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
Backoff mechanism is a key component of contention-based medium access control（MAC） layer protocol.It has been shown that the backoff mechanism of IEEE 802.11 standard may be very inefficient especially when the net...Backoff mechanism is a key component of contention-based medium access control（MAC） layer protocol.It has been shown that the backoff mechanism of IEEE 802.11 standard may be very inefficient especially when the network is congested.Numbers of methods have been proposed to tune the contention window（CW） with the aim to achieve the optimal throughput in IEEE 802.11 WLANs.However,the mechanisms do not specifically address proper settings for the variable packet length influence and CW diverging problem.This paper proposes a novel four-way handshaking full-feedback backoff algorithm named adoptive contention window backoff（ACWB） to overcome these drawbacks.The performance of the proposed algorithm is investigated through analysis and simulation.Simulation results demonstrate that the ACWB algorithm provides a remarkable performance improvement in terms of short-term fairness,packet delay and delay jitter,while maintaining an optimal throughput close to the theoretical throughput limit of the IEEE 802.11 distributed coordination function（DCF） access scheme.展开更多
In Underwater Wireless Sensor Networks(UWSNs),protocols with definite contention windows fail to adapt to changing network conditions,resulting in channel congestion and collisions.This paper introduces the Adaptive L...In Underwater Wireless Sensor Networks(UWSNs),protocols with definite contention windows fail to adapt to changing network conditions,resulting in channel congestion and collisions.This paper introduces the Adaptive Load-based Contention Window Medium Access Control(ALCW-MAC)protocol,which improves the backoff mechanism of the Contention Window Medium Access Control(CW-MAC)protocol.The ALCW-MAC protocol calculates a collision busy factor to evaluate the system load more accurately and dynamically adjusts the contention window size based on the average collision rate and channel busy rate.These dynamic adjustments enable the protocol to reflect real-time network loads,resulting in channel congestion reduction and bandwidth efficiency improvement.Comprehensive experimental results confirm that ALCW-MAC surpasses CW-MAC in throughput and packet loss rate,significantly enhancing network performance and stability.展开更多
With the boom of wireless devices, the number of wireless users under wireless local area networks （WLANs） has increased dramatically. However, the standard baekoff mechanism in IEEE 802.11 adopts fixed initial cont...With the boom of wireless devices, the number of wireless users under wireless local area networks （WLANs） has increased dramatically. However, the standard baekoff mechanism in IEEE 802.11 adopts fixed initial contention window （CW） size without considering changes of network load, which leads to a high collision probability and low channel utilization in bursty arrivals. In this paper, a novel CW dynamic adjustment scheme is proposed to achieve high throughput performance in dense user environment. In the proposed scheme, the initial CW size is dynamically adjusted to optimum according to the measured packet collision probability. Simulation results show that the proposed scheme can significantly improve the throughput performance.展开更多
In view of the problem that existing Media Access Control(MAC) protocols can not pro-vide real-time monitor on network conditions,this paper puts forward a new MAC protocol- Predict and Feedback MAC(PFMAC) which can p...In view of the problem that existing Media Access Control(MAC) protocols can not pro-vide real-time monitor on network conditions,this paper puts forward a new MAC protocol- Predict and Feedback MAC(PFMAC) which can predict the channel's congestion level reasonably.The dominant idea of the new scheme is to record the channel's busy or idle situation in the backoff stage by sending Sensor Nodes(SNs),and according to the congestion level every SN can change the contention window adaptively when send packets successfully to minimize collisions,saving energy and channel resources.The result of simulation shows that compared with other MAC protocols,the PFMAC protocol can improve network throughput and reduce energy consumption in high speed network en-vironment.展开更多
Guaranteed quality of service(QoS) support has been an open issue of distributed wireless networks for years. The IEEE802.11 e provides a valuable method for this purpose. However, it could only provide service differ...Guaranteed quality of service(QoS) support has been an open issue of distributed wireless networks for years. The IEEE802.11 e provides a valuable method for this purpose. However, it could only provide service differentiation, rather than service guarantee, for multi-priority traffic. Many studies have tried to improve its QoS ability, but still leave some problems. This paper investigates these problems and proposes a scheme called the priority access based on busy tone(PABT) to improve the Qo S performance. To guarantee the priority channel access, this scheme uses an in-band busy tone to limit the transmission of lower-priority traffic when higher-priority traffic has packets to send. Based on that, it also optimizes the contention window tuning according to the flows number of each traffic type individually, in order to improve the throughput as well as the traffic capacity. Simulation results show that the proposed scheme significantly improves the real-time traffic capacity, throughput, delay, fairness and packet loss rate.展开更多
IEEE 802.11 distributed coordination function(DCF)can alleviate the collision and hidden station problem,but it doesn't differentiate traffic categories(TC).Therefore,it can't provide sufficient quality of ser...IEEE 802.11 distributed coordination function(DCF)can alleviate the collision and hidden station problem,but it doesn't differentiate traffic categories(TC).Therefore,it can't provide sufficient quality of service(QoS)support for different TC.Recently,a new contention-based enhanced distributed channel access(EDCA)scheme is proposed which provides a probabilistic QoS support.In this paper,an improved EDCA scheme for service differentiation in ad hoc networks is proposed.In this scheme,signal channel resistance coefficient is used to adjust the contention window(CW).It proves that the scheme provides the traffic differentiation,high throughput and low delay through simulation.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Backoff mechanism is a key component of contention-based medium access control（MAC） layer protocol.It has been shown that the backoff mechanism of IEEE 802.11 standard may be very inefficient especially when the network is congested.Numbers of methods have been proposed to tune the contention window（CW） with the aim to achieve the optimal throughput in IEEE 802.11 WLANs.However,the mechanisms do not specifically address proper settings for the variable packet length influence and CW diverging problem.This paper proposes a novel four-way handshaking full-feedback backoff algorithm named adoptive contention window backoff（ACWB） to overcome these drawbacks.The performance of the proposed algorithm is investigated through analysis and simulation.Simulation results demonstrate that the ACWB algorithm provides a remarkable performance improvement in terms of short-term fairness,packet delay and delay jitter,while maintaining an optimal throughput close to the theoretical throughput limit of the IEEE 802.11 distributed coordination function（DCF） access scheme.
基金supported by the National Natural Science Foundation of China(No.62372131).
文摘In Underwater Wireless Sensor Networks(UWSNs),protocols with definite contention windows fail to adapt to changing network conditions,resulting in channel congestion and collisions.This paper introduces the Adaptive Load-based Contention Window Medium Access Control(ALCW-MAC)protocol,which improves the backoff mechanism of the Contention Window Medium Access Control(CW-MAC)protocol.The ALCW-MAC protocol calculates a collision busy factor to evaluate the system load more accurately and dynamically adjusts the contention window size based on the average collision rate and channel busy rate.These dynamic adjustments enable the protocol to reflect real-time network loads,resulting in channel congestion reduction and bandwidth efficiency improvement.Comprehensive experimental results confirm that ALCW-MAC surpasses CW-MAC in throughput and packet loss rate,significantly enhancing network performance and stability.
基金supported by the WLAN Achievement Transformation Based on Software-Defined Networking of Beijing Municipal Commission of Education (201501001)the National Natural Science Foundation of China (61671073)
文摘With the boom of wireless devices, the number of wireless users under wireless local area networks （WLANs） has increased dramatically. However, the standard baekoff mechanism in IEEE 802.11 adopts fixed initial contention window （CW） size without considering changes of network load, which leads to a high collision probability and low channel utilization in bursty arrivals. In this paper, a novel CW dynamic adjustment scheme is proposed to achieve high throughput performance in dense user environment. In the proposed scheme, the initial CW size is dynamically adjusted to optimum according to the measured packet collision probability. Simulation results show that the proposed scheme can significantly improve the throughput performance.
基金Supported by the 948 Project (2012-4-21)the Ph.D.Programs Foundation of Ministry of Education of China(20100062120008)the Scientific Research Fund of Heilongjiang Provincial Education Department(11553022)
文摘In view of the problem that existing Media Access Control(MAC) protocols can not pro-vide real-time monitor on network conditions,this paper puts forward a new MAC protocol- Predict and Feedback MAC(PFMAC) which can predict the channel's congestion level reasonably.The dominant idea of the new scheme is to record the channel's busy or idle situation in the backoff stage by sending Sensor Nodes(SNs),and according to the congestion level every SN can change the contention window adaptively when send packets successfully to minimize collisions,saving energy and channel resources.The result of simulation shows that compared with other MAC protocols,the PFMAC protocol can improve network throughput and reduce energy consumption in high speed network en-vironment.
基金supported by the Special Fund for National Defense Technology Innovation(18-163-11-ZT-003-027-01)
文摘Guaranteed quality of service(QoS) support has been an open issue of distributed wireless networks for years. The IEEE802.11 e provides a valuable method for this purpose. However, it could only provide service differentiation, rather than service guarantee, for multi-priority traffic. Many studies have tried to improve its QoS ability, but still leave some problems. This paper investigates these problems and proposes a scheme called the priority access based on busy tone(PABT) to improve the Qo S performance. To guarantee the priority channel access, this scheme uses an in-band busy tone to limit the transmission of lower-priority traffic when higher-priority traffic has packets to send. Based on that, it also optimizes the contention window tuning according to the flows number of each traffic type individually, in order to improve the throughput as well as the traffic capacity. Simulation results show that the proposed scheme significantly improves the real-time traffic capacity, throughput, delay, fairness and packet loss rate.
文摘IEEE 802.11 distributed coordination function(DCF)can alleviate the collision and hidden station problem,but it doesn't differentiate traffic categories(TC).Therefore,it can't provide sufficient quality of service(QoS)support for different TC.Recently,a new contention-based enhanced distributed channel access(EDCA)scheme is proposed which provides a probabilistic QoS support.In this paper,an improved EDCA scheme for service differentiation in ad hoc networks is proposed.In this scheme,signal channel resistance coefficient is used to adjust the contention window(CW).It proves that the scheme provides the traffic differentiation,high throughput and low delay through simulation.
