particle, so as to perform the next particle division. Specifically, if the particle obtains a good energy-saving result while meeting the constraint conditions, the particle will obtain a larger fitness value; correspondingly, if the particle cannot meet the constraint conditions, it means that the particle belongs to an infeasible solution, and a large penalty will be given to the particle in the fitness value calculation to reduce the fitness value of the particle. By using this fitness value calculation method, a more accurate evaluation of the quality of the particles is achieved, providing a basis for a more reasonable and accurate division of the quality of the particles in the next step.

[0075] Among them, the value range of the penalty factor Z is 1000 - 3000.

[0076] In step S42, according to the calculation result of the fitness value, a preset number of particles are selected as superior particles, including:

[0077] Sort the fitness values of each particle in descending order, and select the particles with the top one-half of the fitness values as superior particles.

[0078] The particles are sorted and divided according to their fitness values. In further calculations, the random search algorithm is executed on the better particles, saving computing power, and the neighborhood optimization algorithm is executed on the worse particles, improving accuracy. By taking both accuracy and efficiency into account, a better building air-conditioning control effect is achieved.

[0079] Further, the better particles perform random search through the following formula to obtain a new solution and replace the old solution:

[0080] ;

[0081] where, x ij (t + 1) is the position of the i-th particle at the (t + 1)-th moment in the j-th dimension, x j,max and x j,min respectively represent the maximum and minimum values in the j-th dimension among the better particles, rand is a random number between 0 and 1, x ij (t) is the position of the i-th particle at the t-th moment in the j-th dimension, P(x ij (t + 1)) represents the total energy consumption value corresponding to the position x ij (t + 1), and P(x ij (t)) represents the total energy consumption value corresponding to the position x ij (t).

[0082] Reference Figure 2 , in step S43, neighborhood search is performed on the remaining particles except the better particles and their positions are updated to satisfy the normal distribution, including:

[0083] S431. According to the total energy consumption model, calculate the total energy consumption value corresponding to the remaining particles at the current position;

[0084] S432. According to the total energy consumption value corresponding to the remaining particles at the current position, calculate its mean and variance;

[0085] S433. Perform neighborhood search on the remaining particles, using the total energy consumption value of the remaining particles as a random variable, and update the particle positions to satisfy the normal distribution.

[0086] As a preferred implementation manner, the air-conditioning control method provided in this embodiment can be controlled by multiple computing units to establish a swarm intelligence Internet of Things platform. The algorithms in each computing unit are standardized, so they have good portability, and the air-conditioning control deployment is carried out by means of multiple downloads. Compared with the flat centralized control method, the swarm intelligence Internet of Things platform has higher efficiency, higher algorithm reuse rate, and better control effect.

[0087] Correspondingly, for the remaining particles other than the superior particles, each calculation unit generates multiple new particles that follow a normal distribution model according to the mean and variance of the samples that satisfy the normal distribution obtained after neighborhood search, and forms an overall with the particles formed after random search of the multiple superior particles of the previous generation obtained in step S42. Then, the fitness values of the above particles are evaluated, and a preset number of superior individuals are selected as the particles for the next iteration. After multiple iterative calculations of the above steps, the distribution of the generated new particles will be closer to the optimal solution of the current air-conditioning control parameters than the distribution of the original particles.

[0088] In step S432, the mean and variance are calculated by the following formula:

[0089] ;

[0090] ;

[0091] where μ is the mean, K represents the total number of remaining particles, (P total ) q is the total energy consumption value of the air-conditioning system at the current position of the qth particle, is the variance.

[0092] Furthermore, in step S433, when the remaining particles perform neighborhood search, it is necessary to determine its search radius. In order to make the algorithm converge quickly, the fitness value is also taken into account when determining the search radius, that is, the search radius of the particle with a smaller fitness value is increased; the search radius of the particle with a larger fitness value is decreased. The search radius is determined by the following formula:

[0093] ;

[0094] ;

[0095] where R is the search radius, K is the search step, F is the fitness value, X j,max and X j,min respectively represent the maximum and minimum values in the jth dimension among the remaining particles.

[0096] At the initial stage of the algorithm execution, a larger K value is required to expand the search range; while at the later stage of the algorithm execution, a smaller K value is required to achieve fine-grained search within a smaller range near the optimal solution. Therefore, the size of the K value is determined according to the real-time state information of the remaining particles during the change process.

[0097] Refer to Figure 3 , in some embodiments, a building air-conditioning energy-saving control device based on the Internet of Things is provided, including:

[0098] A communication establishment module 2001, configured to establish a communication connection between the air conditioning system in the building and the Internet of Things platform;

[0099] A model establishment module 2002, configured to establish a total energy consumption model of the air conditioning system on the Internet of Things platform;

[0100] An initialization module 2003, configured to use the control parameter combinations of the air conditioning system as optimization variables, use the operation strategy of the air conditioning system as particles, establish a population, and initialize the positions and velocities of each particle;

[0101] A calculation module 2004, configured to iteratively perform the following operations until a stop condition is met, and output an optimal solution that satisfies the constraint conditions of the total energy consumption model:

[0102] Calculate the fitness value of each particle in the population;

[0103] According to the calculation result of the fitness value, select a preset number of particles as superior particles;

[0104] Perform a neighborhood search on the remaining particles except the superior particles and update their positions to make them satisfy the normal distribution, while the superior particles update their own positions through random search.

[0105] Specifically, in the model establishment module 2002, the total energy consumption of the air conditioning system includes the energy consumption of the chiller, the energy consumption of the cooling water pump, and the energy consumption of the fan.

[0106] The total energy consumption model is as follows:

[0107] min(P total )

[0108] ;

[0109] ;

[0110] ;

[0111] ;

[0112] )

[0113] Wherein, P total is the total energy consumption of the air conditioning system, N represents the number of chillers, P cold,i represents the energy consumption of the i-th chiller, M represents the number of cooling water pumps, P water,j represents the energy consumption of the j-th cooling water pump, Q represents the number of fans, P wind,k represents the energy consumption of the k-th fan, P coldIndicates the energy consumption of the refrigeration host. a1, a2, a3, and a4 represent the coefficient of performance of the refrigeration host. PLR represents the load ratio of the refrigeration host, PLR i Indicates the load ratio of the i-th refrigeration host, RC i Indicates the rated refrigerating capacity of the i-th refrigeration host. CL represents the load demand at the end of the air-conditioning system, P water Indicates the energy consumption of the cooling water pump. b1, b2, and b3 represent the fitting coefficients of the cooling water pump. v represents the cooling water flow rate of the cooling water pump, P wind Indicates the energy consumption of the fan. c1, c2, c3, and c4 represent the fitting coefficients of the fan. FR represents the air flow rate, which is the ratio of the air flow to the rated air flow, P e Indicates the rated power of the fan.

[0114] In the initialization module 2003, the control parameters include the load ratio of the refrigeration host, the cooling water flow rate of the cooling water pump, and the air flow rate.

[0115] In the calculation module 2004, the fitness value of each particle is calculated by the following formula:

[0116] ;

[0117] Where F is the fitness, P total is the total energy consumption of the air-conditioning system, C is the upper limit value of the air-conditioning system energy consumption, Z is the penalty factor, PLR i Indicates the load ratio of the i-th refrigeration host, RC i Indicates the rated refrigerating capacity of the i-th refrigeration host. CL represents the load demand at the end of the air-conditioning system, and N represents the number of refrigeration hosts.

[0118] The calculation module 2004 is also used to select a preset number of particles as superior particles according to the calculation result of the fitness value, including:

[0119] Sort the fitness values of each particle in descending order, and select the particles with the top one-half of the fitness values as superior particles.

[0120] The calculation module 2004 is also used to perform neighborhood search on the remaining particles except the superior particles and update their positions to make them satisfy the normal distribution, including:

[0121] According to the total energy consumption model, calculate the total energy consumption value corresponding to the remaining particles at the current position;

[0122] According to the total energy consumption value corresponding to the remaining particles at the current position, calculate its mean and variance;

[0123] The remaining particles perform neighborhood search, using the total energy consumption value of the remaining particles as a random variable, and updating the particle positions to satisfy the normal distribution.

[0124] Among them, the mean and variance are calculated by the following formulas:

[0125] ;

[0126] ;

[0127] Among them, μ is the mean, K represents the total number of remaining particles, (P total ) q is the total energy consumption value of the air-conditioning system at the current position of the qth particle, is the variance.

[0128] Reference Figure 4 , in some embodiments, a building air-conditioning energy-saving control system based on the Internet of Things is provided, including an Internet of Things platform 200 and an air-conditioning system 100. The Internet of Things platform 200 includes a processor 201 and a storage device 202. The storage device 202 stores multiple instructions, and the processor 201 is configured to read the instructions and execute the above method.

[0129] Among them, the air-conditioning system 100 includes a plurality of refrigeration hosts 101, cooling water pumps 102, and fans 103.

[0130] The building air-conditioning energy-saving control method and system based on the Internet of Things provided in this embodiment analyze the power consumption of air conditioners by establishing a total energy consumption model, and at the same time adopt the methods of neighborhood search and random search. According to the particle swarm algorithm, the energy consumption model is iterated to update the positions of some particles to meet the requirements of normal distribution, and the optimal control parameters of the building air-conditioning system are obtained. The results obtained are more accurate and reasonable, and the energy-saving effect of the building air-conditioning system is good; the total energy consumption model is established based on the parameters of the chiller, cooling water pump and fan, and the control parameters are set. The parameters involve multiple energy-consuming components of the air conditioner, and all factors are comprehensively considered. Based on this, the optimal solution of the air-conditioning system control method obtained by solving is more accurate, further improving the energy-saving effect; when calculating the fitness value, a penalty factor is used to adjust the fitness value of the particles that do not meet the constraint conditions. Using this fitness value calculation method, a more accurate evaluation of the quality of particles is realized, providing a basis for more reasonable and accurate classification of the quality of particles in the next step; when performing iterative solution using the particle swarm algorithm, the obtained particles are sorted according to the fitness value and then classified as good or bad. The better particles are iterated using the random search algorithm of the particle swarm algorithm itself, saving computing power, while the other part of the particles uses the domain search algorithm to iterate to meet the requirements of normal distribution, improving the accuracy of solving the optimal solution. The optimized particle swarm algorithm takes into account both the accuracy and efficiency of the solution, achieving a good building air-conditioning control effect.

[0131] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention. Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An energy-saving control method for building air conditioning based on the Internet of Things, characterized in that, Including: Establish a communication connection between the air conditioning system in the building and the Internet of Things platform; The Internet of Things platform establishes a total energy consumption model of the air conditioning system; Taking the control parameter combination of the air conditioning system as the optimization variable and the operation strategy of the air conditioning system as the particle, establish a population and initialize the position and velocity of each particle; Iteratively execute the following operations until the stop condition is met, and output the optimal solution that satisfies the constraint conditions of the total energy consumption model: Calculate the fitness value of each particle in the population; According to the calculation result of the fitness value, select a preset number of particles as the better particles; Perform neighborhood search on the remaining particles except the better particles and update their positions to make them satisfy the normal distribution. At the same time, the better particles update their own positions through random search; Perform neighborhood search on the remaining particles except the better particles and update their positions to make them satisfy the normal distribution, including: According to the total energy consumption model, calculate the total energy consumption value corresponding to the remaining particles at the current position; Calculate its mean and variance according to the total energy consumption value corresponding to the remaining particles at the current position; The remaining particles perform neighborhood search, taking the total energy consumption value of the remaining particles as a random variable, and update the particle positions to make them satisfy the normal distribution; The search radius of the remaining particles for neighborhood search is determined by the following formula: R = K×(1 - F); Wherein, R is the search radius, K is the search step size, F is the fitness value, X j,max and X j,min respectively represent the maximum and minimum values in the j-th dimension among the remaining particles; The control parameters include the load rate of the chiller, the cooling water flow rate of the cooling water pump, and the air flow rate; The fitness value of each particle is calculated by the following formula: Among them, F is the fitness, P total is the total energy consumption of the air conditioning system, C is the upper limit value of the air conditioning system energy consumption, Z is the penalty factor, PLR i represents the load ratio of the i-th chiller, RC i represents the rated cooling capacity of the i-th chiller, CL represents the load demand at the end of the air conditioning system, and N represents the number of chillers.

2. The method according to claim 1, wherein The total energy consumption of the air conditioning system includes chiller energy consumption, cooling water pump energy consumption, and fan energy consumption.

3. The method according to claim 1 or 2, characterized in that, The total energy consumption model is as follows: min(P total ) P cold = a1 + a2 × PLR + a3 × PLR 2 + a4 × PLR 3 ; P water = b1 + b2×v + b3×v 2 ; P wind = P e × (c1 + c2 × FR + c3 × FR 2 + c4 × FR 3 ); Among them, P total is the total energy consumption of the air-conditioning system, N represents the number of refrigeration hosts, and P cold,i represents the energy consumption of the i-th refrigeration host, M represents the number of cooling water pumps, and P water,j represents the energy consumption of the j-th cooling water pump, Q represents the number of fans, and P wind,k represents the energy consumption of the k-th fan, and P cold represents the energy consumption of the refrigeration host, a1, a2, a3, a4 represent the performance coefficients of the refrigeration host, PLR represents the load ratio of the refrigeration host, and PLR i represents the load ratio of the i-th refrigeration host, RC i represents the rated cooling capacity of the i-th refrigeration host, CL represents the load demand at the end of the air-conditioning system, and P water represents the energy consumption of the cooling water pump, b1, b2, b3 represent the fitting coefficients of the cooling water pump, v represents the cooling water flow rate of the cooling water pump, and P wind represents the energy consumption of the fan, c1, c2, c3, c4 represent the fitting coefficients of the fan, FR represents the air flow rate, which is the ratio of the air flow to the rated air flow, and P e represents the rated power of the fan.

4. The method according to claim 1, wherein According to the calculation result of the fitness value, select a preset number of particles as the better particles, including: Sort the fitness values of each particle in descending order, and select the particles with the top half of the fitness values as the better particles.

5. The method according to claim 1, characterized in that The mean and variance are calculated by the following formula: Among them, μ is the mean value, K represents the total number of remaining particles, and (P total ) q is the total energy consumption value of the air conditioning system at the current position of the q-th particle, and σ is the variance.

6. An energy-saving control system for building air conditioning based on the Internet of Things, characterized in that, Including an Internet of Things platform and an air conditioning system. The Internet of Things platform includes a processor and a storage device. The storage device stores multiple instructions, and the processor is used to read the instructions and execute the method according to any one of claims 1-5.

7. The system according to claim 6, wherein The air conditioning system includes multiple chillers, cooling water pumps, and fans.

Images