Simulated annealing particle swarm based air-conditioning energy consumption model parameter identification method

Abstract

The invention provides a simulated annealing particle swarm based air-conditioning energy consumption model parameter identification method. The method includes: taking an energy consumption model function, created via a mechanism analysis method, of an entire air-conditioning system as an objective function, optimizing the objective function with a simulated annealing and particle swarm combined algorithm, and determining an optimal parameter combination under certain load. The concept of simulated annealing is introduced into the particle swarm algorithm, and parameters can be optimized and controlled in the process of particle evolution to be changed adaptively according to the algorithm, so that on the basis of existing advantages of the algorithm, global convergence of the algorithm is enhanced, convergence precision of the algorithm is improved, and the shortcoming that the convergence process stops easily and is trapped in local optimization easily is overcome.

Description

technical field [0001] The invention relates to a parameter identification method of an air-conditioning energy consumption model, which belongs to the field of energy-saving optimization of an air-conditioning system, and in particular relates to a parameter identification method of an air-conditioning energy consumption model based on simulated annealing particle swarm. Background technique [0002] With the development of the economy, my country's construction industry is developing rapidly, and the energy consumption of buildings is increasing, of which two-thirds of the energy consumption is consumed by the air conditioning system. Under the current situation that building energy consumption accounts for an increasing proportion of the entire energy consumption, the energy saving of air conditioning systems in buildings has become a focus and hot spot in the field of energy saving. According to the concept of terminal energy saving, increasing the energy saving of air c...

AI Technical Summary

Problems solved by technology

For example, in the document "Energy Saving Optimal Operation of Refrigeration System", the author obtained the functional relationship between the energy consumption of the air conditioning system and the main factors through the preliminary analysis of many factors of energy consumption of the refrigeration system, using orthogonal experiments and regression calculations, etc. The optimization calculation quickly finds the best operating parameters to guide the operation, so as to achieve the purpose of energy saving, but in the optimization process, the flow rate of chilled water and cooling water does not change, and it is only a regression optimization for individual air conditioning systems, which has no universal applicability

In the literature "Research on Optimum Control Strategies for Central Air-Conditioning Water System", the author used neural network to establish the energy consumption model of air-conditioning water system, and then used genetic algorithm to optimize the performance of the energy consumption model. However, the establishment of neural network requires a large amount of data. The lack of traffic data makes the accuracy of the established model not high; on the other hand, the accuracy of genetic algorithm optimization has a great influence on the initial value of the individual, and the convergence speed is slow

In the literature "Research on Optimum Design and Operation of Central Air Conditioning Water System", the author used the mechanism analysis method to establish the energy consumption function expression of each part of the air conditioning system, which has the advantages of high model accuracy and good versatility, but the sequence used for optimization The quadratic programming method needs to carry out Taylor expansion on the objective function, the implementation process is more complicated, and it cannot guarantee the positive definiteness of the demand matrix in the objective function

In the literature "Process Model Identification Based on Particle Swarm Optimization Algorithm", the author proposes a model parameter identification method based on particle swarm optimization algorithm. Each parameter of the process model is regarded as a particle in the particle swarm, and the particle swarm is used in the parameter identification method. The optimal parameter value of the process model is obtained by efficiently searching the space. Although the algorithm is simple and easy to implement, the parameter setting is small, and the convergence speed is fast, it also has low convergence accuracy and efficiency, and it is easy to stagnate and fall into the convergence process Disadvantages of local optima

[0004] In summary, there are mainly the above methods for the parameter optimization of the air conditioning energy consumption model, and the main disadvantages are: 1. The accuracy of the air conditioning system energy consumption model is not high, and the versatility is not good

2. The parameter optimization method of the air-conditioning energy consumption model is greatly affected by the initial value setting, the accuracy is not high, the convergence speed is slow, and the realization process is complicated, which is not conducive to the realization of the optimization algorithm

3. The particle swarm intelligent optimization algorithm adopted, although the algorithm is simple and easy to implement, the parameter setting is small, and the convergence speed is fast, but it also has low convergence accuracy and convergence efficiency, and it is easy to stagnate during the convergence process and easily fall into a local optimal solution Shortcomings

Images