认知引擎必须根据外界无线环境的变化和用户需求,快速自适应调整无线电参数.本文选取一定比例粒子群个体按选定匹配案例的参数配置进行初始化,其余个体随机初始化,这样使粒子群优化算法的粒子在搜索初期就处于靠近最优解的解空间里,同时保持一定的种群多样性,得到一种基于案例推理粒子群优化算法；并由此算法以最大化数据速率、最小化发射功率及最小化误比特率为目标来优化无线电传输参数,得到一种比现有算法收敛速率快和寻优能力强的认知引擎.多载波系统的仿真结果表明了本算法的有效性.%Cognitive engine must adapt the radio parameters quickly according to the changing environment and user needs. A certain percentage of the particle swarm individuals are initialized based on the parameters of the selected matching cases, and the remaining individuals are randomly initialized, which can make particles of the particle swarm optimization algorithm near the optimal solution in the early search stage and maintain a certain degree of population diversity. A case-based reasoning particle swarm optimization algorithm is got, and the proposed algorithm is used to adjust and optimize the radio parameters to maximize the date throughput、minimize the transmit power and BER. The proposed algorithm is better than current algorithms in both the convergence rate and the optimization capability. Simulation results of multi-carrier system show the effectiveness of the algorithm.
展开▼
