Abstract: A direct search-simulated annealing(DSA)which is memory-based is suggested and constituted to solve the optimum planning model. The algorithm is applied to the optimum planning for the waste treatment system of Urumqi,Xinjiang. Results show an improved performance in finding the global minimum when water quality requirements have been fulfilled. The DSA has been shown to be fast,efficient and stable.And the program is simple.It provides a new way to the optimal planning of water pollution control system and has great application prospects.