Unmanned Aerial Vehicles(UAVs)have become integral components in smart city infrastructures,supporting applications such as emergency response,surveillance,and data collection.However,the high mobility and dynamic top...Unmanned Aerial Vehicles(UAVs)have become integral components in smart city infrastructures,supporting applications such as emergency response,surveillance,and data collection.However,the high mobility and dynamic topology of Flying Ad Hoc Networks(FANETs)present significant challenges for maintaining reliable,low-latency communication.Conventional geographic routing protocols often struggle in situations where link quality varies and mobility patterns are unpredictable.To overcome these limitations,this paper proposes an improved routing protocol based on reinforcement learning.This new approach integrates Q-learning with mechanisms that are both link-aware and mobility-aware.The proposed method optimizes the selection of relay nodes by using an adaptive reward function that takes into account energy consumption,delay,and link quality.Additionally,a Kalman filter is integrated to predict UAV mobility,improving the stability of communication links under dynamic network conditions.Simulation experiments were conducted using realistic scenarios,varying the number of UAVs to assess scalability.An analysis was conducted on key performance metrics,including the packet delivery ratio,end-to-end delay,and total energy consumption.The results demonstrate that the proposed approach significantly improves the packet delivery ratio by 12%–15%and reduces delay by up to 25.5%when compared to conventional GEO and QGEO protocols.However,this improvement comes at the cost of higher energy consumption due to additional computations and control overhead.Despite this trade-off,the proposed solution ensures reliable and efficient communication,making it well-suited for large-scale UAV networks operating in complex urban environments.展开更多
The integration of High-Altitude Platform Stations(HAPS)with Reconfigurable Intelligent Surfaces(RIS)represents a critical advancement for next-generation wireless networks,offering unprecedented opportunities for ubi...The integration of High-Altitude Platform Stations(HAPS)with Reconfigurable Intelligent Surfaces(RIS)represents a critical advancement for next-generation wireless networks,offering unprecedented opportunities for ubiquitous connectivity.However,existing research reveals significant gaps in dynamic resource allocation,joint optimization,and equitable service provisioning under varying channel conditions,limiting practical deployment of these technologies.This paper addresses these challenges by proposing a novel Fairness-Aware Deep Q-Learning(FAIRDQL)framework for joint resource management and phase configuration in HAPS-RIS systems.Our methodology employs a comprehensive three-tier algorithmic architecture integrating adaptive power control,priority-based user scheduling,and dynamic learning mechanisms.The FAIR-DQL approach utilizes advanced reinforcement learning with experience replay and fairness-aware reward functions to balance competing objectives while adapting to dynamic environments.Key findings demonstrate substantial improvements:9.15 dB SINR gain,12.5 bps/Hz capacity,78%power efficiency,and 0.82 fairness index.The framework achieves rapid 40-episode convergence with consistent delay performance.These contributions establish new benchmarks for fairness-aware resource allocation in aerial communications,enabling practical HAPS-RIS deployments in rural connectivity,emergency communications,and urban networks.展开更多
To address low learning efficiency and inadequate path safety in spraying robot navigation within complex obstacle-rich environments—with dense,dynamic,unpredictable obstacles challenging conventional methods—this p...To address low learning efficiency and inadequate path safety in spraying robot navigation within complex obstacle-rich environments—with dense,dynamic,unpredictable obstacles challenging conventional methods—this paper proposes a hybrid algorithm integrating Q-learning and improved A*-Artificial Potential Field(A-APF).Centered on theQ-learning framework,the algorithmleverages safety-oriented guidance generated byA-APF and employs a dynamic coordination mechanism that adaptively balances exploration and exploitation.The proposed system comprises four core modules:(1)an environment modeling module that constructs grid-based obstacle maps;(2)an A-APF module that combines heuristic search from A*algorithm with repulsive force strategies from APF to generate guidance;(3)a Q-learning module that learns optimal state-action values(Q-values)through spraying robot-environment interaction and a reward function emphasizing path optimality and safety;and(4)a dynamic optimization module that ensures adaptive cooperation between Q-learning and A-APF through exploration rate control and environment-aware constraints.Simulation results demonstrate that the proposed method significantly enhances path safety in complex underground mining environments.Quantitative results indicate that,compared to the traditional Q-learning algorithm,the proposed method shortens training time by 42.95% and achieves a reduction in training failures from 78 to just 3.Compared to the static fusion algorithm,it further reduces both training time(by 10.78%)and training failures(by 50%),thereby improving overall training efficiency.展开更多
This research proposes an improved Puma optimization algorithm(IPuma)as a novel dynamic recon-figuration tool for a photovoltaic(PV)array linked in total-cross-tied(TCT).The proposed algorithm utilizes the Newton-Raph...This research proposes an improved Puma optimization algorithm(IPuma)as a novel dynamic recon-figuration tool for a photovoltaic(PV)array linked in total-cross-tied(TCT).The proposed algorithm utilizes the Newton-Raphson search rule(NRSR)to boost the exploration process,especially in search spaces with more local regions,and boost the exploitation with adaptive parameters alternating with random parameters in the original Puma.The effectiveness of the introduced IPuma is confirmed through comprehensive evaluations on the CEC’20 benchmark problems.It shows superior performance compared to both established and modern metaheuristic algorithms in terms of effectively navigating the search space and achieving convergence towards near-optimal regions.The findings indicated that the IPuma algorithm demonstrates considerable statistical promise and surpasses the performance of competing algorithms.In addition,the proposed IPuma is utilized to reconfigure a 9×9 PV array that operates under different shade patterns,such as lower triangular(LT),long wide(LW),and short wide(SW).In addition to other programmed approaches,such as the Whale optimization algorithm(WOA),grey wolf optimizer(GWO),Harris Hawks optimization(HHO),particle swarm optimization(PSO),gravitational search algorithm(GSA),biogeography-based optimization(BBO),sine cosine algorithm(SCA),equilibrium optimizer(EO),and original Puma,the indicated method is contrasted to the traditional configurations of TCT and Sudoku.In addition,the metrics of mismatch power loss,maximum efficiency improvement,efficiency improvement ratio,and peak-to-mean ratio are calculated to assess the effectiveness of the indicated approach.The proposed IPuma improved the generated power by 36.72%,28.03%,and 40.97%for SW,LW,and LT,respectively,outperforming the TCT configuration.In addition,it achieved the best maximum efficiency improvement among the algorithms considered,with 26.86%,21.89%,and 29.07%for the examined patterns.The results highlight the superiority and competence of the proposed approach in both convergence rates and stability,as well as applicability to dynamically reconfigure the PV system and enhance its harvested energy.展开更多
Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for opti...Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for optimal coverage,ranking further refines their execution order to detect critical faults earlier.This study investigates machine learning techniques to enhance both prioritization and ranking,contributing to more effective and efficient testing processes.We first employ advanced feature engineering alongside ensemble models,including Gradient Boosted,Support Vector Machines,Random Forests,and Naive Bayes classifiers to optimize test case prioritization,achieving an accuracy score of 0.98847 and significantly improving the Average Percentage of Fault Detection(APFD).Subsequently,we introduce a deep Q-learning framework combined with a Genetic Algorithm(GA)to refine test case ranking within priority levels.This approach achieves a rank accuracy of 0.9172,demonstrating robust performance despite the increasing computational demands of specialized variation operators.Our findings highlight the effectiveness of stacked ensemble learning and reinforcement learning in optimizing test case prioritization and ranking.This integrated approach improves testing efficiency,reduces late-stage defects,and improves overall software stability.The study provides valuable information for AI-driven testing frameworks,paving the way for more intelligent and adaptive software quality assurance methodologies.展开更多
To address the issues of insufficient and imbalanced data samples in proton exchange membrane fuel cell(PEMFC)performance degradation prediction,this study proposes a data augmentation-based model to predict PEMFC per...To address the issues of insufficient and imbalanced data samples in proton exchange membrane fuel cell(PEMFC)performance degradation prediction,this study proposes a data augmentation-based model to predict PEMFC performance degradation.Firstly,an improved generative adversarial network(IGAN)with adaptive gradient penalty coefficient is proposed to address the problems of excessively fast gradient descent and insufficient diversity of generated samples.Then,the IGANis used to generate datawith a distribution analogous to real data,therebymitigating the insufficiency and imbalance of original PEMFC samples and providing the predictionmodel with training data rich in feature information.Finally,a convolutional neural network-bidirectional long short-termmemory(CNN-BiLSTM)model is adopted to predict PEMFC performance degradation.Experimental results show that the data generated by the proposed IGAN exhibits higher quality than that generated by the original GAN,and can fully characterize and enrich the original data’s features.Using the augmented data,the prediction accuracy of the CNN-BiLSTM model is significantly improved,rendering it applicable to tasks of predicting PEMFC performance degradation.展开更多
The internal flow fields within a three-dimensional inward-tunning combined inlet are extremely complex,especially during the engine mode transition,where the tunnel changes may impact the flow fields significantly.To...The internal flow fields within a three-dimensional inward-tunning combined inlet are extremely complex,especially during the engine mode transition,where the tunnel changes may impact the flow fields significantly.To develop an efficient flow field reconstruction model for this,we present an Improved Conditional Denoising Diffusion Generative Adversarial Network(ICDDGAN),which integrates Conditional Denoising Diffusion Probabilistic Models(CDDPMs)with Style GAN,and introduce a reconstruction discrimination mechanism and dynamic loss weight learning strategy.We establish the Mach number flow field dataset by numerical simulation at various backpressures for the mode transition process from turbine mode to ejector ramjet mode at Mach number 2.5.The proposed ICDDGAN model,given only sparse parameter information,can rapidly generate high-quality Mach number flow fields without a large number of samples for training.The results show that ICDDGAN is superior to CDDGAN in terms of training convergence and stability.Moreover,the interpolation and extrapolation test results during backpressure conditions show that ICDDGAN can accurately and quickly reconstruct Mach number fields at various tunnel slice shapes,with a Structural Similarity Index Measure(SSIM)of over 0.96 and a Mean-Square Error(MSE)of 0.035%to actual flow fields,reducing time costs by 7-8 orders of magnitude compared to Computational Fluid Dynamics(CFD)calculations.This can provide an efficient means for rapid computation of complex flow fields.展开更多
An optimized volt-ampere reactive(VAR)control framework is proposed for transmission-level power systems to simultaneously mitigate voltage deviations and active-power losses through coordinated control of large-scale...An optimized volt-ampere reactive(VAR)control framework is proposed for transmission-level power systems to simultaneously mitigate voltage deviations and active-power losses through coordinated control of large-scale wind/solar farms with shunt static var generators(SVGs).The model explicitly represents reactive-power regulation characteristics of doubly-fed wind turbines and PV inverters under real-time meteorological conditions,and quantifies SVG high-speed compensation capability,enabling seamless transition from localized VAR management to a globally coordinated strategy.An enhanced adaptive gain-sharing knowledge optimizer(AGSK-SD)integrates simulated annealing and diversity maintenance to autonomously tune voltage-control actions,renewable source reactive-power set-points,and SVG output.The algorithm adaptively modulates knowledge factors and ratios across search phases,performs SA-based fine-grained local exploitation,and periodically re-injects population diversity to prevent premature convergence.Comprehensive tests on IEEE 9-bus and 39-bus systems demonstrate AGSK-SD’s superiority over NSGA-II and MOPSO in hypervolume(HV),inverse generative distance(IGD),and spread metrics while maintaining acceptable computational burden.The method reduces network losses from 2.7191 to 2.15 MW(20.79%reduction)and from 15.1891 to 11.22 MW(26.16%reduction)in the 9-bus and 39-bus systems respectively.Simultaneously,the cumulative voltage-deviation index decreases from 0.0277 to 3.42×10^(−4) p.u.(98.77%reduction)in the 9-bus system,and from 0.0556 to 0.0107 p.u.(80.76%reduction)in the 39-bus system.These improvements demonstrate significant suppression of line losses and voltage fluctuations.Comparative analysis with traditional heuristic optimization algorithms confirms the superior performance of the proposed approach.展开更多
With the intensive deployment of users and the drastic increase of traffic load, a millimeter wave （mmWave） backhaul network was widely investigated. A typical mmWave backhaul network consists of the macro base stat...With the intensive deployment of users and the drastic increase of traffic load, a millimeter wave （mmWave） backhaul network was widely investigated. A typical mmWave backhaul network consists of the macro base station （MBS） and the small base stations （SBSs）. How to efficiently associate users with the MBS and the SBSs for load balancing is a key issue in the network. By adding a virtual power bias to the SBSs, more users can access to the SBSs to share the load of the MBS. The bias values shall be set reasonably to guarantee the backhaul efficiency and the quality of service （QoS）. An improved Q-learning algorithm is proposed to effectively adjust the bias value for each SBS. In the proposed algorithm, each SBS becomes an agent with independent learning and can achieve the best behavior, namely the optimal bias value through a series of training. Besides, an improved behavior selection mechanism is adopted to improve the learning efficiency and accelerate the convergence of the algorithm. Finally, simulations conducted in the 60 GHz band demonstrate the superior performance of the proposed algorithm in backhaul efficiency and user outage probability.展开更多
针对无监督环境下传统网络异常诊断算法存在异常点定位和异常数据分类准确率低等不足,通过设计一种基于改进Q-learning算法的无线网络异常诊断方法:首先基于ADU(Asynchronous Data Unit异步数据单元)单元采集无线网络的数据流,并提取数...针对无监督环境下传统网络异常诊断算法存在异常点定位和异常数据分类准确率低等不足,通过设计一种基于改进Q-learning算法的无线网络异常诊断方法:首先基于ADU(Asynchronous Data Unit异步数据单元)单元采集无线网络的数据流,并提取数据包特征;然后构建Q-learning算法模型探索状态值和奖励值的平衡点,利用SA(Simulated Annealing模拟退火)算法从全局视角对下一时刻状态进行精确识别;最后确定训练样本的联合分布概率,提升输出值的逼近性能以达到平衡探索与代价之间的均衡。测试结果显示:改进Q-learning算法的网络异常定位准确率均值达99.4%,在不同类型网络异常的分类精度和分类效率等方面,也优于三种传统网络异常诊断方法。展开更多
基金funded by Hung Yen University of Technology and Education under grand number UTEHY.L.2025.62.
文摘Unmanned Aerial Vehicles(UAVs)have become integral components in smart city infrastructures,supporting applications such as emergency response,surveillance,and data collection.However,the high mobility and dynamic topology of Flying Ad Hoc Networks(FANETs)present significant challenges for maintaining reliable,low-latency communication.Conventional geographic routing protocols often struggle in situations where link quality varies and mobility patterns are unpredictable.To overcome these limitations,this paper proposes an improved routing protocol based on reinforcement learning.This new approach integrates Q-learning with mechanisms that are both link-aware and mobility-aware.The proposed method optimizes the selection of relay nodes by using an adaptive reward function that takes into account energy consumption,delay,and link quality.Additionally,a Kalman filter is integrated to predict UAV mobility,improving the stability of communication links under dynamic network conditions.Simulation experiments were conducted using realistic scenarios,varying the number of UAVs to assess scalability.An analysis was conducted on key performance metrics,including the packet delivery ratio,end-to-end delay,and total energy consumption.The results demonstrate that the proposed approach significantly improves the packet delivery ratio by 12%–15%and reduces delay by up to 25.5%when compared to conventional GEO and QGEO protocols.However,this improvement comes at the cost of higher energy consumption due to additional computations and control overhead.Despite this trade-off,the proposed solution ensures reliable and efficient communication,making it well-suited for large-scale UAV networks operating in complex urban environments.
基金supported by the Princess Nourah bint Abdulrahman University Researchers Supporting Project,number PNURSP2025R757Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The integration of High-Altitude Platform Stations(HAPS)with Reconfigurable Intelligent Surfaces(RIS)represents a critical advancement for next-generation wireless networks,offering unprecedented opportunities for ubiquitous connectivity.However,existing research reveals significant gaps in dynamic resource allocation,joint optimization,and equitable service provisioning under varying channel conditions,limiting practical deployment of these technologies.This paper addresses these challenges by proposing a novel Fairness-Aware Deep Q-Learning(FAIRDQL)framework for joint resource management and phase configuration in HAPS-RIS systems.Our methodology employs a comprehensive three-tier algorithmic architecture integrating adaptive power control,priority-based user scheduling,and dynamic learning mechanisms.The FAIR-DQL approach utilizes advanced reinforcement learning with experience replay and fairness-aware reward functions to balance competing objectives while adapting to dynamic environments.Key findings demonstrate substantial improvements:9.15 dB SINR gain,12.5 bps/Hz capacity,78%power efficiency,and 0.82 fairness index.The framework achieves rapid 40-episode convergence with consistent delay performance.These contributions establish new benchmarks for fairness-aware resource allocation in aerial communications,enabling practical HAPS-RIS deployments in rural connectivity,emergency communications,and urban networks.
基金supported by the National Natural Science Foundation of China(Grant No.52374156).
文摘To address low learning efficiency and inadequate path safety in spraying robot navigation within complex obstacle-rich environments—with dense,dynamic,unpredictable obstacles challenging conventional methods—this paper proposes a hybrid algorithm integrating Q-learning and improved A*-Artificial Potential Field(A-APF).Centered on theQ-learning framework,the algorithmleverages safety-oriented guidance generated byA-APF and employs a dynamic coordination mechanism that adaptively balances exploration and exploitation.The proposed system comprises four core modules:(1)an environment modeling module that constructs grid-based obstacle maps;(2)an A-APF module that combines heuristic search from A*algorithm with repulsive force strategies from APF to generate guidance;(3)a Q-learning module that learns optimal state-action values(Q-values)through spraying robot-environment interaction and a reward function emphasizing path optimality and safety;and(4)a dynamic optimization module that ensures adaptive cooperation between Q-learning and A-APF through exploration rate control and environment-aware constraints.Simulation results demonstrate that the proposed method significantly enhances path safety in complex underground mining environments.Quantitative results indicate that,compared to the traditional Q-learning algorithm,the proposed method shortens training time by 42.95% and achieves a reduction in training failures from 78 to just 3.Compared to the static fusion algorithm,it further reduces both training time(by 10.78%)and training failures(by 50%),thereby improving overall training efficiency.
基金funded by the Deanship of Scientific Research and Libraries,Princess Nourah bint Abdulrahman University,through the Program of Research Project Funding After Publication,grant No.(RPFAP-82-1445)。
文摘This research proposes an improved Puma optimization algorithm(IPuma)as a novel dynamic recon-figuration tool for a photovoltaic(PV)array linked in total-cross-tied(TCT).The proposed algorithm utilizes the Newton-Raphson search rule(NRSR)to boost the exploration process,especially in search spaces with more local regions,and boost the exploitation with adaptive parameters alternating with random parameters in the original Puma.The effectiveness of the introduced IPuma is confirmed through comprehensive evaluations on the CEC’20 benchmark problems.It shows superior performance compared to both established and modern metaheuristic algorithms in terms of effectively navigating the search space and achieving convergence towards near-optimal regions.The findings indicated that the IPuma algorithm demonstrates considerable statistical promise and surpasses the performance of competing algorithms.In addition,the proposed IPuma is utilized to reconfigure a 9×9 PV array that operates under different shade patterns,such as lower triangular(LT),long wide(LW),and short wide(SW).In addition to other programmed approaches,such as the Whale optimization algorithm(WOA),grey wolf optimizer(GWO),Harris Hawks optimization(HHO),particle swarm optimization(PSO),gravitational search algorithm(GSA),biogeography-based optimization(BBO),sine cosine algorithm(SCA),equilibrium optimizer(EO),and original Puma,the indicated method is contrasted to the traditional configurations of TCT and Sudoku.In addition,the metrics of mismatch power loss,maximum efficiency improvement,efficiency improvement ratio,and peak-to-mean ratio are calculated to assess the effectiveness of the indicated approach.The proposed IPuma improved the generated power by 36.72%,28.03%,and 40.97%for SW,LW,and LT,respectively,outperforming the TCT configuration.In addition,it achieved the best maximum efficiency improvement among the algorithms considered,with 26.86%,21.89%,and 29.07%for the examined patterns.The results highlight the superiority and competence of the proposed approach in both convergence rates and stability,as well as applicability to dynamically reconfigure the PV system and enhance its harvested energy.
文摘Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for optimal coverage,ranking further refines their execution order to detect critical faults earlier.This study investigates machine learning techniques to enhance both prioritization and ranking,contributing to more effective and efficient testing processes.We first employ advanced feature engineering alongside ensemble models,including Gradient Boosted,Support Vector Machines,Random Forests,and Naive Bayes classifiers to optimize test case prioritization,achieving an accuracy score of 0.98847 and significantly improving the Average Percentage of Fault Detection(APFD).Subsequently,we introduce a deep Q-learning framework combined with a Genetic Algorithm(GA)to refine test case ranking within priority levels.This approach achieves a rank accuracy of 0.9172,demonstrating robust performance despite the increasing computational demands of specialized variation operators.Our findings highlight the effectiveness of stacked ensemble learning and reinforcement learning in optimizing test case prioritization and ranking.This integrated approach improves testing efficiency,reduces late-stage defects,and improves overall software stability.The study provides valuable information for AI-driven testing frameworks,paving the way for more intelligent and adaptive software quality assurance methodologies.
基金supported by the Jiangsu Engineering Research Center of the Key Technology for Intelligent Manufacturing Equipment and the Suqian Key Laboratory of Intelligent Manufacturing(Grant No.M202108).
文摘To address the issues of insufficient and imbalanced data samples in proton exchange membrane fuel cell(PEMFC)performance degradation prediction,this study proposes a data augmentation-based model to predict PEMFC performance degradation.Firstly,an improved generative adversarial network(IGAN)with adaptive gradient penalty coefficient is proposed to address the problems of excessively fast gradient descent and insufficient diversity of generated samples.Then,the IGANis used to generate datawith a distribution analogous to real data,therebymitigating the insufficiency and imbalance of original PEMFC samples and providing the predictionmodel with training data rich in feature information.Finally,a convolutional neural network-bidirectional long short-termmemory(CNN-BiLSTM)model is adopted to predict PEMFC performance degradation.Experimental results show that the data generated by the proposed IGAN exhibits higher quality than that generated by the original GAN,and can fully characterize and enrich the original data’s features.Using the augmented data,the prediction accuracy of the CNN-BiLSTM model is significantly improved,rendering it applicable to tasks of predicting PEMFC performance degradation.
文摘The internal flow fields within a three-dimensional inward-tunning combined inlet are extremely complex,especially during the engine mode transition,where the tunnel changes may impact the flow fields significantly.To develop an efficient flow field reconstruction model for this,we present an Improved Conditional Denoising Diffusion Generative Adversarial Network(ICDDGAN),which integrates Conditional Denoising Diffusion Probabilistic Models(CDDPMs)with Style GAN,and introduce a reconstruction discrimination mechanism and dynamic loss weight learning strategy.We establish the Mach number flow field dataset by numerical simulation at various backpressures for the mode transition process from turbine mode to ejector ramjet mode at Mach number 2.5.The proposed ICDDGAN model,given only sparse parameter information,can rapidly generate high-quality Mach number flow fields without a large number of samples for training.The results show that ICDDGAN is superior to CDDGAN in terms of training convergence and stability.Moreover,the interpolation and extrapolation test results during backpressure conditions show that ICDDGAN can accurately and quickly reconstruct Mach number fields at various tunnel slice shapes,with a Structural Similarity Index Measure(SSIM)of over 0.96 and a Mean-Square Error(MSE)of 0.035%to actual flow fields,reducing time costs by 7-8 orders of magnitude compared to Computational Fluid Dynamics(CFD)calculations.This can provide an efficient means for rapid computation of complex flow fields.
基金supported by Yunnan Power Grid Co.,Ltd.Science and Technology Project:Research and application of key technologies for graphical-based power grid accident reconstruction and simulation(YNKJXM20240333).
文摘An optimized volt-ampere reactive(VAR)control framework is proposed for transmission-level power systems to simultaneously mitigate voltage deviations and active-power losses through coordinated control of large-scale wind/solar farms with shunt static var generators(SVGs).The model explicitly represents reactive-power regulation characteristics of doubly-fed wind turbines and PV inverters under real-time meteorological conditions,and quantifies SVG high-speed compensation capability,enabling seamless transition from localized VAR management to a globally coordinated strategy.An enhanced adaptive gain-sharing knowledge optimizer(AGSK-SD)integrates simulated annealing and diversity maintenance to autonomously tune voltage-control actions,renewable source reactive-power set-points,and SVG output.The algorithm adaptively modulates knowledge factors and ratios across search phases,performs SA-based fine-grained local exploitation,and periodically re-injects population diversity to prevent premature convergence.Comprehensive tests on IEEE 9-bus and 39-bus systems demonstrate AGSK-SD’s superiority over NSGA-II and MOPSO in hypervolume(HV),inverse generative distance(IGD),and spread metrics while maintaining acceptable computational burden.The method reduces network losses from 2.7191 to 2.15 MW(20.79%reduction)and from 15.1891 to 11.22 MW(26.16%reduction)in the 9-bus and 39-bus systems respectively.Simultaneously,the cumulative voltage-deviation index decreases from 0.0277 to 3.42×10^(−4) p.u.(98.77%reduction)in the 9-bus system,and from 0.0556 to 0.0107 p.u.(80.76%reduction)in the 39-bus system.These improvements demonstrate significant suppression of line losses and voltage fluctuations.Comparative analysis with traditional heuristic optimization algorithms confirms the superior performance of the proposed approach.
基金supported by the State Major Science and Technique Project (MJ-2014-S-37)the 111 Project (B08038)
文摘With the intensive deployment of users and the drastic increase of traffic load, a millimeter wave （mmWave） backhaul network was widely investigated. A typical mmWave backhaul network consists of the macro base station （MBS） and the small base stations （SBSs）. How to efficiently associate users with the MBS and the SBSs for load balancing is a key issue in the network. By adding a virtual power bias to the SBSs, more users can access to the SBSs to share the load of the MBS. The bias values shall be set reasonably to guarantee the backhaul efficiency and the quality of service （QoS）. An improved Q-learning algorithm is proposed to effectively adjust the bias value for each SBS. In the proposed algorithm, each SBS becomes an agent with independent learning and can achieve the best behavior, namely the optimal bias value through a series of training. Besides, an improved behavior selection mechanism is adopted to improve the learning efficiency and accelerate the convergence of the algorithm. Finally, simulations conducted in the 60 GHz band demonstrate the superior performance of the proposed algorithm in backhaul efficiency and user outage probability.
文摘针对无监督环境下传统网络异常诊断算法存在异常点定位和异常数据分类准确率低等不足,通过设计一种基于改进Q-learning算法的无线网络异常诊断方法:首先基于ADU(Asynchronous Data Unit异步数据单元)单元采集无线网络的数据流,并提取数据包特征;然后构建Q-learning算法模型探索状态值和奖励值的平衡点,利用SA(Simulated Annealing模拟退火)算法从全局视角对下一时刻状态进行精确识别;最后确定训练样本的联合分布概率,提升输出值的逼近性能以达到平衡探索与代价之间的均衡。测试结果显示:改进Q-learning算法的网络异常定位准确率均值达99.4%,在不同类型网络异常的分类精度和分类效率等方面,也优于三种传统网络异常诊断方法。
