针对异构并行任务分配的最小完成时间和负载均衡组合优化问题,提出一种混合离散微粒群算法,将启发式Sufferage算法引入离散微粒群算法(DPSO)中,改进DPSO算法中的位置速度关系模型,提高DPSO算法的搜索效率和精度.通过实验验证,从算法效率和收敛速度上均优于DPSO算法和GA算法,且负载均衡度较好. Aiming at the minimum completion time and load balancing combinatorial optimization problem of heterogeneous parallel task allocation, a hybrid discrete particle swarm optimization algorithm is proposed. The heuristic Sufferage algorithm is introduced into discrete particle swarm optimization (DPSO) to improve the location-velocity relation model , Which improves the search efficiency and accuracy of DPSO algorithm.Experimental results show that the proposed algorithm is superior to DPSO algorithm and GA algorithm in terms of efficiency and convergence speed, and the load balancing is better.