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 Vehicle Routing Problem with Time Windows(VRPTW)presents a significant challenge in combinatorial optimization,especially under real-world uncertainties such as variable travel times,service durations,and dynamic ...The Vehicle Routing Problem with Time Windows(VRPTW)presents a significant challenge in combinatorial optimization,especially under real-world uncertainties such as variable travel times,service durations,and dynamic customer demands.These uncertainties make traditional deterministic models inadequate,often leading to suboptimal or infeasible solutions.To address these challenges,this work proposes an adaptive hybrid metaheuristic that integrates Genetic Algorithms(GA)with Local Search(LS),while incorporating stochastic uncertainty modeling through probabilistic travel times.The proposed algorithm dynamically adjusts parameters—such as mutation rate and local search probability—based on real-time search performance.This adaptivity enhances the algorithm’s ability to balance exploration and exploitation during the optimization process.Travel time uncertainties are modeled using Gaussian noise,and solution robustness is evaluated through scenario-based simulations.We test our method on a set of benchmark problems from Solomon’s instance suite,comparing its performance under deterministic and stochastic conditions.Results show that the proposed hybrid approach achieves up to a 9%reduction in expected total travel time and a 40% reduction in time window violations compared to baseline methods,including classical GA and non-adaptive hybrids.Additionally,the algorithm demonstrates strong robustness,with lower solution variance across uncertainty scenarios,and converges faster than competing approaches.These findings highlight the method’s suitability for practical logistics applications such as last-mile delivery and real-time transportation planning,where uncertainty and service-level constraints are critical.The flexibility and effectiveness of the proposed framework make it a promising candidate for deployment in dynamic,uncertainty-aware supply chain environments.展开更多
Considering that the vehicle routing problem （VRP） with many extended features is widely used in actual life, such as multi-depot, heterogeneous types of vehicles, customer service priority and time windows etc., a ...Considering that the vehicle routing problem （VRP） with many extended features is widely used in actual life, such as multi-depot, heterogeneous types of vehicles, customer service priority and time windows etc., a mathematical model for multi-depot heterogeneous vehicle routing problem with soft time windows （MDHVRPSTW） is established. An improved ant colony optimization （IACO） is proposed for solving this model. First, MDHVRPSTW is transferred into different groups according to the nearest principle, and then the initial route is constructed by the scanning algorithm （SA）. Secondly, genetic operators are introduced, and crossover probability and mutation probability are adaptively adjusted in order to improve the global search ability of the algorithm. Moreover, the smooth mechanism is used to improve the performance of the ant colony optimization （ACO）. Finally, the 3-opt strategy is used to improve the local search ability. The proposed IACO was tested on three new instances that were generated randomly. The experimental results show that IACO is superior to the other three existing algorithms in terms of convergence speed and solution quality. Thus, the proposed method is effective and feasible, and the proposed model is meaningful.展开更多
The formula for calculating the threshold of average transmitting power of cylindrical TE11 mode window is revised by accurate deduction and a practical method for calculating the temperature increment of the dielectr...The formula for calculating the threshold of average transmitting power of cylindrical TE11 mode window is revised by accurate deduction and a practical method for calculating the temperature increment of the dielectric disk in cylindrical box type window is given. Meanwhile,a typical cylindrical box type window is calculated and used as an example to discuss the power capacity, the special harmfulness and elimination of ghost mode resonance when the window is used to transmit high power Continuous Wave(CW).展开更多
A 50 mA CW deuteron RFQ is being built for a joint 973 project between Peking University and the Institute of Modern Physics. This RFQ adopts a high-frequency window-type structure. To study its RF properties and to v...A 50 mA CW deuteron RFQ is being built for a joint 973 project between Peking University and the Institute of Modern Physics. This RFQ adopts a high-frequency window-type structure. To study its RF properties and to validate the reliability of an electromagnetic simulation, two full-length aluminum models with tuners were built in succession. RF measurements were obtained from the test bench and compared to the simulations, including frequencies, quality factors, and electric fields of different modes and the field in aperture. Through field tuning, the maximal field unflatness for a single quadrant and the average asymmetry of four quadrants were reduced from 8.7% and ± 3.6% to 5.8% and ± 1.7%, respectively.Moreover, a tuning method of adjusting the gap distance between the endplates and the vanes was also studied in this paper.展开更多
Sinopec's Weiyuan Shale Gas Block is structurally located at the Baimazhen syncline held by the Weiyuan paleo-uplift and Ziliujing anticline in the Sichuan Basin.In this block,the Wufeng Fm of Upper OrdovicianeLon...Sinopec's Weiyuan Shale Gas Block is structurally located at the Baimazhen syncline held by the Weiyuan paleo-uplift and Ziliujing anticline in the Sichuan Basin.In this block,the Wufeng Fm of Upper OrdovicianeLongmaxi Fm of Lower Silurian is an organic-rich dark shale deposit of deepwater shelf facies,whose litho-electric characteristics of geophysical logging are obviously different vertically and reservoir heterogeneity is strong.For providing a guidance for target window optimization and drilling trajectory tracking and adjustment of horizontal wells in the Weiyuan Shale Gas Block,parameter indexes were evaluated by refining the reservoir classification based on well logging subdivision,fine characterization of core laminae,high-precision geophysical prediction and genetic analysis of sedimentary microfacies.Furthermore,the“sweet spots”of shale gas reservoirs were predicted.Then,the target window was optimized and the trajectory of a horizontal well was designed.Finally,the effects of the target window of a horizontal well on shale gas productivity were evaluated.And the following research results were obtained.First,three types of laminae are developed in the high-quality shale reservoir at the bottom of Wufeng FmeLong 1 Member,and they are vertically staggered and overlapped,which reflects the microscopic difference of sedimentary environment and reservoir quality.Second,shale gas reservoirs in this block can be divided into high-quality reservoirs,better reservoirs,general reservoirs and poor reservoirs.Third,the sublayer 2-3^(1) at the bottom of Longmaxi Fm is biogenic sedimentary microfacies and it has the characteristics of“geological+engineering”sweet spot,e.g.high TOC contents,high porosity,high brittleness,high gas content and low in-situ stress difference,so it is classified as a high-quality reservoir.Fourth,actual drilling results show that the location selection of the target window of a horizontal well has a significant impact on single-well shale gas productivity,and the penetration rate of a high-quality reservoir is the key geological factor to achieve high-yield shale gas.The research results provide support for the evaluation of shale gas productivity and lay a foundation for the commercial development of shale gas in the Weiyuan Shale Gas Block.展开更多
在经典车辆路径问题(vehicle routing problem,VRP)的基础上增加了客户要求访问的时间窗约束,以车辆行驶路径最短和使用车辆数最小为目标,建立了不确定车辆数的多约束车辆路径问题(multi-constraint vehicle routing problem with varia...在经典车辆路径问题(vehicle routing problem,VRP)的基础上增加了客户要求访问的时间窗约束,以车辆行驶路径最短和使用车辆数最小为目标,建立了不确定车辆数的多约束车辆路径问题(multi-constraint vehicle routing problem with variable fleets,MVRP-VF)的数学模型。引入遗传算法的交叉操作以及大规模邻域搜索算法中的破坏算子和修复算子,重新定义了基本灰狼优化算法(grey wolf optimizer,GWO)的操作算子,优化了GWO的寻优机制,从而设计出用于求解MVRP-VF问题的混合灰狼优化算法(hybrid grey wolf optimizer,HGWO)。通过仿真实验与其他参考文献中的算法求解结果进行比较,验证了HGWO求解该类问题的有效性与可行性。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 Vehicle Routing Problem with Time Windows(VRPTW)presents a significant challenge in combinatorial optimization,especially under real-world uncertainties such as variable travel times,service durations,and dynamic customer demands.These uncertainties make traditional deterministic models inadequate,often leading to suboptimal or infeasible solutions.To address these challenges,this work proposes an adaptive hybrid metaheuristic that integrates Genetic Algorithms(GA)with Local Search(LS),while incorporating stochastic uncertainty modeling through probabilistic travel times.The proposed algorithm dynamically adjusts parameters—such as mutation rate and local search probability—based on real-time search performance.This adaptivity enhances the algorithm’s ability to balance exploration and exploitation during the optimization process.Travel time uncertainties are modeled using Gaussian noise,and solution robustness is evaluated through scenario-based simulations.We test our method on a set of benchmark problems from Solomon’s instance suite,comparing its performance under deterministic and stochastic conditions.Results show that the proposed hybrid approach achieves up to a 9%reduction in expected total travel time and a 40% reduction in time window violations compared to baseline methods,including classical GA and non-adaptive hybrids.Additionally,the algorithm demonstrates strong robustness,with lower solution variance across uncertainty scenarios,and converges faster than competing approaches.These findings highlight the method’s suitability for practical logistics applications such as last-mile delivery and real-time transportation planning,where uncertainty and service-level constraints are critical.The flexibility and effectiveness of the proposed framework make it a promising candidate for deployment in dynamic,uncertainty-aware supply chain environments.
基金The National Natural Science Foundation of China(No.61074147)the Natural Science Foundation of Guangdong Province(No.S2011010005059)+2 种基金the Foundation of Enterprise-University-Research Institute Cooperation from Guangdong Province and Ministry of Education of China(No.2012B091000171,2011B090400460)the Science and Technology Program of Guangdong Province(No.2012B050600028)the Science and Technology Program of Huadu District,Guangzhou(No.HD14ZD001)
文摘Considering that the vehicle routing problem （VRP） with many extended features is widely used in actual life, such as multi-depot, heterogeneous types of vehicles, customer service priority and time windows etc., a mathematical model for multi-depot heterogeneous vehicle routing problem with soft time windows （MDHVRPSTW） is established. An improved ant colony optimization （IACO） is proposed for solving this model. First, MDHVRPSTW is transferred into different groups according to the nearest principle, and then the initial route is constructed by the scanning algorithm （SA）. Secondly, genetic operators are introduced, and crossover probability and mutation probability are adaptively adjusted in order to improve the global search ability of the algorithm. Moreover, the smooth mechanism is used to improve the performance of the ant colony optimization （ACO）. Finally, the 3-opt strategy is used to improve the local search ability. The proposed IACO was tested on three new instances that were generated randomly. The experimental results show that IACO is superior to the other three existing algorithms in terms of convergence speed and solution quality. Thus, the proposed method is effective and feasible, and the proposed model is meaningful.
文摘The formula for calculating the threshold of average transmitting power of cylindrical TE11 mode window is revised by accurate deduction and a practical method for calculating the temperature increment of the dielectric disk in cylindrical box type window is given. Meanwhile,a typical cylindrical box type window is calculated and used as an example to discuss the power capacity, the special harmfulness and elimination of ghost mode resonance when the window is used to transmit high power Continuous Wave(CW).
基金supported by the National Basic Research Program of China(No.2014CB845503)
文摘A 50 mA CW deuteron RFQ is being built for a joint 973 project between Peking University and the Institute of Modern Physics. This RFQ adopts a high-frequency window-type structure. To study its RF properties and to validate the reliability of an electromagnetic simulation, two full-length aluminum models with tuners were built in succession. RF measurements were obtained from the test bench and compared to the simulations, including frequencies, quality factors, and electric fields of different modes and the field in aperture. Through field tuning, the maximal field unflatness for a single quadrant and the average asymmetry of four quadrants were reduced from 8.7% and ± 3.6% to 5.8% and ± 1.7%, respectively.Moreover, a tuning method of adjusting the gap distance between the endplates and the vanes was also studied in this paper.
基金Project supported by the National science and technology major project of the 13th five-year plan“Exploration potential and target evaluation of marine shale gas in South China”(No.2017zx05036-003).
文摘Sinopec's Weiyuan Shale Gas Block is structurally located at the Baimazhen syncline held by the Weiyuan paleo-uplift and Ziliujing anticline in the Sichuan Basin.In this block,the Wufeng Fm of Upper OrdovicianeLongmaxi Fm of Lower Silurian is an organic-rich dark shale deposit of deepwater shelf facies,whose litho-electric characteristics of geophysical logging are obviously different vertically and reservoir heterogeneity is strong.For providing a guidance for target window optimization and drilling trajectory tracking and adjustment of horizontal wells in the Weiyuan Shale Gas Block,parameter indexes were evaluated by refining the reservoir classification based on well logging subdivision,fine characterization of core laminae,high-precision geophysical prediction and genetic analysis of sedimentary microfacies.Furthermore,the“sweet spots”of shale gas reservoirs were predicted.Then,the target window was optimized and the trajectory of a horizontal well was designed.Finally,the effects of the target window of a horizontal well on shale gas productivity were evaluated.And the following research results were obtained.First,three types of laminae are developed in the high-quality shale reservoir at the bottom of Wufeng FmeLong 1 Member,and they are vertically staggered and overlapped,which reflects the microscopic difference of sedimentary environment and reservoir quality.Second,shale gas reservoirs in this block can be divided into high-quality reservoirs,better reservoirs,general reservoirs and poor reservoirs.Third,the sublayer 2-3^(1) at the bottom of Longmaxi Fm is biogenic sedimentary microfacies and it has the characteristics of“geological+engineering”sweet spot,e.g.high TOC contents,high porosity,high brittleness,high gas content and low in-situ stress difference,so it is classified as a high-quality reservoir.Fourth,actual drilling results show that the location selection of the target window of a horizontal well has a significant impact on single-well shale gas productivity,and the penetration rate of a high-quality reservoir is the key geological factor to achieve high-yield shale gas.The research results provide support for the evaluation of shale gas productivity and lay a foundation for the commercial development of shale gas in the Weiyuan Shale Gas Block.
文摘在经典车辆路径问题(vehicle routing problem,VRP)的基础上增加了客户要求访问的时间窗约束,以车辆行驶路径最短和使用车辆数最小为目标,建立了不确定车辆数的多约束车辆路径问题(multi-constraint vehicle routing problem with variable fleets,MVRP-VF)的数学模型。引入遗传算法的交叉操作以及大规模邻域搜索算法中的破坏算子和修复算子,重新定义了基本灰狼优化算法(grey wolf optimizer,GWO)的操作算子,优化了GWO的寻优机制,从而设计出用于求解MVRP-VF问题的混合灰狼优化算法(hybrid grey wolf optimizer,HGWO)。通过仿真实验与其他参考文献中的算法求解结果进行比较,验证了HGWO求解该类问题的有效性与可行性。
