This study introduces the Smart Exponential-Threshold-Linear with Double Deep Q-learning Network(SETL-DDQN)and an extended Gumbel distribution method,designed to optimize the Contention Window(CW)in IEEE 802.11 networ...This study introduces the Smart Exponential-Threshold-Linear with Double Deep Q-learning Network(SETL-DDQN)and an extended Gumbel distribution method,designed to optimize the Contention Window(CW)in IEEE 802.11 networks.Unlike conventional Deep Reinforcement Learning(DRL)-based approaches for CW size adjustment,which often suffer from overestimation bias and limited exploration diversity,leading to suboptimal throughput and collision performance.Our framework integrates the Gumbel distribution and extreme value theory to systematically enhance action selection under varying network conditions.First,SETL adopts a DDQN architecture(SETL-DDQN)to improve Q-value estimation accuracy and enhance training stability.Second,we incorporate a Gumbel distribution-driven exploration mechanism,forming SETL-DDQN(Gumbel),which employs the extreme value theory to promote diverse action selection,replacing the conventional-greedy exploration that undergoes early convergence to suboptimal solutions.Both models are evaluated through extensive simulations in static and time-varying IEEE 802.11 network scenarios.The results demonstrate that our approach consistently achieves higher throughput,lower collision rates,and improved adaptability,even under abrupt fluctuations in traffic load and network conditions.In particular,the Gumbel-based mechanism enhances the balance between exploration and exploitation,facilitating faster adaptation to varying congestion levels.These findings position Gumbel-enhanced DRL as an effective and robust solution for CW optimization in wireless networks,offering notable gains in efficiency and reliability over existing methods.展开更多
The horizontal diffusion coefficients of the operational model (T42L9) in numerical weather prediction are optimized by the steepest descent search of multi-dimensional optimization. In order to improve prediction acc...The horizontal diffusion coefficients of the operational model (T42L9) in numerical weather prediction are optimized by the steepest descent search of multi-dimensional optimization. In order to improve prediction accuracy in low latitudes, the optimum horizontal diffusion coefficients are chosen, with changing variation of the basic diffusion coefficient with the passage of time, and later forecasts are also made better. In view of the averages of forecast verifications of 9 cases, the forecasts with optimum diffusion coefficients are an improvement on operational forecasts. It means that the forecasts are got much better with optimum values of some important parameters by optimization in numerical weather prediction.展开更多
粒子群优化(PSO)算法是一种新兴的群体智能优化技术,由于其原理简单、参数少、效果好等优点已经广泛应用于求解各类复杂优化问题.而影响该算法收敛速度和精度的2个主要因素是粒子个体极值与全局极值的更新方式.通过分析粒子的飞行轨迹...粒子群优化(PSO)算法是一种新兴的群体智能优化技术,由于其原理简单、参数少、效果好等优点已经广泛应用于求解各类复杂优化问题.而影响该算法收敛速度和精度的2个主要因素是粒子个体极值与全局极值的更新方式.通过分析粒子的飞行轨迹和引入广义中心粒子和狭义中心粒子,提出双中心粒子群优化(double center particle swarm optimization,DCPSO)算法,在不增加算法复杂度条件下对粒子的个体极值和全局极值更新方式进行更新,从而改善了算法的收敛速度和精度.采用Rosenbrock和Rastrigrin等6个经典测试函数,按照固定迭达次数和固定时间长度运行2种方式进行测试,验证了新算法的可行性和有效性.展开更多
针对人工鱼群算法的寻优速度慢,后期收敛性差等缺陷提出了一种并行运行方式的改进人工鱼群算法(Improvement Artificial Fish Swarm Algorithm,IAFSA)。进而应用IAFSA算法对BP神经网络初始权值进行寻优,以解决BP网络初始权值选取困难且...针对人工鱼群算法的寻优速度慢,后期收敛性差等缺陷提出了一种并行运行方式的改进人工鱼群算法(Improvement Artificial Fish Swarm Algorithm,IAFSA)。进而应用IAFSA算法对BP神经网络初始权值进行寻优,以解决BP网络初始权值选取困难且优化过程中容易陷入局部极值的问题。最后,将IAFSA-BP网络混合算法应用于PID参数的优化,从而克服了PID控制参数难以整定的难题。通过仿真实验,结果表明:改进的人工鱼群算法寻优速度更快,优化值更加合理。应用IAFSA-BP混合算法得到的PID控制参数使得系统响应更快,稳态误差更小,系统性能得到提升。展开更多
针对粒子群算法(Particle Swarm Optimization,PSO)易陷入局部极值的缺陷,提出了一种新的自适应惯性权重混沌PSO算法(a New Chaos Particle Swarm Optimization based on Adaptive Inertia Weight,CPSO-NAIW)。首先采用新的惯性权重自...针对粒子群算法(Particle Swarm Optimization,PSO)易陷入局部极值的缺陷,提出了一种新的自适应惯性权重混沌PSO算法(a New Chaos Particle Swarm Optimization based on Adaptive Inertia Weight,CPSO-NAIW)。首先采用新的惯性权重自适应方法,很好地平衡粒子的搜索行为,减少算法陷入局部极值的概率,然后在算法陷入局部极值时,引入混沌优化策略,对群体极值位置进行调整,以使粒子搜索新的邻域和路径,增加算法摆脱局部极值的可能。最后,实验结果表明,CPSO-NAIW算法能有效避免陷入局部极值,提高算法性能。展开更多
文摘This study introduces the Smart Exponential-Threshold-Linear with Double Deep Q-learning Network(SETL-DDQN)and an extended Gumbel distribution method,designed to optimize the Contention Window(CW)in IEEE 802.11 networks.Unlike conventional Deep Reinforcement Learning(DRL)-based approaches for CW size adjustment,which often suffer from overestimation bias and limited exploration diversity,leading to suboptimal throughput and collision performance.Our framework integrates the Gumbel distribution and extreme value theory to systematically enhance action selection under varying network conditions.First,SETL adopts a DDQN architecture(SETL-DDQN)to improve Q-value estimation accuracy and enhance training stability.Second,we incorporate a Gumbel distribution-driven exploration mechanism,forming SETL-DDQN(Gumbel),which employs the extreme value theory to promote diverse action selection,replacing the conventional-greedy exploration that undergoes early convergence to suboptimal solutions.Both models are evaluated through extensive simulations in static and time-varying IEEE 802.11 network scenarios.The results demonstrate that our approach consistently achieves higher throughput,lower collision rates,and improved adaptability,even under abrupt fluctuations in traffic load and network conditions.In particular,the Gumbel-based mechanism enhances the balance between exploration and exploitation,facilitating faster adaptation to varying congestion levels.These findings position Gumbel-enhanced DRL as an effective and robust solution for CW optimization in wireless networks,offering notable gains in efficiency and reliability over existing methods.
文摘The horizontal diffusion coefficients of the operational model (T42L9) in numerical weather prediction are optimized by the steepest descent search of multi-dimensional optimization. In order to improve prediction accuracy in low latitudes, the optimum horizontal diffusion coefficients are chosen, with changing variation of the basic diffusion coefficient with the passage of time, and later forecasts are also made better. In view of the averages of forecast verifications of 9 cases, the forecasts with optimum diffusion coefficients are an improvement on operational forecasts. It means that the forecasts are got much better with optimum values of some important parameters by optimization in numerical weather prediction.
文摘粒子群优化(PSO)算法是一种新兴的群体智能优化技术,由于其原理简单、参数少、效果好等优点已经广泛应用于求解各类复杂优化问题.而影响该算法收敛速度和精度的2个主要因素是粒子个体极值与全局极值的更新方式.通过分析粒子的飞行轨迹和引入广义中心粒子和狭义中心粒子,提出双中心粒子群优化(double center particle swarm optimization,DCPSO)算法,在不增加算法复杂度条件下对粒子的个体极值和全局极值更新方式进行更新,从而改善了算法的收敛速度和精度.采用Rosenbrock和Rastrigrin等6个经典测试函数,按照固定迭达次数和固定时间长度运行2种方式进行测试,验证了新算法的可行性和有效性.
文摘针对人工鱼群算法的寻优速度慢,后期收敛性差等缺陷提出了一种并行运行方式的改进人工鱼群算法(Improvement Artificial Fish Swarm Algorithm,IAFSA)。进而应用IAFSA算法对BP神经网络初始权值进行寻优,以解决BP网络初始权值选取困难且优化过程中容易陷入局部极值的问题。最后,将IAFSA-BP网络混合算法应用于PID参数的优化,从而克服了PID控制参数难以整定的难题。通过仿真实验,结果表明:改进的人工鱼群算法寻优速度更快,优化值更加合理。应用IAFSA-BP混合算法得到的PID控制参数使得系统响应更快,稳态误差更小,系统性能得到提升。
文摘针对粒子群算法(Particle Swarm Optimization,PSO)易陷入局部极值的缺陷,提出了一种新的自适应惯性权重混沌PSO算法(a New Chaos Particle Swarm Optimization based on Adaptive Inertia Weight,CPSO-NAIW)。首先采用新的惯性权重自适应方法,很好地平衡粒子的搜索行为,减少算法陷入局部极值的概率,然后在算法陷入局部极值时,引入混沌优化策略,对群体极值位置进行调整,以使粒子搜索新的邻域和路径,增加算法摆脱局部极值的可能。最后,实验结果表明,CPSO-NAIW算法能有效避免陷入局部极值,提高算法性能。
