A decentralized, model-free, global optimization method for energy saving in heating, ventilation and air conditioning systems

Abstract

To solve the challenges of high labour and maintenance cost while saving energy in engineering, a decentralized agent-based model-free global optimization method for heating, ventilation and air conditioning systems is proposed. In this novel optimization method, each updated smart equipment is connected according to the physical relationships, such that it can communicate and collaborate with adjacent nodes. Furthermore, to achieve the overall optimal operation of heating, ventilation and air conditioning systems, a decentralized evolutionary algorithm is developed. With the decentralized algorithm executed in all smart nodes in parallel with the feedback of sensor measurements instead of accurate device models, the system can achieve optimal coordination and avoid conflicts between correlated devices. The equivalence between the centralized and decentralized methods is proven. This method is confirmed to be effective through hardware testing based on actual engineering. Practical application: The traditional optimization methods for heating, ventilation and air conditioning are based on a centralized structure with a series of deficiencies, such as high maintenance and labour costs, link congestion and operational lag. This study presents a novel decentralized structure constructed using basic physical relations and a model-free method that possesses the advantages of plug-and-play, rapid development, great flexibility and convenience for engineering implementation without having to build a central monitor. The case study results validate the efficiency and effectiveness of the proposed method.

Optimization Design of Indoor Environmental Ventilation in Buildings Based on Improved SVR-PSO Model

“…In Equation (11), I Cη represents the thermal resistance of human clothing. The calculation of T Cη is shown in Equation (12).…”

“…This method involved heating, ventilation, and air conditioning systems, and different devices were mainly connected through physical relationships. To achieve overall optimization of heating, ventilation, and air conditioning systems, this study assessed the influence of distributed area fans on airflow velocity [12]. Researchers such as Ju FL developed a theoretical expression for the deviation of airflow rate in branch duct design for mechanical ventilation systems and identified the factors that affect the deviation.…”

Impacts of uncertain information delays on distributed real-time optimal controls for building HVAC systems deployed on IoT-enabled field control networks

“…Few researchers addressed the practical implementation of distributed optimal control, the implementation and distribution of decomposed optimization tasks on physical devices. Wang et al [15] and Cai et al [16] presented a generic structure of an agent-based optimal control strategy for HVAC systems. Both chose to decompose the optimization problems from the system level to the components level.…”