“…There are key difficulties, to resolve the UC problems, by incorporating these classical approaches like deprived convergence, computation intricacy to handle multi-objective functions with many constraints, to achieve efficient results. Nontraditional artificial intelligence based optimization approaches like Network Programming (NP) [80], Tabu Search (TS) [81], Hybrid fuzzy based TS [82], Heuristic search techniques [83]- [85], Simulated Annealing (SA) [86]- [89], Twofold SA [90], [91], Adaptive SA [92], Enhanced SA [93], [94], Stochastic SA [95], [96], Ant Colony Optimization (ACO) [97], [98], ACO with Random Perturbation [99], Memory Bounded ACO [100], Nodal ACO [101], Hybrid Taguchi ACO [102], Fuzzy Logic [103]- [107], Fuzzy based SA [108], [109], Fuzzy DP [110], Fuzzy Hierarchical Bi-Level Modelling [111], Artificial Neural Network (ANN) [112]- [119], Hybrid ANN [120]- [122], Hopfield ANN [123]- [127], Expert System [128]- [131] and Quasi-Oppositional Teaching Learning Algorithm [132], could cope with the convergence properties, intricacy of computational operation and give innovative solutions against conservative methods. Every traditional and non-traditional technique has diverse properties, merits and demerits.…”