Energy management in cooling system using hybrid optimization clustering technique

Malaysia is situated in Southeast Asia, close to the equator, and as a result of its position, it has hot and humid weather. Because of the impact of the high ambient temperature, more than 50% of the building's energy is used to meet the cooling load demand. Reducing energy consumption in cooling systems without compromising cooling load demand is still an issue to manage. Numerous research studies have been conducted on cooling load demand and its power usage in order to regulate energy consumption and cooling load. These studies have included fuzzy c-mean (FCM) and fuzzy subtractive clustering (FSC) have been involved in cooling systems. As a result, when it comes to deciding how many clusters to use and deploying big data, both FCM and FSC are constrained. This work proposes accelerated particle swarm optimization (APSO) and FSC techniques to achieve this. By adjusting the cluster radius of the FSC-based APSO algorithm. To tune and adjust the cluster radius, a proportional-integral (PI) controller is adopted. The main objective of the APSO is to fine-tune the data clustering parameters. The outcome of the proposed FSC-APSO based PI technique is to identify the input-output dataset for evaluating electricity usage and cooling load demand. The energy usage and load demand in this work are evaluated based on the influence of ambient temperature and relative humidity. The results show that the FSC-APSO technique reduces energy consumption by 10% without compromising comfort-cooling demand. The result is validated using actual data obtained from Latexx Manufacturing Sdn Bhd, Malaysia.