A Parallel Constrained Efficient Global Optimization Algorithm For Expensive Constrained Optimization Problems

The Constrained Expected Improvement (CEI) criterion used in the so-called Constrained Efficient Global Optimization (C-EGO) algorithm is one of the most famous infill criteria for expensive constrained optimization problems. However, the standard CEI criterion selects only one point to evaluate in each cycle, which is time consuming when parallel computing architecture is available. This work proposes a new Parallel Constrained EGO (PC-EGO) algorithm to extend the C-EGO algorithm to parallel computing. The proposed PC-EGO algorithm is tested on sixteen analytical problems as well as one real-world engineering problem. The experiment results show that the proposed PC-EGO algorithm converges significantly faster and finds better solutions on the test problems compared to the standard C-EGO algorithm. Moreover, when compared to another state-of-the-art parallel constrained EGO algorithm, the proposed PC-EGO algorithm shows more efficient and robust performance.