【摘要】 任务调度是P2P计算中的一项关键技术,直接影响到整个系统的计算性能.提出了基于免疫算法的多目标约束P2P任务调度策略.首先对多目标P2P任务调度相关问题做出定义,然后分别构造了考虑负载均衡的种群初始化算子和基于熵的克隆选择算子,并设计了新颖的交叉算子、变异算子和具有先验知识的疫苗.在描述了P2P节点获取和管理策略的基础上,提出了多目标任务调度策略.实验结果验证了调度策略在缩短任务执行时间和通信时间、以及节省调度费用等方面的有效性.更多还原

【Abstract】 Since the task scheduling algorithm directly affects the performance of the P2P computing,the task scheduling with multi-objective constraints is presented by using immune algorithm.The population initialization operator considering load balance,the clone selection operator controlled by entropy,the new crossover operator,mutation operator and vaccine with apriori knowledge are designed for task scheduling based on model definition.And then the multi-objective task scheduling strategy is proposed after describing the mechanism for searching and managing the available P2P nodes.Experimental results indicate the validity of the proposed scheduling strategy in shortening the execution time and communication time,as well as saving the scheduling costs.更多还原