Search

Ubiquitous computing has potentials to harness the flexibility of distributed computing systems including cloud, edge, and internet of things devices. Mobile edge computing (MEC) benefits time-critical applications by providing low latency connections. However, most of the resource-constrained edge devices are not computationally feasible to host deep learning (DL) solutions. Further, these edge devices if deployed under denser deployments may result in topological dependencies which if not taken into consideration may adversely affect the MEC performance. To bring more intelligence to the edge under topological dependencies, compared to optimization heuristics, this work proposes a novel collaborative distributed DL approach. The proposed approach exploits topological dependencies of the edge using a resource-optimized graph neural network (GNN) version with an accelerated inference. By exploiting edge collaborative learning using stochastic gradient (SGD), the proposed approach called CGNN-edge ensures fast convergence and high accuracy. Collaborative learning of the deployed CGNN-edge incurs extra communication overhead and latency. To cope, this work proposes compressed collaborative learning based on momentum correction called cCGNN-edge with better scalability while preserving accuracy. Performance evaluation under IEEE 802.11ax-high-density wireless local area networks deployment demonstrates that both the schemes outperform cloud-based GNN inference in response time, satisfaction of latency requirements, and communication overhead.

Mammography is a popular diagnostic imaging procedure for detecting breast cancer at an early stage. Various deep-learning approaches to breast cancer detection incur high costs and are erroneous. Therefore, they are not reliable to be used by medical practitioners. Specifically, these approaches do not exploit complex texture patterns and interactions. These approaches warrant the need for labelled data to enable learning, limiting the scalability of these methods with insufficient labelled datasets. Further, these models lack generalisation capability to new-synthesised patterns/textures. To address these problems, in the first instance, we design a graph model to transform the mammogram images into a highly correlated multigraph that encodes rich structural relations and high-level texture features. Next, we integrate a pre-training self-supervised learning multigraph encoder (SSL-MG) to improve feature presentations, especially under limited labelled data constraints. Then, we design a semi-supervised mammogram multigraph convolution neural network downstream model (MMGCN) to perform multi-classifications of mammogram segments encoded in the multigraph nodes. Our proposed frameworks, SSL-MGCN and MMGCN, reduce the need for annotated data to 40% and 60%, respectively, in contrast to the conventional methods that require more than 80% of data to be labelled. Finally, we evaluate the classification performance of MMGCN independently and with integration with SSL-MG in a model called SSL-MMGCN over multi-training settings. Our evaluation results on DSSM, one of the recent public datasets, demonstrate the efficient learning performance of SSL-MNGCN and MMGCN with 0.97 and 0.98 AUC classification accuracy in contrast to the multitask deep graph (GCN) method Hao Du et al. (2021) with 0.81 AUC accuracy.

The IEEE 802.11ax standard is designed to provide high-efficiency WLAN operating in dense deployment, with a focus on increasing robustness and uplink transmission. IEEE 802.11ax aims to deliver self-configuration and self-adaptation capabilities for interference management techniques in dense deployments, to improve overall network conditions. The IEEE 802.11ax medium strives to intelligently use network allocation vectors (NAV), which block simultaneous transmission of neighboring co-existing access points from transmitting for a set period of time. Given an acceptable collision probability, this collision avoidance strategy tends to degrade network throughput and increase transmission delays since the medium is never completely exploited. In this paper, we propose affinityGNN, a graph neural network approach to actively optimize network co-existence transmission in a dense scenario. We introduce direct-affinityGNN which considers direct communications between IEEE802.11ax-compliant wireless systems and in contrast, skip-affinityGNN, which considers communication between IEEE802.11ax and Legacy devises by aggregating neural messages from direct and skip (two-hop) communicating neighbors in the dense wireless network deployment. Extensive experimental results not only show the superior performance of our proposed model over the state-of-the-art, but also demonstrate its potentially good interpretability and robustness for wireless network structure.

Hybrid FSO/RF system requires an efficient FSO and RF link switching mechanism to improve the system capacity by realizing the complementary benefits of both the links. The dynamics of network conditions, such as fog, dust, and sand storms compound the link switching problem and control complexity. To address this problem, we initiate the study of deep reinforcement learning (DRL) for link switching of hybrid FSO/RF systems. Specifically, in this work, we focus on actor-critic called Actor/Critic-FSO/RF and Deep-Q network (DQN) called DQN-FSO/RF for FSO/RF link switching under atmospheric turbulences. To formulate the problem, we define the state, action, and reward function of a hybrid FSO/RF system. DQN-FSO/RF frequently updates the deployed policy that interacts with the environment in a hybrid FSO/RF system, resulting in high switching costs. To overcome this, we lift this problem to ensemble consensus-based representation learning for deep reinforcement called DQNEnsemble-FSO/RF. The proposed novel DQNEnsemble-FSO/RF DRL approach uses consensus learned features representations based on an ensemble of asynchronous threads to update the deployed policy. Experimental results corroborate that the proposed DQNEnsemble-FSO/RF’s consensus learned features switching achieves better performance than Actor/Critic-FSO/RF, DQN-FSO/RF, and MyOpic for FSO/RF link switching while keeping the switching cost significantly low.

Mammography is a popular diagnostic imaging procedure for detecting breast cancer at an early stage. Various deep learning (DL) approaches to breast cancer detection incur high costs and are prone to classify incorrectly. Therefore, they are not sufficiently reliable to replace existing techniques used by medical practitioners. Specifically, these DL approaches do not exploit the complex texture patterns and interactions in mammograms. These DL approaches need labelled data to enable learning, limiting the scalability of these methods because of sufficient labelled datasets. Further, these DL models lack generalisation capability to newly-synthesised patterns/textures. To address these problems, in the first instance, we design a graph model to transform the mammogram images into highly correlated multi-graphs, encoding rich structural relations and high-level texture features. Then, we consider a self-supervised learning multi-graph encoder (SSL-MG) to improve the features presentation, especially when limited labelled data is available. Finally, we design a semi-supervised mammogram multi graph convolution neural network downstream model (MMGCN) to perform multi classification of mammogram segments encoded in the multi-graph nodes. We evaluate the classification performance of MMGCN independently and with integration with SSL-MG in a model called SSL-MMGCN over several training settings. Our results reveal the efficient learning performance of SSL-MNGCN and MMGCN with 0.97 and 0.98 AUC classification accuracy in contrast to the multitask deep graph (GCN) method of Hao Du et al. (2021) with 0.81 AUC accuracy.

Mammography is a popular diagnostic imaging procedure for detecting breast cancer at an early stage. Variousdeep learning approaches to breast cancer detection incur high costs and are erroneous. Therefore, they are notreliable to be used by medical practitioners. Specifically, these approaches do not exploit the complex texture patternsand interactions. These approaches warrant the need for labelled data to enable learning, limiting the scalabilityof these methods under insufficient labelled datasets. Further, these models lack generalisation capability to newsynthesizedpatterns/textures. To address these problems, in the first instance, we design a graph model to transform themammograms images into highly correlated multigraph encode rich structural relations and high-level texture features.Then, we consider a self-supervised learning multigraph encoder (SSL-MG) to improve the features presentation,especially under limited labelled data constraints. Finally, we design a semi-supervised mammogram multigraphconvolution neural network downstream model (MMGCN) to perform multi classifications of mammogram segmentsencoded in the multigraph nodes. We evaluate the classification performance of MMGCN independently and withintegration with SSL-MG in a model called SSL-MMGCN over multi training settings. Our results reveal the efficientlearning performance of SSL-MNGCN and MMGCN with 0.97 and 0.98 AUC classification accuracy in contrast tothe multitask deep graph (GCN) method Hao Du et al. (2021) with 0.81 AUC accuracy.

Since the rapid outbreak of Covid-19, profound research interest has emerged to understand the innate immune response to viruses to enable appropriate vaccination. This understanding can help to inhibit virus replication, prolong adaptive immune response, accelerated virus clearance, and tissue recovery, a key milestone to combat coronaviruses (CoVs), e.g., Covid-19. An innate immune system triggers inflammatory responses against CoVs upon recognition of viruses. An appropriate defense against various coronavirus strains requires a deep understanding of the innate immune response system. Current deep learning approaches focus more on Covid-19 detection and pay no attention to understand the immune response once a virus invades. In this work, we propose a graph neural network-based (GNN) model that exploits the interactions between pattern recognition receptors (PRRs)to understand the human immune response system. PRRs are germline-encoded proteins that identify molecules related to pathogens and initiate a defense mechanism against the related pathogens, thereby aiding the innate immune response system. An understanding of PRR interactions can help to recognize pathogen-associated molecular patterns (PAMPs) to predict the activation requirements of each PRR. The immune response information of each PRR is derived from combining its historical PAMPs activation coupled with the modeled effect on the same from PRRs in its neighborhood. On one hand, this work can help to understand how long Covid-19 can confer immunity for a strong immune response. On the other hand, this GNN-based understanding can also abode well for appropriate vaccine development efforts against CoVs. Our proposal has been evaluated using CoVs immune response dataset, with results showing an average IFNs activation prediction accuracy of 90%, compared to 85% using feed-forward neural networks.

Due to high data rates, license-free spectrum, and immunity to electromagnetic interference, free-space optical (FSO) links are being considered as a potential candidate to meet the ever-increasing traffic demands of users. The FSO links remain less explored, as their performance depends on environmental conditions such as dust, fog, and clouds. Such conditions do not affect the radio frequency (RF) links in a similar way; however, RF resources are scarce. As an ultimate solution to this performance/scarcity dilemma, we propose a fuzzy logic-based hybrid architecture of FSO and RF links, which can be used to enhance reliability and resource efficiency. We present an intelligent soft switching mechanism between FSO and RF links using a fuzzy inference system to achieve the maximum link reliability and provide heterogeneous wireless services.

Hybrid FSO/RF system requires an efficient FSO and RF link switching mechanism to improve the system capacity by realizing the complementary benefits of both the links. The dynamics of network conditions, such as fog, dust, and sand storms compound the link switching problem and control complexity. To address this problem, we initiate the study of deep reinforcement learning (DRL) for link switching of hybrid FSO/RF systems. Specifically, in this work, we focus on actor-critic called Actor/Critic-FSO/RF and Deep-Q network (DQN) called DQN-FSO/RF for FSO/RF link switching under atmospheric turbulences. To formulate the problem, we define the state, action, and reward function of a hybrid FSO/RF system. DQN-FSO/RF frequently updates the deployed policy that interacts with the environment in a hybrid FSO/RF system, resulting in high switching costs. To overcome this, we lift this problem to ensemble consensus-based representation learning for deep reinforcement called DQNEnsemble-FSO/RF. The proposed novel DQNEnsemble-FSO/RF DRL approach uses consensus learned features representations based on an ensemble of asynchronous threads to update the deployed policy. Experimental results corroborate that the proposed DQNEnsemble-FSO/RF's consensus-learned features switching achieves better performance than Actor/Critic-FSO/RF, DQN-FSO/RF, and MyOpic for FSO/RF link switching while keeping the switching cost significantly low., Comment: Number of pages 16 and number of figures 15, Unpublished work, accepted

LoRa is a long-range, low power and single-hop wireless technology that has been envisioned for Internet of Things (IoT) applications having battery driven nodes. Nevertheless, increase in number of end devices and varying throughput requirements impair the performance of pure Aloha in LoRaWAN. Considering these limitations, we evaluate the performance of slotted Aloha in LoRaWAN using extensive simulations. We employed packet error rate (PER), throughput, delay, and energy consumption of devices under different payload sizes and varying number of end devices as benchmarks. Moreover, an analytical analysis of backlogged and non-backlogged under slotted Aloha LoRaWAN environment is also performed. The simulation shows promising results in terms of PER and throughput compared to the pure Aloha. However, increase in delay has been observed during experimental evaluation.Finally, we endorse slotted aloha LoRaWAN for Green IoT Environment.

Network Function Virtualisation (NFV) has emerged as a key paradigm in network softwarisation, enabling virtualisation in future generation networks. Once deployed, the Virtual Network Functions (VNFs) in an NFV application’s Service Function Chain (SFC) experience dynamic fluctuations in network traffic and requests, which necessitates dynamic scaling of resource instances. Dynamic resource management is a critical challenge in virtualised environments, specifically while balancing the trade-off between efficiency and reliability. Since provisioning of virtual infrastructures is time-consuming, this negates the Quality of Service (QoS) requirements and reliability criterion in latency-critical applications such as autonomous driving. This calls for predictive scaling decisions to balance the provisioning time sink, with a methodology that preserves the topological dependencies between the nodes in an SFC for effective resource forecasting. To address this, we propose the model for an Asynchronous Deep Reinforcement Learning (DRL) enhanced Graph Neural Networks (GNN) for topology-aware VNF resource prediction in dynamic NFV environments.

Barrier coverage is one of the popular applications of Wireless Sensor Networks (WSNs). A barrier construction algorithm which takes into account both energy efficiency and fault tolerance is critical for the security of mission-critical regions. Sensor devices of a sensor network have the capability to monitor and understand the critical environment, and if part of the internet of things (IoT), they can communicate this information to a remote location for immediate action. This paper deals with the barrier coverage achieved through sensor nodes and communicate coverage information to a mission partner agency. The contributions of this paper are two folds. First, we propose a disjoint barrier construction algorithm based on the residual energy of sensors. Second, we propose an IoT-enabled paradigm to report barrier coverage information to a mission partner agency for immediate action. Simulation results show that the proposed algorithm improves barrier coverage and ensures better barrier lifetime compared to 2- barrier and LABC algorithms.

The use of multiple channels for transmissions has raised several challenges, for example, multi-channel hidden terminal problem, channel switching delay, and control channel saturation problem. Dedicated control channel techniques simplify channel coordination by eliminating the need for synchronization, however the control channel may become the bottleneck for the performance of the network. A better trade off which can solve the coordination problem, and can mitigate the control channel bottleneck is desirable. Least Channel Variant Multi-channel MAC (LCV-MMAC) is a multi-channel MAC based on IEEE 802.11 MAC. The novel part of this protocol is the channel assignment technique, where a mechanism to avoid unnecessary channel assignment and thus channel switching is used. Further, LCV-MMAC avoids channel contention when the control channel is highly saturated. In this paper, we explore the properties of LCV-MMAC through extensive simulations with the help of ns-2, and compare it with popular existing multi-channel MAC protocols in different mobile and static random topologies. Experimental results validate that LCV-MMAC achieves significantly better aggregated throughput, and fairness index than other multi-channel MAC protocols in different random network scenarios.

Energy conversation is one of the primary objectives of duty cycle MAC protocols. Different synchronous and asynchronous duty cycle MAC protocols have been proposed in recent years. These protocols perform well under low traffic loads, but efficiency of these protocols degrade under high traffic loads. We present an asynchronous hybrid duty cycle MAC protocol called Hybrid MAC (H-MAC), which uses both sender and receiver initiated mechanisms to combat the packet delivery latency. In H-MAC each node schedules its sleep and wake up time based on cross layer routing information on the receiver initiated part and on the sender initiated part each sender chooses its wake up time based on the receiver's wake up information. We have evaluated HMAC in diverse network under dynamic traffic loads. Experiments reveal that, H-MAC significantly reduces packet delivery latency and energy consumption compared to RIMAC.

Vehicular Ad hoc Networks (VANETs) provide road safety, commercial, entertainment, and convenience services. Users have access to real time traffic updates, road hazard notifications, post crashed notification, remote vehicle diagnostics, audio and video streaming, and route suggestions to enhance the travel experience. However service delivery in VANETs suffers as nodes in VANETs move at high speed causing the network topology to change rapidly. A node becomes unreachable from its current point of attachment as it moves out of its range. Mobility management ensures that a mobile node can continuously access the services while it roams around by re-attaching itself via another point of attachment. Various solutions for mobility management have been proposed. Nonetheless handoff delay, packet loss and signaling overhead, and are still a concern in VANETs. Internet Engineering Task Force (IETF) has chartered a Distributed Mobility Management (DMM) group in year 2014. The purpose of DMM is to provide an alternate solution to the mobility management problem in wireless networks. In this research, the effectiveness of distributed mobility management schemes in VANETs is compared on the basis of different parameters.

In this paper, we present a MAC protocol called Hop Extended Pipelined Routing MAC (HE-PRMAC) that enables a node to send a data packet for multiple hops in a single duty cycle similar to PR-MAC and has the ability to handle traffic overhead in an efficient way. HE-PRMAC addresses delivery latency and throughput degradation in wireless sensor networks (WSNs) using hop extended mechanism and a new message, i.e., RTR message. The main goal of this research is to reduce the overhead and latency compared to R-MAC and PR-MAC. We evaluate the performance of our protocol using ns-2 simulations. As compared to R-MAC and PR-MAC, HE-PRMAC shows 22.1% less power consumption and 13.6% less packet latency on average for 250 nodes in chain, cross, and real scenario.

The problem of idle listening is one of the most significant sources of energy consumption in wireless sensor nodes. Many techniques have been proposed based on duty cycling to reduce this idle listening. This paper presents Adaptive Scheduling Predictive-Wakeup MAC (AS-PW-MAC), a new MAC protocol based on asynchronous duty cycling. AS-PW-MAC introduces RTE and RAS messages for pending data transmission. RTE and RAS are beneficial for varying traffic loads. We evaluate the performance of AS-PW-MAC through detailed ns-2 simulation and compare it to RI-MAC and PW-MAC, two well-known MAC protocols. Our evaluation includes clique, grid and random network scenarios. In all experiments, AS-PW-MAC significantly out performs RI-MAC and PW-MAC protocols. AS-PW-MAC achieves higher packet delivery ratio under a wide range of traffic loads compared to RI-MAC and PW-MAC. Especially, when there are contending flows, such as bursty traffic or transmissions from hidden nodes, AS-PW-MAC significantly improves the packet delivery ratio and delivery latency. The delivery latency for AS-PW-MAC is less than 21% compared to RI-MAC and PW-MAC. In all experiments, AS-PW-MAC maintained approximately 100% packet delivery ratio.

Challenges faced by Medium access control (MAC) protocols for Wireless Sensor Networks (WSNs) include energy efficient operation and bandwidth limitations. Low duty cycle MAC conserves energy but at the same time it affects delivery ratio and latency. Use of multiple channels can improve the throughput and latency by alleviating the bandwidth limitations. This paper presents the design and performance evaluation of PW-MMAC (Predictive Wake up Multi-Channel MAC) protocol which addresses these challenges by coupling the benefits of multiple channels with adaptive duty cycling and predictive wake-up mechanism. PW-MMAC significantly improves energy efficiency and channel utilization by adapting dynamically to varying network conditions without the need of a dedicated control channel. Implemented in ns-2, PWMMAC shows significant improvement over other duty cycle MAC protocols. PW-MMAC achieves lowest duty cycle, 100% delivery ratio, and lowest packet delivery latency in different network scenarios in both multi-hop and single-hop clique, grid, and random networks.

In this paper, we present PW-SA-MAC, an asynchronous energy efficient duty cycle MAC protocol. Similar to RI-MAC, PW-SA-MAC employs receiver-initiated transmissions with a sender-assisted contention resolution. PW-SA-MAC enables senders to wake up at predicted times according to the receiver’s schedule. We evaluate PW-SA-MAC using ns-2 and compare it to RI-MAC and SA-RI-MAC, under clique, grid, and random networks. In random network scenarios, the average duty cycle of PW-SA-MAC is 66 % less compared to RI-MAC and SA-RI-MAC.

Recently, wireless body area networks (WBANs) have attracted significant consideration in ubiquitous healthcare. A number of medium access control (MAC) protocols, primarily derived from the superframe structure of the IEEE 802.15.4, have been proposed in literature. These MAC protocols aim to provide quality of service (QoS) by prioritizing different traffic types in WBANs. A contention access period (CAP)with high contention in priority-based MAC protocols can result in higher number of collisions and retransmissions. During CAP, traffic classes with higher priority are dominant over low-priority traffic; this has led to starvation of low-priority traffic, thus adversely affecting WBAN throughput, delay, and energy consumption. Hence, this paper proposes a traffic-adaptive priority-based superframe structure that is able to reduce contention in the CAP period, and provides a fair chance for low-priority traffic. Simulation results in ns-3 demonstrate that the proposed MAC protocol, called traffic- adaptive priority-based MAC (TAP-MAC), achieves low energy consumption, high throughput, and low latency compared to the IEEE 802.15.4 standard, and the most recent priority-based MAC protocol, called priority-based MAC protocol (PA-MAC).

The use of multi-channel MAC protocols improves the capacity of wireless networks. Efficient multi-channel MAC protocols aim to utilize multiple channels effectively. Our proposed multi-channel MAC protocol called LCV-MMAC effectively utilizes the multiple channels by handling the control channel saturation. LCV-MMAC demonstrates significantly better throughput and fairness compared to DCA, MMAC, and AMCP in different network scenarios.

Due to limited battery life and fault tolerance issues posed by Wireless Sensor Networks (WSNs), efficient methods which ensure reliable coverage are highly desirable. One solution is to use disjoint set covers to cover the targets. We formulate a problem called MDC which addresses the maximum coverage by using disjoint set covers S 1 and S 2. We prove that MDC is \(\mathcal{NP}\)-complete and propose a \(\sqrt{n}\)-approximation algorithm for the MDC problem to cover n targets.

Duty cycling is an efficient mechanism to conserve energy in wireless sensor networks. Several existing duty cycling techniques have been proposed to conserve energy, but they are not able to handle the contention under dynamic traffic loads. In this paper we propose a protocol called Sender-Assisted-Receiver-Initiated MAC (SA-RI-MAC) which solves this problem without sacrificing the energy efficiency. SA-RI-MAC employs the receiver initiated transmissions mechanism of RI-MAC with a sender assisted approach to handle the contention at the receiver. Senders tend to cooperate with each other to resolve the contention dynamically based on the contention level at the receiver. A further improvement is achieved by prioritizing the sender transmissions which has been starved long for the channel occupancy. Our simulation results in ns-2 show that SA-RI-MAC achieves significant improvement in conserving energy over RI-MAC. It can handle traffic contention much more efficiently than RI-MAC; thus improving end to end delivery ratio with a reduction in the latency. Under light traffic load, the performance of SA-RI-MAC is comparable with RI-MAC in terms of end to end delivery ratio, latency and energy efficiency.

Broadcasting is a fundamental operation underlying different routing, multicasting and address resolution protocols. Broadcasting in a network requires that all the nodes in the network receive the broadcast packet. Mobility in the network induces link failures which cause some nodes to lose the broadcast packets. Objective of all broadcasting protocols is to achieve high reachability while keeping the broadcast redundancy as low as possible. In this paper we propose a cross layer protocol, called cross layer mobility adaptive broadcasting (CMAB) to handle the mobility in mobile ad hoc networks (MANETs). CMAB uses two Disjoint Sets of Broadcast Relay Gateways (BRGs1 and BRG2) to ensure high reliability in case of high mobility. Our approach minimizes broadcast redundancy by activating the second set of BRG2s only in highly mobile scenarios. A further reduction in broadcast redundancy is achieved by forcing the second Disjoint BRG2 to rebroadcast only if it is covering a maximum number of 2-hop neighbors of upstream sender or source to be covered by BRG1. The proposed protocol balances the retransmission redundancy avoiding the broadcast storm problem and increasing reachability in highly mobile and denser network scenarios. Simulation results show that CMAB provides high delivery ratio, low forwarding ratio and low end-to-end delay in highly mobile and denser network scenarios.

Flooding is an obligatory technique to broadcast messages within mobile ad hoc networks (MANETs). Simple flooding mechanisms cause the broadcast storm problem and swamp the network with a high number of unnecessary retransmissions, thus resulting in increased packet collisions and contention. This degrades the network performance enormously. There are several broadcasting schemes that adapt to different network conditions of node density, congestion and mobility.

Unlike wired networks, random packet loss due to bit errors is not negligible in wireless networks. These networks have mobility as another challenge. This causes significant performance degradation of TCP. Different Variants of TCP exist; some have no mechanism to differentiate random losses on the wireless link from congestion and therefore treat all random losses as an indication of congestion. Analyzing the performance of existing TCP Variants under random packet loss is important in order to select an appropriate version of TCP in the networks where random packet losses are more frequent. This paper describes an ns-2 based simulation analysis of TCP-Vegas, TCP-Tahoe, TCP-Reno, TCP-New Reno, TCP-SACK, TCP-Veno, TCP-Westwood, TCP-Westwood New Reno and TCP-New Jersey under random packet loss rate in wireless networks. Experimental studies indicate that the Throughput of TCP-New Jersey is much better than all other TCP variants for high Random Packet Loss Rate. Results show that when we have to deal with the protocol overhead TCP-New Jersey and TCP-Vegas have lowest overhead than other TCP variants. Analyzing the impact of TCP variants on the performance of MANET routing protocols is also important to improve their performance in highly mobile networks. In this paper we have also evaluated the performance of TCP-New Jersey and TCP-Vegas with DSR, AODV and DSDV. Simulations show that MANET routing protocols perform well in combination with TCP-New Jersey than with TCP-Vegas.