Online end‐to‐end quality of service monitoring for service level agreement management

A major challenge in network and service level agreement (SLA) management is to provide Quality of Service (QoS) demanded by heterogeneous network applications. Online QoS monitoring plays an important role in the process by providing objective measurements that can be used for improving network design, troubleshooting and management. Online QoS monitoring becomes increasingly difficult and complex due to the rapid expansion of the Internet and the dramatic increase in the speed of network. Sampling techniques have been explored as a means to reduce the difficulty and complexity of measurement. In this paper, we investigate several major sampling techniques, i.e. systematic sampling, simple random sampling and stratified sampling. Performance analysis is conducted on these techniques. It is shown that stratified sampling with optimum allocation has the best performance. However, stratified sampling with optimum allocation requires additional statistics usually not available for real‐time applications. An adaptive stratified sampling algorithm is proposed to solve the problem. Both theoretical analysis and simulation show that the proposed adaptive stratified sampling algorithm outperforms other sampling techniques and achieves a performance comparable to stratified sampling with optimum allocation. A QoS monitoring software using the aforementioned sampling techniques is designed and tested in various real networks. Copyright © 2007 John Wiley & Sons, Ltd.     

QoS‐aware routing and power control algorithm for multimedia service over multi‐hop mobile ad hoc network

This paper presents a QoS (quality of service) aware routing and power control algorithm consuming low transmission power for multimedia service over mobile ad hoc network. Generally, multimedia services need stringent QoS over the network. However, it is not easy to guarantee the QoS over mobile ad hoc network since its network resources are very limited and time‐varying. Furthermore, only a limited amount of power is available at mobile nodes, which makes the problem more challenging. We propose an effective routing and power control algorithm for multimedia services that satisfies end‐to‐end delay constraint with low transmission power consumption. The proposed algorithm supports the required bandwidth by controlling each link channel quality over route in a tolerable range. In addition, a simple but effective route maintenance mechanism is implemented to avoid link failures that may significantly degrade streaming video quality. Finally, performance comparison with existing algorithms is presented in respect to traditional routing performance metrics, and an achievable video quality comparison is provided to demonstrate the superiority of the proposed algorithm for multimedia services over mobile ad hoc network. Copyright © 2010 John Wiley & Sons, Ltd.     

区分服务结构及其TCP性能分析

本文首先对区分服务(DiffServ)结构中的边缘路由器和核心路由器机制进行了系统的分类研究,分析并比较了各种机制.接着,对区分服务结构中TCP的性能问题进行了研究,总结了国内外对这一问题的仿真、解析模型分析和实验研究的成果.找出了关键的问题所在,并根据我们的研究成果提出了一些区分服务结构本身的改进建议.     

一种综合缓存管理和主动队列管理的 区分服务节点机制

随着网络和应用的飞速发展,Internet不仅要提供尽力转发(Best Effort)的服务,还要支持各种传输类型和多个优先级的QoS服务.目前普遍认为区分服务体系机构是很有前途的提供QoS保证的Internet框架,而网络节点机制是其关键技术之一.我们提出了一种在网络节点上实现的区分服务机制comBAQ(combining Buffer Management and Active Queue Management),它综合了适当的缓存管理和主动队列管理方法.我们详细介绍了它的服务框架和分组处理判决算法,实验模拟结果显示,它能满足我们提出来的五个设计目标,可以在网络节点上实现多个丢失优先级的区分服务:为需要可靠传输的多媒体应用提供"有保证"服务,为传统TCP传输提供"无保证"服务.     

Energy‐delay‐aware caching strategy in green CCN using markov approximation

One of the basic challenges in content‐centric networking (CCN) is how to optimize the overall energy consumption of content transmission and caching. Furthermore, designing an appropriate caching policy that considers both energy consumption and quality of service (QoS) is a major goal in green CCN. In this paper, the problem of minimizing the total CCN energy consumption while being aware of the end‐to‐end delay is formulated as an integer linear programming model. Since it is an Non‐deterministic Polynomial‐time (NP)‐hard problem, the Markov approximation method for an energy‐delay aware caching strategy (MAEDC) is proposed through a log‐sum‐exp function to find a near‐optimal solution in a distributed manner. The numerical results show that the MAEDC achieves near‐optimal energy consumption with better delay profile compared with the optimal solution. Moreover, due to the possibility of distributed and parallel processing, the proposed method is proper for the online situation where the delay is a crucial issue.     

Performance analysis of hop‐limited epidemic routing in DTN with limited forwarding times

Because of the uncertainty of transmission opportunity in delay tolerant networks (DTN), routing algorithms in DTN often need nodes to serve as relays for others to carry and forward messages. One classic policy is the Epidemic routing (ER) algorithm. To reduce the overhead, the hop‐limited ER protocol is proposed. This method can get better performance through controlling the message hop count. However, because of the energy constraint or other factors, each node may forward only limited times, that is, both the message hop count and the forwarding times may be limited. This paper proposes a unifying framework to evaluate the performance of ER with the aforementioned constraints. Simulations based on both synthetic and real motion traces show the accuracy of the framework. In addition, we explore the impact of many parameters (e.g., message hop count) through extensive numerical results. For example, numerical results show that both the message hop count and the forwarding times can have certain impact on the routing performance, but their impact is related with many other factors (e.g., the number of nodes). Copyright © 2014 John Wiley & Sons, Ltd.     

Improving MANET performance by a hop‐aware and energy‐based buffer management scheme

A hop‐aware and energy‐based buffer management scheme (HEB) is proposed in this paper. HEB can provide better quality of service to packets with real‐time requirements and improve MANET power efficiency. In our algorithm, the buffer is divided into real‐time and non‐real‐time partitions. We consider the number of hops passed, the power levels of the transmitting node, the predicted number of remaining hops, and waiting time in the buffer to determine packet transmission priority. In addition, specialized queue management and a probabilistic scheduling algorithm are proposed to decrease retransmissions caused by packet losses. Mathematical derivations of loss rates and end‐to‐end delays are also proposed. Coincidence between mathematical and simulation results is also shown. Finally, the HEB is compared with first in first out, random early detection, and hop‐aware buffering scheme. Simulation results show that the proposed algorithm reduces loss rates, power consumption, and end‐to‐end delays for real‐time traffic, considerably improving the efficiency of queue management in MANET. Copyright © 2012 John Wiley & Sons, Ltd.     

An adaptive‐aware energy and queue improvement of AOMDV

Because the node energy and network resources in the wireless sensor network (WSN) are very finite, it is necessary to distribute data traffic reasonably and achieve network load balancing. Ad hoc on‐demand multipath distance vector (AOMDV) is a widely used routing protocol in WSN, but it has some deficiencies: establishes the route by only using hop counts as the routing criterion without considering other factors such as energy consumption and network load; forwards route request in fixed delay resulting in building the nonoptimal path; and cannot update the path status after built paths. For the deficiency of AOMDV, this paper proposes a multipath routing protocol adaptive energy and queue AOMDV (AEQAOMDV) based on adaptively sensing node residual energy and buffer queue length. When sending a routing request, the forwarding delay of the routing request is adaptively adjusted by both the residual energy and the queue length of the intermediate node; when establishing routes, a fitness is defined as a routing criterion according to the link energy and the queue load, predicting the available duration of the node based on the energy consumption rate and adjusting the weight of the routing criterion by the available duration of the node; after the routes are established, the path information status are updated via periodically broadcasting Hello that carries the path information with the minimum fitness, making the source node update the path information periodically. By using NS‐2, simulations demonstrate that compared with AOMDV, AEQAOMDV has obvious improvements in increasing packet delivery ratio, reducing network routing overhead, reducing route discovery frequency, and decreasing the network delay. And AEQAOMDV is more suitable for WSN.     

A study of deploying smooth‐ and responsive‐TCPs with different queue management schemes

While there exist extensive research works on congestion control and active queue management, or the joint dynamics of a congestion control strategy with the random early detection (RED) algorithm, little has been done on the interactions between different window adjustment strategies and different queue management schemes such as DropTail and RED. In this paper, we consider a spectrum of TCP‐friendly additive increase and multiplicative decrease (AIMD) parameters. At the one end of this spectrum, smooth‐TCP enhances smoothness for multimedia applications by reducing the window decrease ratio upon congestion, at the cost of the additive increase speed and the responsiveness to available bandwidth. At the other end, responsive‐TCP enhances the responsiveness by increasing the additive increase speed, at the cost of smoothness. We investigate the network dynamics with various combinations of AIMD parameters and queue management schemes, under different metrics. The investigation is conducted from the deployment (especially incremental deployment) point of view. We discussed the impact of the interactions on the goodput, fairness, end‐to‐end delay, and its implications to energy consumption on mobile hosts. Copyright © 2008 John Wiley & Sons, Ltd.     

Performance analysis of geography‐limited broadcasting in multihop wireless networks

In multihop wireless networks, delivering a packet to all nodes within a specified geographic distance from the source is a packet forwarding primitive (geography‐limited broadcasting), which has a wide range of applications including disaster recovery, environment monitoring, intelligent transportation, battlefield communications, and location‐based services. Geography‐limited broadcasting, however, relies on all nodes having continuous access to precise location information, which may not be always achievable. In this paper, we consider achieving geography‐limited broadcasting by means of the time‐to‐live (TTL) forwarding, which limits the propagation of a packet within a specified number of hops from the source. Because TTL operation does not require location information, it can be used universally under all conditions. Our analytical results, which are validated by simulations, confirm that TTL‐based forwarding can match the performance of the traditional location‐based geography‐limited broadcasting in terms of the area coverage as well as the broadcasting overhead. It is shown that the TTL‐based approach provides a practical trade‐off between geographic coverage and broadcast overhead. By not delivering the packet to a tiny fraction of the total node population, all of which are located near the boundary of the target area, TTL‐based approach reduces the broadcast overhead significantly. This coverage‐overhead trade‐off is useful if the significance of packet delivery reduces proportionally to the distance from the source. Copyright © 2011 John Wiley & Sons, Ltd.     

Performance evaluation of selected Transmission Control Protocol variants over a digital video broadcasting‐second generation broadband satellite multimedia system with QoS

This paper presents an analysis of several Transmission Control Protocol (TCP) variants working over a digital video broadcasting‐second generation (DVB‐S2) satellite link with the support of the Differentiated Services (DiffServ) architecture to provide quality of service (QoS). This analysis is carried out using the NS‐2 simulator tool. Three TCP variants are considered: SACK TCP, Hybla TCP, and CUBIC TCP. These TCP variants are taken as a starting point because they have proven to be the most suitable variants to deal with long delays present in satellite links. The DVB‐S2 link also introduces the challenge of dealing with variable bandwidth, whereas the DiffServ architecture introduces the challenge of dealing with different priorities. In this paper, we propose a DiffServ model that includes a modified queuing mechanism to enhance the goodput of the assured forwarding traffic class. This modified DiffServ model is simulated and tested, considering the interaction of the selected TCP variants. In addition, we present evaluation metrics, significant simulations results, and conclusions about the performance of these TCP variants evaluated over the proposed scenario. As a general conclusion, we show that CUBIC TCP is the TCP variant that shows the best performance in terms of goodput, latency, and friendliness. Copyright © 2012 John Wiley & Sons, Ltd.     

Performance analysis of WPM‐based transmission with equalization‐aware bit loading

Wavelet packet modulation (WPM) is a multicarrier modulation (MCM) technique that has emerged as a potential alternative to the widely used orthogonal frequency‐division multiplexing (OFDM) method. Because WPM has overlapped symbols, equalization cannot rely on the use of the cyclic prefix (CP), which is used in OFDM. This study applies linear minimum mean‐square error (MMSE) equalization in the time domain instead of in the frequency domain to achieve low computational complexity. With a modest equalizer filter length, the imperfection of MMSE equalization results in subcarrier attenuation and noise amplification, which are considered in the development of a bit‐loading algorithm. Analytical expressions for the bit error rate (BER) performance are derived and validated using simulation results. A performance evaluation is carried out in different test scenarios as per Recommendation ITU‐R M.1225. Numerical results show that WPM with equalization‐aware bit loading outperforms OFDM with bit loading. Because previous comparisons between WPM and OFDM did not include bit loading, the results obtained provide additional evidence of the benefits of WPM over OFDM.     

Optimal rate and power allocation under quality‐of‐service requirements for wireless multihop networks

In wireless networks, real‐time applications have strict QoS requirements for packet delay, packet loss, and reliability. However, most existing work has not considered these QoS metrics when allocating wireless resources so that the QoS requirements of real‐time applications may not be satisfied. To overcome this shortcoming, a rate and power allocation framework incorporating these QoS metrics is first proposed for slow‐fading systems. Second, two distributed algorithms are developed to solve this optimization framework although it is nonconvex and nonseparable. Third, an improved framework is proposed to deal with the rate and power allocation with QoS requirements for fast‐fading systems. It is shown that the fast‐fading state of the network does not need to be considered in this improved framework, and it can be solved using algorithms that are similar to those for the framework of slow‐fading systems. In the end, simulations show that our algorithms converge closely to the globally optimal solution. By comparison with an existing model, simulations also verify the validity of our frameworks on dealing with the rate and power allocation with QoS requirements. Copyright © 2012 John Wiley & Sons, Ltd.     

Energy‐aware dynamic task offloading and collective task execution in mobile cloud computing

There is a good opportunity for enlightening the services of the mobile devices by introducing computational offloading using cloud technology. Offloading is a process for managing the complexity of the mobile environment by migrating computational load to the cloud. The mobile devices oblige the quick response for the offloading requests; it is dependent on network connectivity. The cloud services take long set‐up time irrespective of network connectivity. In this paper, new system architecture for the dynamic task offloading in the mobile cloud environment is proposed. The architecture includes the offloading algorithm that concentrates on energy consumption of the tasks both in the local and remote environment. The proposed algorithm formulates a collective task execution model for minimizing the energy consumption. The architecture concentrates on the network model by considering the task completion time in three different network scenarios. The experimental results show the efficiency of the suggested architecture in reducing the energy consumption and completion time of the tasks.     

Performance analysis of a channel allocation scheme for multi‐service mobile cellular networks

This paper presents a new channel allocation scheme, namely the dynamic partition with pre‐emptive priority (DPPP) scheme, for multi‐service mobile cellular networks. The system is modelled by a two‐dimensional Markov process and analysed by the matrix‐analytic method. A pre‐emptive priority (PP) mechanism is employed to guarantee the quality of service (QoS) requirement of the real‐time (RT) traffic at the expense of some degradation of non‐real‐time (NRT) traffic, while the victim buffer compensates the degradation and has no negative impact on the RT traffic. The complete service differentiation between new calls and handoff calls from different traffic classes is achieved by using the dynamic partition (DP) concept with the help of related design parameters. The performance analysis and numerical results show that the DPPP scheme, compared with the existing schemes, is effective and practical in multi‐service environments. Copyright © 2006 John Wiley & Sons, Ltd.     

Quality of service analysis and resource allocation scheme for Long‐Term Evolution network

In this paper, we analyze the quality of service (QoS) framework supported by the Long‐Term Evolution standard and model the behavior of a finite‐state downlink wireless fading channel based on the configurations and system parameters provided by the 3GPP Long‐Term Evolution and provide experimental results. The model can be used to provide realistic physical layer input to evaluate the performance of algorithms at the upper layers. For example, the medium access control layer will use this data to test the performance of scheduling, admission control, power control, and so on. The QoS requirements at the physical layer, the data link layer, and the cross‐layer modeling are stated. Then, we present a QoS‐based call admission control algorithm that considers admission of calls for future start‐up as well as the immediate and hand‐off calls with a certain priority admission scheme. Analytical study based on two‐dimensional Markov chain is also provided. We then use a stochastic discrete event simulator to evaluate the performance of the call admission control algorithm. The results obtained for look‐ahead admission are compelling and indicate the usefulness of making advance resource reservations. Copyright © 2013 John Wiley & Sons, Ltd.     

Performance comparison of end‐to‐end and on‐the‐spot traffic‐aware techniques

Traffic‐aware routing protocols have recently received considerable attention. This has been motivated by the role that it could play in extending the network's lifetime (or operational time) as it target the reservation of node's power and better utilisation of channel bandwidth, which could lead to performance improvement in terms of important performance metrics including throughput and end‐to‐end delay. Traffic‐aware techniques can be classified into two categories, namely end‐to‐end and on‐the‐spot, based on the way of establishing and maintaining routes between any source and destination. Although there has been much work on both categories, there has been no comparative performance study of the two approaches. To the best of our knowledge, this is the first work that carries out such a performance comparison. To this end, we have adapted our traffic‐aware technique namely load density to suggest a new ‘on‐the‐spot’ traffic‐aware technique. The main reason for doing this adaptation is to ensure that the comparison between the two approaches is fair and realistic. The study will reveal the main performance characteristics of the two approaches under various traffic and network conditions. Copyright © 2011 John Wiley & Sons, Ltd.     

Relative loss rate differentiation: performance of short‐lived TCP flows

The relative differentiated service model provides assurances for the relative quality ordering between service classes, rather than for the actual service level in each class. In this paper, we describe a relative loss rate differentiation scheme where packet drop probabilities are determined according to an active queue management (AQM) mechanism based on random early detection (RED) in a first‐in first‐out (FIFO) queue, are weighted in inverse proportion to the price that the network operator assigns to each service class. Basically, we describe a scheme where relative loss rate differentiation is incorporated directly into AQM. Most TCP flows today, particularly Web flows, can be characterized as short‐lived flows. Using simulations with short‐lived TCP flows, we show that the scheme is very effective in ensuring relative loss rate differentiation between service classes during times of network congestion. Copyright © 2004 John Wiley & Sons, Ltd.     

An energy‐aware approach for resource managing in the fog‐based Internet of Things using a hybrid algorithm

Regarding the recent information technology improvement, the fog computing (FC) emergence increases the ability of computational equipment and supplies modern solutions for traditional industrial applications. In the fog environment, Internet of Things (IoT) applications are completed by computing nodes that are intermediate in the fog, and the physical servers in data centers of the cloud. From the other side, because of resource constraints, dynamic nature, resource heterogeneity, and volatility of fog environment, resource management problems must be considered as one of the challenging issues of fog. The resource managing problem is an NP‐hard issue, so, in the current article, a powerful hybrid algorithm for managing resources in FC‐based IoT is proposed using an ant colony optimization (ACO) and a genetic algorithm (GA). GAs are computationally costly because of some problems such as the lack of guarantee for obtaining optimal solutions. Then, the precision and speed of convergence can be optimized by the ACO algorithm. Therefore, the powerful affirmative feedback pros of ACO on the convergence rate is considered. The algorithm uses GA's universal investigation power, and then it is transformed into ACO primary pheromone. This algorithm outperforms ACO and GA under equal conditions, as the simulation experiments showed.     

Performance analysis and optimization of best‐effort service in IEEE 802.16 networks

The IEEE 802.16‐based WiMAX technology has great potential for the fourth‐generation mobile networks. Some of its service classes use the contention‐based broadcast polling mechanism to request resources. In this paper, we investigate the performance experienced by these services when the network is unsaturated. In particular, we model each subscriber station as an M/G/1 queue where the service time is determined by the parameters of the network configuration and the binary exponential backoff contention resolution algorithm. We develop a fixed‐point analysis to derive analytical expressions for network throughput and packet access delay. The accuracy of the analytical model is validated by comparing it with simulation over a wide range of operating conditions. The implications of various different parameter configurations on the performance are investigated using the analytical model. Moreover, we show that the model can be degenerated to the saturated condition. The utility of both the unsaturated and saturated models is further demonstrated by finding the optimal set of parameter values that maximize the network throughput. Copyright © 2011 John Wiley & Sons, Ltd.