CN-120931432-B - Cold and heat source system energy-saving control method and system based on particle swarm nested decoupling

CN120931432BCN 120931432 BCN120931432 BCN 120931432BCN-120931432-B

Abstract

The invention discloses a particle swarm nested decoupling-based energy-saving control method and system for a cold and heat source system, which relate to the field of building energy conservation and solve the problem of difficult solution of coupling parameters of the cold and heat source system of a building, and are characterized in that an equipment swarm model of the cold and heat source system of the building is established, wherein the equipment swarm model comprises a water chilling unit, a ground source heat pump, a chilled water pump, a ground source circulating pump, a cooling tower model and a ground buried pipe; based on the equipment group model, mapping and matching the associated coupling variables with the same physical meaning among the equipment, establishing a cold and heat source system group model, wherein the system group model comprises a water chilling unit system and a ground source heat pump system, based on the cold and heat source system group model, adopting a particle group nested optimization algorithm to carry out system global control parameter optimization solution, outputting a system global control parameter optimal value, and achieving the purposes of realizing overall optimal energy-saving control of a cold and heat source system of a building and global collaborative optimization and accurate modeling of the cold and heat source system of the building.

Inventors

LI YUANFU
FAN XIANGCHEN
MENG FANBO
LIANG HUIYUAN
WANG GUORONG
CAO YONG
LI JIAJIE
ZHONG ANQI
CUI ZHIGUO
YU XIAOLONG
MAO XIAOFENG
WANG RUIQI
GONG WEISHUAI
TAO XIAOLONG
WANG ZHELONG
LI YANZHEN
LIANG YAJIE
WANG WEISHUAI
WANG HUALEI

Assignees

中国建筑科学研究院有限公司
国网山东省电力公司青岛供电公司
国网山东综合能源服务有限公司

Dates

Publication Date: 20260505
Application Date: 20251014

Claims (6)

1. The energy-saving control method for the cold and heat source system based on particle swarm nesting decoupling is characterized by comprising the following steps of: s1, building an equipment group model of a cold and heat source system of a building, wherein the equipment group model comprises a water chilling unit, a ground source heat pump, a chilled water pump, a ground source circulating pump, a cooling tower model and a ground buried pipe; S2, mapping and matching the associated coupling variables with the same physical meaning among the devices based on the device group model, and establishing a cold and heat source system group model, wherein the system group model comprises a water chilling unit system and a ground source heat pump system; s3, based on the cold and hot source system group model, adopting a particle group nested optimization algorithm to carry out system global control parameter optimization solution, and outputting a system global control parameter optimal value; In step S3, the particle swarm nested optimization algorithm includes an outer layer particle swarm optimization process and an inner layer particle swarm optimization process; the outer particle swarm optimization process is used for solving the optimal value of the system global control parameter which enables the total energy consumption of the system to be the lowest; The inner layer particle swarm optimization process is used for decoupling and solving the coupling variable in the system aiming at the control parameters given by the outer layer particle swarm; the outer particle swarm optimization process comprises the following steps: S3a, inputting system condition variables, initializing position vectors and speed vectors of outer particle swarms, and determining search ranges and boundary conditions of the position vectors; S3b, updating the speed vector and the position vector of the outer particle swarm; S3c, for each particle at the updated position, calling an inner layer particle swarm decoupling solving process, and solving system state parameters of each particle at the updated position of the outer layer particle swarm; S3d, calculating an objective function of the updated position of the outer layer particles by using the system state parameters output by the system group model and the inner layer particle swarm, and updating an individual extremum and a global optimal solution; S3e, repeating the steps S3b to S3d until a convergence condition is met or the maximum iteration number is reached, and outputting the global control parameter optimal value; The inner layer particle swarm optimization process comprises the following steps: S3c1, inputting the system condition variable and the position vector of the outer particle swarm, and initializing the position vector and the speed vector of the inner particle swarm, wherein the position vector of the inner particle swarm is a coupling parameter comprising condenser water inlet temperature and condenser water outlet temperature, ground source water outlet temperature and ground source water inlet temperature; S3c2, comparing the input position vector of the outer particle swarm with the optimal solution position of the outer particle in the last optimization step length to obtain a comparison result, inquiring a preset search space boundary adjustment rule based on the comparison result, determining a search direction adjustment strategy of the coupling parameters of the inner particle swarm, and adjusting the search space boundary of the position vector corresponding to the inner particle swarm according to the adjustment strategy; s3c3, performing inner layer particle swarm search, and updating the position vector and the speed vector of the inner layer particle swarm; s3c4, inputting the updated inner layer particle position vector into a mutually coupled equipment model, and performing cross prediction to obtain a cross prediction value; S3c5, establishing a decoupling solving and evaluating objective function, and solving each particle objective function of the inner layer particle swarm by utilizing the current position of the inner layer particles and the cross predicted value; s3c6, repeating the steps S3c3 to S3c5 until a convergence condition is met or the maximum iteration number is reached, and outputting the solved system state parameters; the preset search space boundary adjustment rule comprises the following steps: For the water chilling unit system, according to the change trend of the rotation speed ratio of the cooling water pump and the rotation speed ratio of the cooling tower fan, the searching direction of the inlet water temperature of the condenser and the outlet water temperature of the condenser is adjusted; for the ground source heat pump system, according to the change trend of the ground source circulating pump speed ratio, the searching direction of the ground source water outlet temperature is adjusted; the outer layer particle position vector comprises a rated rotation speed ratio of a chilled water pump or a load water pump, a rated rotation speed ratio of a cooling water pump or a ground source circulating pump, a rated rotation speed ratio of a cooling tower fan and a water outlet temperature set value of refrigeration or heating equipment, and the system condition variables comprise a unit load rate, a system load rate, an outdoor wet bulb temperature/ground source well soil temperature, the number of chilled water pumps or load water pumps and the number of cooling water pumps or ground source circulating pumps.
2. The energy-saving control method for the cold and heat source system based on particle swarm nesting decoupling according to claim 1, wherein the total energy consumption of the system is the sum of main equipment power of the cold and heat source system, and comprises main machine refrigerating power, main machine heating power, chilled water pump or load water pump power, cooling water pump or ground source circulating pump power and cooling tower power.
3. The energy-saving control method for the cold and heat source system based on particle swarm nested decoupling according to claim 1, wherein the calculation process of the decoupling solving and evaluating objective function is as follows: acquiring a current particle position value; Inputting the position value, the condition variable, the outer particle position and the control parameter into another equipment model coupled with the position value and the condition variable, and calculating the predicted value; Comparing the position value of the particle hypothesis with a predicted value obtained by cross prediction, and respectively calculating square deviation of the water chilling unit system and the ground source heat pump system; and adding square deviation of the water chilling unit system and the ground source heat pump system, and taking square root to obtain an objective function value of the particles.
4. The method for controlling energy conservation of a cold and heat source system based on particle swarm nesting decoupling according to claim 1, wherein the method for adjusting the search space boundary of the position vector corresponding to the inner layer particle swarm further comprises the following steps: Invoking a pre-trained reinforcement learning intelligent agent, forming a state characteristic vector by a comparison result of the position vector of the outer layer particle swarm and the optimal solution position in the last optimization step length, the current state of the inner layer particle swarm and the system condition variable together, and inputting the state characteristic vector to the reinforcement learning intelligent agent; Outputting a corresponding boundary adjustment action by the reinforcement learning agent according to the state feature vector; and dynamically adjusting the search space boundary of the inner particle swarm position vector according to the boundary adjusting action.
5. The energy-saving control method of a cold and heat source system based on particle swarm nesting decoupling according to claim 4, wherein said outputting, by said reinforcement learning agent, a corresponding boundary adjustment action according to said state feature vector, comprises the steps of: Performing multi-layer nonlinear transformation on the input state feature vector through a strategy network of the reinforcement learning agent, and outputting action probability distribution, wherein each action of the action probability distribution corresponds to a predefined atomic operation for translating or zooming a search space boundary; Selecting a final boundary adjustment action by sampling or selecting the maximum probability value according to the action probability distribution; executing the boundary adjustment action generates specific boundary adjustment instructions, which include the direction and magnitude of adjustment.
6. The energy-saving control system of the cold and heat source system based on particle swarm nested decoupling is characterized in that the system is used for realizing the energy-saving control method of the cold and heat source system based on particle swarm nested decoupling according to any one of claims 1-5, and comprises the following steps: The equipment group module is used for establishing an equipment group model of the cold and heat source system of the building, and the equipment group model comprises a water chilling unit, a ground source heat pump, a chilled water pump, a cooling water pump, a ground source circulating pump, a cooling tower model and a ground buried pipe; The system group module is used for mapping and matching the associated coupling variables with the same physical meaning among the devices based on the device group model, and establishing a cold and heat source system group model, wherein the system group model comprises a water chilling unit system and a ground source heat pump system; And the parameter analysis decision module is used for carrying out system global control parameter optimization solution by adopting a particle swarm nested optimization algorithm based on the cold and heat source system swarm model and outputting a system global control parameter optimal value.

Description

Cold and heat source system energy-saving control method and system based on particle swarm nested decoupling Technical Field The invention relates to the field of building energy conservation, in particular to a cold and heat source system energy conservation control method and system based on particle swarm nested decoupling. Background The building cold and heat source system is an important component of building energy consumption, the energy consumption can reach 40% of the total energy consumption of the building, the energy consumption of the building cold and heat source system is reduced, and the building cold and heat source system has important significance for energy conservation and carbon reduction in the building field. With the development of the internet of things, the control of a building cold and heat source system is gradually automated from the traditional manual operation and maintenance. The control equipment and the platform are often arranged in the public building, the control functions of remote start and stop, interlocking start and stop and the like are realized for the cold and heat source system of the building, and part of the control platform can realize energy conservation by adjusting the operation parameters of the system. However, the current parameter adjustment modes are mostly manually adjusted by operation and maintenance personnel according to self experience, the intelligent degree is low, scientificity is lacking, the optimal operation parameters of the system are difficult to determine according to actual demands, and a huge energy-saving space still exists in the system. In the prior art, an artificial intelligent optimization algorithm is gradually applied to control of a cold and heat source system of a building, such as heuristic algorithms of particle swarm and the like, and in an iterative process of solving an optimal control parameter value, a main equipment energy consumption calculation function is constructed as an optimization objective function, and an equipment energy consumption calculation model comprises control parameters and system state parameters. However, the building cold and heat source system has higher complexity and strong coupling, the system state parameters are related to the control parameters of each device, closed-loop correlation exists between the devices, and the parameters are input and output. In the current actual control process, all the devices are generally independently optimized, and the global optimal control of the system cannot be realized. Therefore, a method for solving the above technical problems is needed. Disclosure of Invention In order to solve the defects in the prior art, the invention aims to provide the energy-saving control method and the energy-saving control system for the cold and heat source system based on particle swarm nested decoupling, so as to achieve the effects of realizing overall optimal energy-saving control of the cold and heat source system of a building and overall collaborative optimization and precise modeling of the cold and heat source system of the building, and fundamentally solving the technical problems that each device is independently optimized and cannot be precisely modeled and collaborative controlled from the overall angle of the system in the traditional method. The technical aim of the invention is realized by the following technical scheme: In a first aspect, a method for controlling energy conservation of a cold and heat source system based on particle swarm nesting decoupling is provided, which comprises the following steps: s1, building an equipment group model of a cold and heat source system of a building, wherein the equipment group model comprises a water chilling unit, a ground source heat pump, a chilled water pump, a ground source circulating pump, a cooling tower model and a ground buried pipe; S2, mapping and matching the associated coupling variables with the same physical meaning among the devices based on the device group model, and establishing a cold and heat source system group model, wherein the system group model comprises a water chilling unit system and a ground source heat pump system; And S3, based on the cold and heat source system group model, adopting a particle group nested optimization algorithm to carry out system global control parameter optimization solution, and outputting a system global control parameter optimal value. Further, in step S3, the particle swarm nested optimization algorithm includes an outer particle swarm optimization process and an inner particle swarm optimization process; the outer particle swarm optimization process is used for solving the optimal value of the system global control parameter which enables the total energy consumption of the system to be the lowest; the inner layer particle swarm optimization process is used for decoupling and solving the coupling variable in the system aiming at the control paramete