Dear Editor,This letter is concerned with the problem of stable high-quality signal transmission of unmanned aerial vehicle(UAV)-assisted multiple-input multiple-output(MIMO)communication system.The particle swarm opt...Dear Editor,This letter is concerned with the problem of stable high-quality signal transmission of unmanned aerial vehicle(UAV)-assisted multiple-input multiple-output(MIMO)communication system.The particle swarm optimization(PSO)algorithm is used to achieve optimal beamforming and power allocation for this system.Additionally,sensitive particle(SP)and parameter adaptive adjustment are introduced into the traditional PSO algorithm,aiming to improve the performance of the PSO algorithm in dynamic environments with real-time changes in the UAV position.A reinforcement learning(RL)-based approach is proposed to obtain optimal UAV trajectory and adaptive adjustment strategy for PSO parameters,which combine with a specific obstacle avoidance scheme to achieve accurate UAV navigation while satisfying high-quality signal transmission.Simulation experiments show that our scheme provides higher and more stable spectral efficiency as well as more efficient UAV navigation than the currently commonly used scheme with a single RL approach.展开更多
机械钻速(rate of penetration,ROP)是钻井作业优化和减少成本的关键因素,钻井时有效地预测ROP是提升钻进效率的关键。由于井下钻进时复杂多变的情况和地层的非均质性,通过传统的ROP方程和回归分析方法来预测钻速受到了一定的限制。为...机械钻速(rate of penetration,ROP)是钻井作业优化和减少成本的关键因素,钻井时有效地预测ROP是提升钻进效率的关键。由于井下钻进时复杂多变的情况和地层的非均质性,通过传统的ROP方程和回归分析方法来预测钻速受到了一定的限制。为了实现对钻速的高精度预测,对现有BP (back propagation)神经网络进行优化,提出了一种新的神经网络模型,即动态自适应学习率的粒子群优化BP神经网络,利用录井数据建立目标井预测模型来对钻速进行预测。在训练过程中对BP神经网络进行优化,利用启发式算法,即附加动量法和自适应学习率,将两种方法结合起来形成动态自适应学习率的BP改进算法,提高了BP神经网络的训练速度和拟合精度,获得了更好的泛化性能。将BP神经网络与遗传优化算法(genetic algorithm,GA)和粒子群优化算法(particle swarm optimization,PSO)结合,得到优化后的动态自适应学习率BP神经网络。研究利用XX8-1-2井的录井数据进行实验,对比BP神经网络、PSO-BP神经网络、GA-BP神经网络3种不同的改进后神经网络的预测结果。实验结果表明:优化后的PSO-BP神经网络的预测性能最好,具有更高的效率和可靠性,能够有效的利用工程数据,在有一定数据采集量的区域提供较为准确的ROP预测。展开更多
基金supported by the National Natural Science Foundation of China(62173251,62203113the“Zhishan”Scholars Programs of Southeast University,and the Fundamental Research Funds for the Central Universities(2242023K30034).
文摘Dear Editor,This letter is concerned with the problem of stable high-quality signal transmission of unmanned aerial vehicle(UAV)-assisted multiple-input multiple-output(MIMO)communication system.The particle swarm optimization(PSO)algorithm is used to achieve optimal beamforming and power allocation for this system.Additionally,sensitive particle(SP)and parameter adaptive adjustment are introduced into the traditional PSO algorithm,aiming to improve the performance of the PSO algorithm in dynamic environments with real-time changes in the UAV position.A reinforcement learning(RL)-based approach is proposed to obtain optimal UAV trajectory and adaptive adjustment strategy for PSO parameters,which combine with a specific obstacle avoidance scheme to achieve accurate UAV navigation while satisfying high-quality signal transmission.Simulation experiments show that our scheme provides higher and more stable spectral efficiency as well as more efficient UAV navigation than the currently commonly used scheme with a single RL approach.
