Solving chiller loading optimization problems using an improved teaching-learning-based optimization algorithm

In this study, we present a novel teaching-learning-based optimization (TLBO) algorithm for solving the optimal chiller loading problem. The proposed algorithm uses a novel integer-based encoding and decoding mechanism that is efficient and easy to implement. The teaching phase can improve the quality of learning process and thus enhance the exploitation ability. In addition, a well-designed learning phase procedure is developed to enhance the learning process between one another in the population. A novel exploration and self-learning procedures are embedded in the proposed TLBO algorithm, which can enhance the exploitation and exploration capabilities. The proposed algorithm is tested on several well-known case studies and compared with several efficient algorithms. From the experimental comparisons, the efficient performance of the proposed TLBO is verified.