扩展变异ADE算法的有向传感器网络覆盖增强

Extended-differentiation-mode based adaptive differential evolution algorithm for coverage-enhancing in directional sensor networks

针对有向传感器节点大规模随机部署形成的感知重叠区和监测盲区,在节点位置不变、感知方向可调的前提下,协同调整节点感知方向使其覆盖范围从感知重叠区旋转到监测盲区以增强网络覆盖。将有向传感器网络覆盖增强问题转换为以区域覆盖率为目标函数、节点集感知方向为决策变量的最优化问题,提出了基于扩展变异模式的自适应差分进化算法求解该问题,即寻求一种节点感知方向分布方案最大化区域覆盖率。算法迭代前期采用DE/rand/1/bin变异策略以保证种群的多样性,后期采用扩展变异模式DE/current-to-best/2/bin加强算法的收敛速度以保证算法高效率地搜索全局最优解。与传统的有向传感器网络覆盖增强算法对比,仿真实验验证了算法的有效性。

Aiming at eliminating the sensing overlapping regions and coverage holes caused by random deployment of nodes, the major sensing direction can be adjusted to make sensors uniformly distributed as well as the coverage enhancing in the di- rection adjustable sensing model. This paper proposed an extended-differentiation-mode based adaptive differential evolution algorithm in which the major sensing direction of nodes was treated as decision variable and coverage ratio was selected as ob- jective function. In early stage, the improved algorithm used DE/rand/l/bin differentiation mode to keep individual diversity and avoid premature convergence as well. Then DE/current-to-best/2/bin differentiation mode was employed to increase the convergence speed in the later iteration stage. Furthermore adaptive mechanism was introduced for differentiation constant to search the optimal solution more efficiently. Simulation results comparing with the traditional coverage-enhancing algorithms are performed to demonstrate the effectiveness of the proposed algorithm.