Applications In Heterogeneous Networks Research Articles

Game-theoretic robotic offloading via multi-agent learning for agricultural applications in heterogeneous networks

Intelligent robotics, as a frontier field of widespread attention, is increasingly applied to realize cyber-physical-social system (CPSS). Taking Agriculture 4.0 as one use case, using various agricultural robot applications can reduce labor costs and improve operation efficiency, but limited by the onboard resources, these mobile robots need to make full use of network and computation resources provided by infrastructures in the smart farm to enhance their capabilities.On the one hand, the heterogeneity of networks brings more options for access selection; however, on the other hand, the mobility of robots and the Quality of Service (QoS) requirements of different agricultural applications pose great challenges to the current offloading work. Therefore in this paper, we introduce a stochastic game framework to address these challenges faced by smart agriculture, and propose a multi-agent task offloading and network selection (MATONS) scheme, which utilizes reinforcement learning to offload tasks from robots to central cloud or edge servers. The robots cooperatively optimize the QoS perceived and the energy usage by adopting a joint Nash equilibrium strategy, which requires the decision of offloading along with the optimal transmission technology and corresponding access nodes, i.e., WiFi or cellular network. Simulation results verify that MATONS has great convergence and stability under different scales of robots in the farm, and can achieve superior performance than mainstream algorithms in various scenarios.

Efficient Polar Coded Selective Decode-and-Forward with Cooperative Decision Threshold in Cooperative Multi-Relay Transmissions

In some satellite Internet of Things (IoT) devices with terrain shielding, the qualities of the direct source-destination (S-D) channel are poor, requiring cooperative communications with multi-relays to be employed. In order to solve error propagation of current decode-and-forward (DF) on such occasions, an efficient polar coded selective decode-and-forward (SDF) cooperation method is proposed with a new decision threshold derived from channel state information (CSI). First, the proposed threshold is derived from the CSI by exploiting the channel gain ratio of optimal relay-destination link (R-D) with source-relay (S-R) link. The above R-D link possesses good channel quality among all links in the system. Second, when the channel gain ratio of certain relay links is larger than the aforementioned decision threshold, the source and all these relays cooperatively send messages together to the destination to accomplish perfect SDF transmission. Otherwise, all relays are frozen and the messages are directly transmitted through the S-D link. If it fails anyway, a retransmission is subsequently tried in the next transmission cycle. In addition, a polar code for fading channels is designed and adaptively adjusted to a proper code rate according to channel quality to attain good bit error rate (BER) performance. Simulation results show that the proposed scheme achieves about 0.9 and 0.5 dB gain at BER of 10-4, respectively, in multi-relay cooperative communications with multi-path fading channels compared with those of non-cooperation and existing polar coded cooperation channels. Therefore, the proposed polar coded SDF (PCSDF) scheme can improve both the BER and the outage probability (OP) performance in multi-relay cooperative systems, making it quite suitable for heterogeneous network applications in cooperative satellite IoT systems involving sixth-generation (6G) communications.

Attention based multi-agent intrusion detection systems using reinforcement learning

Designing an effective network intrusion system (IDS) is a challenging problem because of the emergence of a large number of novel attacks and heterogeneous network applications. The existing IDSs fail to adapt to the changing attack patterns and unseen attacks that lead to inaccurate detection of network vulnerabilities and system performance degradation. Therefore, there is a need to design robust, scalable, efficient, and adaptive IDS for networks. This paper presents a novel deep reinforcement learning-based IDS that employs Deep Q-Network logic in multiple distributed agents and uses attention mechanisms to efficiently detect and classify advanced network attacks. Our proposed multi-agent IDS is designed as a distributed attack detection platform where agents work in a coordinated manner to provide scalable, fault-tolerant, multi-view architecture guided security system. We have tested our model with extensive experimentation on two benchmark datasets: NSL-KDD and CICIDS2017. It shows improved performance in terms of higher accuracy, precision, recall, F1-Score, and low false-positive rate (FPR) in comparison to the state-of-the-art IDS works. On the other hand, many machine learning systems are found vulnerable to adversarial attacks. Thus, we evaluated our model’s robustness against a practical black-box adversarial attack and observed only a little degradation in performance. We integrated the concept of denoising autoencoder (DAE) with our model to further improve its robustness. Finally, we discuss the usability of our system in real-life applications against zero-day attack patterns.

Enhanced QoS Through Optimized Architecture for Video Streaming Applications in Heterogeneous Networks

The exponential growth in the number of internet users for utilizing diversified applications, such as Voice over IP(VoIP), video on demand (VoD), video streaming and e-learning, has resulted in a steady increase in traffic on the transmission channel. Despite video streaming being a large contributor of traffic to both commercial and non-commercial uses, it still lags in the proper delivery of data to the users of cellular devices and another heterogeneous network. As the popularity of video streaming services increases, so does the user’s expectation for quality services. The poor quality of video streaming services has now become absolute in the video stream ecosystem. Therefore, video service providers have taken providing good Quality of Service to their users as their major goal. Provisioning of optimal QoS services in these applications become a challenging task for service providers in the presence of huge traffic and congestion. Since video streaming architecture follows a server-client architecture model, we propose to optimize the functions at the server-side to maximize QoS. The performance of the proposed architecture is compared with the existing architecture in terms of QoS features such as delay, delivery ratio and throughput for various data rates and buffer sizes. The proposed work is simulated using NS2 Simulator. The results show that, end to end delay is reduced by 10%, the delivery ratio is improved by 12% and throughput is improved by 17% when compared to the existing architecture.

Routing, modulation format, spectrum and core allocation in space-division-multiplexed programmable filterless networks

Abstract Elastic optical networks are considered as promising solutions to improve the spectral efficiency of optical networks and fulfill the diverse bandwidth requirements of heterogeneous network applications. Elastic filterless optical networks with passive broadcast-and-select architecture are introduced to offer network agility. However, the presence of unfiltered signals stems from the signal broadcast and the absence of filtering (so-called drop-and-waste transmission), can lead to an overhead in spectrum usage. This issue can be alleviated by combining the unprecedented flexibility of programmable architecture on demand (AoD) nodes with the extra diversity in spatial domain provided by space division multiplexing (SDM). In this paper, we propose a hardware-aware strategy based on the two-objective binary particle swarm optimization (BPSO) to solve the routing, modulation format, spectrum and core allocation (RMSCA) problem in programmable filterless SDM networks. The proposed BPSO-based hardware-aware RMSCA (BH-RMSCA) strategy aims at minimizing jointly the number of optical couplers and maximum backplane switch size inside the filterless AoD nodes. The physical layer impairment in terms of the inter-core crosstalk (XT) is taken into account in solving the resource allocation problem. Simulation results show that the proposed BH-RMSCA strategy successfully provides Pareto-optimal solutions with remarkable hardware savings compared to the benchmark methods. The cost-efficient network solutions are achieved at the expense of a favorable trade-off with the spectrum usage and the path length, especially for higher connected topology.

Joint optimization of QoS and security for differentiated applications in heterogeneous networks

The recent proliferation of various new real-time and latency-sensitive applications and differentiated services, surge of mobile traffic, and emergence of next generation Het- Nets are anticipated to exponentially increase the number of potentially “untrusted” links to the operator’s core network. Therefore, mobile broadband operators need to provide much needed security without sacrificing the network performance which calls for the joint provisioning of QoS and security technologies. However, research studies on HetNets have often treated QoS and security as separate entities, and overlooked the combined QoS and security optimization because they usually have difficult-to-model trade-off. In this article, we formulate this problem and propose a game-theoretic algorithm to solve it. In our proposal, the mobile users and their servicing base stations play games with each other to ensure a balanced set of security and QoS parameters for the users. The effectiveness of our proposal is evaluated through simulations.

Average latency and link utilization analysis of heterogeneous wormhole NoCs

We present a novel methodology for analysis of the average end-to-end latency and link utilization of wormhole NoCs with heterogeneous link capacities and heterogeneous number of virtual channels per unidirectional link. Our analysis methodology supports different heterogeneous NoC topologies for which no analysis framework has been developed in the past. The average end-to-end latency per flow is separated to three components: (1) The time it takes the head-flit to leave the source queue (queuing time at the source); (2) The time it takes the head-flit to reach the destination module (path acquisition time) and (3) The time it takes the rest of the packet to leave the network (transfer time). Furthermore, we take into account the interaction between intersecting flows. The average link utilization is calculated based on the path acquisition time and transfer time. To that end, our analysis introduces a set of implicit equations, which can be efficiently solved iteratively. We demonstrate the accuracy and the efficiency of our approximate analysis by comparing the analysis results to accurate simulations for several synthetic examples and SoC multimedia applications in heterogeneous networks. In addition, we compare the analysis results with HNOCS simulation results for a chip-multi-processor (CMP) using SPLASH-2 and PARSEC traces for both homogeneous and heterogeneous NoC configurations.

PicoGrid: A Web-Based Distributed Computing Framework for Heterogeneous Networks Using Java

We propose a framework for distributed computing applications in heterogeneous networks. The system is simple to deploy and can run on any operating systems that support the Java Virtual Machine. Using our developed system, idle computing power in an organization can be harvested for performing computing tasks. Agent computers can enter and leave the computation at any time which makes our system very flexible and easily scalable. Our system also does not affect the normal use of client machines to guarantee satisfactory user experience. System tests show that the system has comparable performance to the theoretical case and the computation time is significantly reduced by utilizing multiple computers on the network.

Introducing Flexible and Synthetic Optical Networking: Planning and Operation Based on Network Function Programmable ROADMs

Elastic optical networks are envisaged as promising solutions to fulfill the diverse bandwidth requirements for the emerging heterogeneous network applications. To support flexible allocation of spectrum resources the optical network nodes need to be agile. Among the different proposed solutions for elastic nodes, the one based on architecture of demand (AoD) exhibits considerable flexibility against the other alternatives. The node modules in the case of AoD are not hard-wired, but can be connected/disconnected to any input/output port according to the requirements. Thus, each AoD node and the network (fabricated with AoD nodes) as a whole acts like an optical field-programmable gate array. This flexibility inherent in AoD can be exploited for different purposes, such as for cost-efficient and energy-efficient design of the networks. This study looks into the cost-efficient network planning issue for synthetic networks implemented through AoD nodes. The problem is formalized as an integer linear programming formulation for presenting the optimal solution. Furthermore, a scalable and effective heuristic algorithm is proposed for cost-efficient design, and its performance is compared with the optimal solution. The designed networks with AoD nodes are further investigated for a dynamic scenario, and their blocking probability due to limited switching resources in the nodes is examined. To alleviate the blocking performance for the dynamic case, an efficient synthesis strategy along with a scheme for optimal placement of switching resources within the network nodes is presented. Extensive results show that 1) even at high loads, the network with AoD nodes achieves saving of switching modules up to 40% compared to the one with static reconfigurable optical add–drop multiplexers (ROADMs) through a proper network design, 2) by diminishing the spectrum selective switches the overall power consumption of the network decreases by more than 25% for high loads, and 3) for the dynamic scenario the blocking owing to the node modules constraint is alleviated significantly by slightly augmenting the switching devices and optimally deploying them within the network nodes.

A Novel Multicast Algorithm for Collaborative Multimedia Applications in Heterogeneous Networks

In this paper, we study the problem of QoS group communication in a heterogeneous network, which consists of multiple MANETs attached to the backbone Internet. We propose a heuristic multicast algorithm called MCMA (Multi-Constrained Multicast Algorithm). MCMA is designed for solving the DVBMT (Delay-and delay Variation-Bounded Multicast Tree) problem, which has been proved to be NP-complete. The literature studies are limited to end-to-end delay bound and delay variation minimization. In this paper, we improve and extend previous well known from literature heterogeneous network algorithms to provide scalable and stable multicast services on the Internet by introducing a new Delay–Variation Estimation Scheme for heterogeneous networks. This Scheme helps the MCMA algorithm achieve better performance in terms of the multicast delay variation than some well-known algorithms. The algorithm defines QoS parameters as constraints on both delay and delay variation. Theoretical analysis is given to show the correctness of MCMA and its performance in terms of the multicast delay variation.

Fault tolerant component management platform over Data Distribution Service

Distributed Real Time Systems (DRTS) are evolving to a higher level of complexity in terms of heterogeneity, dynamism and QoS constraints, as they must interact with an increasingly demanding environment. In an scenario with distributed applications running over different hardware platforms and networks, middleware technologies that provide real-time or QoS support are gaining importance, as they ease the development and deployment of complex distributed applications in heterogeneous networks while ensuring certain time and QoS constraints. In this sense, distribution middleware technologies like Data Distribution Service (DDS) have emerged, adding extensive QoS support to traditional middleware advantages. This paper proposes a component based applications management platform built on top of DDS that provides an easy way to deploy, configure and manage component based distributed applications, while ensuring the fulfillment of certain QoS aspects.

Scheduling security-critical multimedia applications in heterogeneous networks

Security is becoming an increasingly important issue in the design of multimedia applications, which are widely used in the industry and academic organizations. However, existing scheduling schemes for real-time multimedia service in heterogeneous networks generally do not take into account security requirements when making allocation and control decisions. In this paper, we develop and evaluate a security-critical multimedia scheduling scheme in the framework of heterogeneous networks. At first, we construct a general media distortion model according to the observed parameters in each network, as well as each application’s characteristic. After that, we exploit a scalable graph-based authentication method which achieves a good trade-off between flexibility and efficiency. Furthermore, a security-critical scheduling scheme is proposed by taking into account applications’ timing and security requirements in addition to precedence constraints. The proposed scheme is applied to heuristically find resource allocations, which maximize the quality of security and the probability of meeting deadlines for all the multimedia applications running on heterogeneous networks. Extensive simulations are provided to demonstrate the effectiveness and feasibility of the proposed scheme.

User-Centric Seamless Handover Scheme for Real-Time Applications in Heterogeneous Networks

The authors propose a user-centric seamless handover (HO) scheme, which is a kind of a vertical HO from a new perspective, toward a next generation network where heterogeneous access networks converge. The users' experience-oriented scheme allows users to enjoy the optimal service quality for real-time applications in respective access networks. In addition, the scheme sustains on-going sessions during the vertical HO. The proposed scheme consists of two methods — the bicasting of Different Quality-level Streams (DiffQS) and the Delay Difference Absorption (DDA) method. Initially, the authors propose two plausible methods for the SIP-based bicasting of DiffQS. This document introduces a SIP-capable network element named the HO Assistive Server (HOAS). HOAS controls bicasting of DiffQS and provides users with the optimal service quality for real-time applications via respective access networks as well as avoiding packet loss during HO. The DDA method is also proposed to prevent a service interruption and smoothly continue a real-time service during HO. Evaluation results show that the scheme achieves the seamless service continuity from the users' perspective for HO between cellular and high-speed wireless access via the implementation of a prototype system.

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

AbstractA 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.

Quality of service in heterogeneous wired/wireless networks

Recent technological developments in broadband peer-topeer and overlay networks, wireless and mobile networks, and grid computing have led to a wide variety of new challenging problems. These include the provisioning of Quality of Service (QoS), survivability, resilience and scalability in a wide range of emerging applications—such as large-scale multimedia systems—across both wired and wireless networks. Many aspects of the challenges should be considered, including the QoS provisioning, performance optimization, cross-layer design, resilience, scalability and survivability of distributed applications in heterogeneous networks. The special issue consists of eight papers addressing recent cutting edge research and state-of-the-art technology of multimedia QoS support in heterogeneous wired/wireless networks. It is timely and valuable for those involved in the research areas. The first three papers propose novel energy efficient algorithms to improve the performance of wireless sensor networks (WSNs). In the first paper “Localized Coverage Boundary Detection for Wireless Sensor Networks”, Zhang, Zhang, and Fang propose two deterministic, localized algorithms for coverage boundary detection in WSNs. The algorithms are based on two novel computational geometric techniques called localized Voronoi and neighbour embracing polygons. They are truly distributed and localized by merely needing the minimal position information of one-hop neighbours and a limited number of simple local computa-

CORBA-BASED ARCHITECTURE FOR COOPERATIVE PERCEPTION

In these networked days cooperative perception means that multiple robots with multiple sensors can share their data creating a common knowledge base so that they can plan and interact with the environment in a more appropriate and efficient way. We propose in this work an architecture for cooperative perception for mobile robots based on distributed objects in a network. The implementation follow the CORBA specification, created to facilitate development of distributed applications in heterogeneous network. Objects could be the sensors and actuators of a robot or processes that treat common sensor data. An implementation of an image acquisition and distribution service is presented and others are proposed to compose the architecture.

Concepts for the Usage of Real-Time Corba in Time-Triggered Architectures

CORBA is the established standard derived from the Client/Server model for distributed applications in heterogeneous networks. This paper presents concepts for a software architecturethat is based on Real-Time CORBA for hard real-time applications. These applications are in common timetriggeredcommunication systems like TTP/C The aim is to develop a middleware concept for timetriggered architectures as aplatform for the software development of upcoming x-by-wire systems. The advantage of a middleware concept is that the distribution of the objects is transparent for the user and that the support of interoperability is guaranteed. An Object Request Broker (ORB) is responsible for the complete object management. Therefore, a developer does not have to take care for it. This paper examines the problems with CORBA on time-triggered architectures and shows possible solutions for the use of Real-Time CORBA on TTP/C