Cross-layer Design Research Articles

COAC: Cross-Layer Optimization of Accelerator Configurability for Efficient CNN Processing

To achieve high accuracy, convolutional neural networks (CNNs) are increasingly growing in complexity and diversity in layer types and topologies. This makes it very challenging to efficiently deploy such networks on custom processor architectures for resource-scarce edge devices. Existing mapping exploration frameworks enable searching for the optimal execution schedules or hardware mappings of individual network layers, by optimizing each layer’s spatial (dataflow parallelization) and temporal unrolling (TU, execution order). However, these tools fail to take into account the overhead of supporting different unrolling schemes within a common hardware architecture. Using a fixed unrolling scheme across all layers is also not ideal, as this misses significant opportunities for energy and latency savings from optimizing the mapping of diverse layer types. A balanced approach assesses the right amount of mapping flexibility needed across target neural networks, while taking into account the overhead to support multiple unrollings. This article, therefore, presents cross-layer optimization of accelerator configurability (COAC), a cross-layer design space exploration and mapping framework to optimize the flexibility of neural processing architectures by balancing configurability overhead against resulting energy and latency savings for end-to-end inference. COAC does not only provide a systematical analysis of the architectural overhead in function of the supported spatial unrollings (SUs), but also builds an automated flow to find the best unrolling combination(s) for efficient end-to-end inference with limited hardware overhead. Results demonstrate that architectures with carefully optimized flexibility can achieve up to 38% energy-delay-product (EDP) savings for a set of six neural networks at the expense of a relative area increase of 9.5%.

Cross-Layer Design for Combining Adaptive Modulation and Coding with DMMPP Queuing for Wireless Networks

Cross-Layer Design for Combining Adaptive Modulation and Coding with DMMPP Queuing for Wireless Networks

Ultraviolet random access collaborative networking protocol based on time division multiple access

The ultraviolet network, with its advantages of high security, non-line-of-sight communication, and all-weather operation, has broad military application potential. This study proposes an ultraviolet random access collaborative networking protocol based on time division multiple access that combines the benefits of synchronous and asynchronous media access control protocols. Considering the physical layer characteristics, the frame structure of the protocol is constructed based on a cross-layer design. Compared with the time division multiple access protocol, the proposed protocol can achieve higher throughput with a lower delay and packet loss rate by the dynamic timeslot allocation mechanism. Then, the effects of maximum cache capacity and burst traffic on network performance are investigated. Finally, the conducted network experiments prove the cooperative forwarding and random access capabilities of the ultraviolet random access collaborative networking protocol. The proposed protocol provides a reliable and effective method for independent and flexible ultraviolet networks.

Resource allocation optimization for mitigating multi-jammer in underwater sensor network

<p class="16">Wireless underwater sensor networks (UWSNs) are used for coastal area monitoring and military monitoring applications, such as tsunami prevention and target tracking. In UWSNs, jamming is considered to be a serious problem where the intruder affects the lifetime of sensor motes and impacts the performance of the packet transmission. This paper considers that the jammer device is capable of reducing battery life and preventing the trustworthy UWSN mote from communication. Considering the presence of multiple jammers, the existing resource utilization model is not effective. This work presents an efficient resource allocation design to mitigate multiple jammers in UWSNs to overcome research problems. The resource allocation (ERA) model adopts a cross-layer design and can interact in a cooperative manner using direct and hop-based communication to maximize the quality of resource use. Compared to existing resource allocation methodologies, considering the presence of multiple jammer motes, the ERA achieves a much better detection rate, resource utilization, packet drop, and energy efficiency performance.</p>

Intelligent multichannel cross-layer framework for enhanced energy-efficiency in 6G-IoT wireless networks

The sixth-generation (6G) communication technology is expected to enable a fully-connected world with enhanced wireless connectivity, accessibility, reliability, and performance. 6G systems will be critical in addressing the massive-connectivity requirements for Internet-of-Things (IoT) networks. Cognitive radio (CR) technology is considered a promising solution in 6G networks that can provide tremendous spectrum opportunities to support large-scale IoT deployments. Due to the IoT’s energy-constrained and massively connected nature, existing CR-based communication protocols cannot be directly implemented in 6G-IoT networks. This is because they are usually designed to enhance spectrum-utilization in networks with finite users. Therefore, energy-efficient protocols are required to support the massive-connectivity requirement for energy-constrained IoT nodes. Non-persistent Carrier-Sense-Multiple-Access (CSMA)-based protocols are recognized as energy-effective spectrum-access paradigms for networks with massive users. This paper proposes a novel energy-efficient multi-channel cross-layer MAC framework that utilizes a non-persistent CSMA protocol in CR-enabled 6G-IoT networks. Based on a joint adaptation of the physical and MAC layer parameters, our framework aims to improve IoT networks’ energy efficiency (EE). Specifically, we formulate and solve the per-bit EE maximization problem subject to several design constraints. Numerical results show that our multi-channel cross-layer framework enhances network EE by up to 50% compared to a reference single-channel cross-layer design.

A Cross-Layer Design Approach to Strategic Cyber Defense and Robust Switching Control of Cyber-Physical Wind Energy Systems

Due to the increasing adoption of smart sensing and Internet of things (IoT) devices, wind energy system (WES) becomes more vulnerable to cyber and physical attacks. Therefore, designing a secure and resilient WES is critical. This paper first proposes a system-of-systems (SoS) framework for the cyber-physical WES. Specifically, on the one hand, we adopt a game-theoretic model to capture the interactions between the WES system defender and the adversary at the cyber layer. The outcome of this cyber defense game is reflected by control-aware Nash equilibria. On the other hand, we devise a cyber-aware robust and resilient switching controller based on a Markov jump linear system model for the physical WES. The performances of the WES cyber and physical layers are interdependent due to their natural couplings. We further investigate the SoS equilibrium of the integrated WES, which considers the system security, robustness, and resilience holistically. Finally, we use case studies to corroborate the developed cross-layer design principles for the cyber-physical WES. Note to Practitioners—Cybersecurity becomes a critical concern of wind energy system (WES) operators as an increasing amount of IoT devices are adopted for WES’s communication, monitoring, and operation support purposes. This cyber-physical integration in WES creates a much broader attack surface because adversaries can compromise the physical WES by attacking its dependent cyberspace. To mitigate the impact of attacks, the operator should not only design intelligent control strategies for WES but also strategically secure the WES’s cyber layer. These two goals are naturally coupled together. On the one hand, the WES operates under different compromised conditions depending on the attack actions at the cyber layer. Thus, the control design needs to be adversary-aware by taking the real-time cyber state into account. On the other hand, the adversary’s cyberattack strategy is influenced by the induced performance degradation of WES. Hence, the corresponding attack measures and countermeasures, in turn, should be physically control-aware. This paper establishes a holistic mathematical framework to simultaneously address these two challenging objectives. The obtained solution provides guidelines for the WES operator on the optimal security resource investment in defending against cyberattacks and the robust switching control design to mitigate the impacts of attacks further. This methodology creates a defense-in-depth paradigm for the WES operators to maintain the energy system efficiency in the adversarial environment. This cross-layer design approach is also efficient and user-friendly for online implementation with the developed iterative algorithm. The simulated-based case studies in this paper show the effectiveness of the proposed approach. However, a more thorough validation of the method in practice is necessary before its integration with the production standard.

A Novel Cross-Layer Adaptive Fuzzy-Based Ad Hoc On-Demand Distance Vector Routing Protocol for MANETs

One of the essential processes in Mobile Ad hoc Networks (MANETs) is blind flooding to discover routes between source and destination mobile nodes. As the density of nodes in the network increases, the number of broadcast packets increases exponentially. This can lead to broadcast storms, a drain on the device’s battery, and reduced network efficiency. We propose a Cross-layer Adaptive Fuzzy-based Ad hoc On-Demand Distance Vector routing protocol (CLAF-AODV) to minimize the routing broadcast traffic by considering the quality of service (QoS) (e.g. delay, throughput, packet loss), stability, and adaptability of the network. The suggested method employs two-level fuzzy logic and a cross-layer design approach to select the appropriate nodes with a higher probability of participating in broadcasting by considering parameters from the three first layers of the Open Systems Interconnection (OSI) model to achieve a quality of service, stability, and adaptability. It not only investigates the quality of the node and the network density around the node to make a decision but also investigates the path that the broadcast packet traveled to reach this node. Simulation results reveal that our proposed protocol reduces the number of broadcast packets and significantly improves network performance with respect to throughput, packet loss, normalized routing load, collision rate, and average energy consumption compared to the standard AODV and the Fixed Probability AODV (FP-AODV) algorithms.

Loose Coupling: An Invisible Thread in the History of Technology

We present an interdisciplinary survey of the history of loosely coupled systems. We apply the presented concepts in communication networks and suggest hybrid self-organizing networks (SONs) as a universal model for future networks. Self-organizing networks can fulfill the tight requirements of future networks but are challenging to use due to their complexity and immaturity. Moreover, the lack of an externally defined goal and centralized control has resulted in many distributed self-organizing systems failing. This is because the nonlinear relationships between the system parts result in emergence, i.e., we cannot predict the behavior of the whole from the behavior of the parts. Furthermore, a set of local optima does not produce a global optimum. Hybrid SONs tackle these challenges with loose or weak coupling of interacting agents that combine centralized control for global optimization with distributed control for local optimization. In the loose centralized control of almost autonomous agents, decisions are made mostly locally with small delays. This architecture has beneficial properties such as stability, obtained by decoupling the feedback loops: vertically with time-scale separation and horizontally with interference avoidance. Applications of loose coupling include modular electronics and computer design, structured software design, and service-oriented architectures, especially for microservices. Cross-layer design for network optimization is a new reason to use loose coupling in networks to improve stability. We also summarize some recent trends and present a roadmap to the future. We expect that loose coupling will be widely used in self-organizing networks of future wireless systems.

Cross-Layer MAC/Routing Protocol for Reliability Improvement of the Internet of Things

The IEEE 802.15.4 standard is recognized as one of the most successful for short-range low-rate wireless communications and is used in Internet of Things (IoT) applications. To improve the performance of wireless networks, interest in protocols that rely on interaction between different layers has increased. Cross-layer design has become an issue in wireless communication systems as it can improve the capacity of wireless networks by optimizing cooperation between multiple layers that constitute network systems. Power efficiency and network scalability must be addressed to spread IoT. In multi-hop networks, many devices share wireless media and are geographically distributed; consequently, efficient medium access control (MAC) and routing protocols are required to mitigate interference and improve reliability. Cross-layer design is a novel network design approach to support flexible layer techniques in IoT. We propose a cross-layer protocol for the MAC layer and routing layer to satisfy the requirements of various networks. The proposed scheme enables scalable and reliable mesh networking using the IEEE 802.15.4 standard and provides robust connectivity and efficient path discovery procedures. It also proposes a novel address-allocation technique to improve address-allocation methods that cannot support large sensor networks. Simulation results indicate that the proposed scheme could improve reliability and reduce end-to-end delay.

A Deep Reinforcement Learning-Based QoS Routing Protocol Exploiting Cross-Layer Design in Cognitive Radio Mobile Ad Hoc Networks

In this paper, we propose a novel deep reinforcement learning-based quality-of-service (QoS) routing protocol, namely DRQR, exploiting cross-layer design to establish efficient QoS (EQS) routes in cognitive radio mobile ad hoc networks. An EQS route is a route with minimum end-to-end (E2E) queuing delay subject to QoS constraints such as link stability, residual energy, number of hops and avoiding licensed channels of primary users. Particularly, we propose an NP-complete optimization problem which has a feasible solution as an EQS route. To tackle this problem, we design a new deep reinforcement learning model which supports the DRQR protocol to establish EQS routes in real time by offline training instead of online training like most of literature studies. Moreover, the DRQR protocol guarantees to have high system performance. A mathematical analysis of the E2E queuing delay with random waypoint mobility model also provides to verify simulation results. Numerical results show that the DRQR protocol outperforms state-of-the-art routing protocols in terms of routing delay, queuing delay, control overhead, PDR and energy consumption.

Quality of Service-Based Cross-Layer Protocol for Wireless Sensor Networks

Sensor nodes in wireless sensor networks (WSN) are used for perceiving, monitoring, and controlling a wide range of applications. Owing to the small size of sensor nodes and limited power sources, energy saving is critical for ensuring network longevity. Protocols in different layers consume energy for their function. It is possible to significantly reduce energy usage by including energy-efficiency measures in the protocol design. Most protocols in the literature focus on the energy efficiency in individual layers. Recent studies have shown that cross-layer designs are more energy efficient than individual layer designs. Therefore, this study presents a cross-layer protocol design that combines network and data link layers to minimize energy consumption. This article proposes a novel "Quality of Service Based Cross-layer (QSCL) Protocol" by combining the IEEE 802.15.4-based MAC protocol and the LEACH-based routing protocol. The dynamic duty cycle of the IEEE 802.15.4 protocol was modified based on the amount of data present in the node, which minimized the energy consumption of the data-transfer mechanism. The cluster head (CH) selection of the LEACH-based protocol was modified to consider the average residual energy (RE) of the nodes and their distance from the sink. This helps preserve the energy in the CH, thereby extending the network lifetime. Simulation studies demonstrated that the proposed QSCL outperformed the existing protocols by prolonging the network lifetime.

Routing and Resource Allocation for IAB Multi-Hop Network in 5G Advanced

Integrated access and backhaul (IAB) is a novel feature for extending the network coverage in 5G cellular networks, based on sharing/efficient allocation of owner’s spectrum traditionally reserved for access. However, since ultra-reliability and low latency (URLLC) requirements are a key component of 5G advanced services, provisioning such services present stringent challenges for IAB multi-hop network design. To fulfill the URLLC requirements in the IAB network, we propose a cross-layer design on routing and resource allocation under the current 3rd Generation Partnership Project (3GPP) 5G standards. We first formulate a routing problem for the IAB multi-hop network, which minimizes the latency while satisfying the reliability requirement. Subsequently, we present a reinforcement learning (RL) framework to solve the resource allocation and routing problem based on the local information of each agent (IAB node) in the environment. Afterward, we propose a novel entropy-based RL algorithm with federated learning (FL) mechanism to improve the overall performance as well as accelerate the convergence speed. Via the simulation, the proposed algorithm outperforms baseline algorithms from the latency and reliability perspective, respectively. Meanwhile, the convergence speed with the proposed algorithm also improves by using FL.

E2HRL: An Energy-efficient Hardware Accelerator for Hierarchical Deep Reinforcement Learning

Recently, Reinforcement Learning (RL) has shown great performance in solving sequential decision-making and control in dynamic environment problems. Despite its achievements, deploying Deep Neural Network (DNN)-based RL is expensive in terms of time and power due to the large number of episodes required to train agents with high dimensional image representations. Additionally, at the interference the large energy footprint of deep neural networks can be a major drawback. Embedded edge devices as the main platform for deploying RL applications are intrinsically resource-constrained and deploying deep neural network-based RL on them is a challenging task. As a result, reducing the number of actions taken by the RL agent to learn desired policy, along with the energy-efficient deployment of RL, is crucial. In this article, we propose Energy Efficient Hierarchical Reinforcement Learning (E2HRL), which is a scalable hardware architecture for RL applications. E2HRL utilizes a cross-layer design methodology for achieving better energy efficiency, smaller model size, higher accuracy, and system integration at the software and hardware layers. Our proposed model for RL agent is designed based on the learning hierarchical policies, which makes the network architecture more efficient for implementation on mobile devices. We evaluated our model in three different RL environments with different level of complexity. Simulation results with our analysis illustrate that hierarchical policy learning with several levels of control improves RL agents training efficiency and the agent learns the desired policy faster compared to a non-hierarchical model. This improvement is specifically more observable as the environment or the task becomes more complex with multiple objective subgoals. We tested our model with different hyperparameters to achieve the maximum reward by the RL agent while minimizing the model size, parameters, and required number of operations. E2HRL model enables efficient deployment of RL agent on resource-constraint-embedded devices with the proposed custom hardware architecture that is scalable and fully parameterized with respect to the number of input channels, filter size, and depth. The number of processing engines (PE) in the proposed hardware can vary between 1 to 8, which provides the flexibility of tradeoff of different factors such as latency, throughput, power, and energy efficiency. By performing a systematic hardware parameter analysis and design space exploration, we implemented the most energy-efficient hardware architectures of E2HRL on Xilinx Artix-7 FPGA and NVIDIA Jetson TX2. Comparing the implementation results shows Jetson TX2 boards achieve 0.1 ∼ 1.3 GOP/S/W energy efficiency while Artix-7 FPGA achieves 1.1 ∼ 11.4 GOP/S/W, which denotes 8.8× ∼ 11× better energy efficiency of E2HRL when model is implemented on FPGA. Additionally, compared to similar works our design shows better performance and energy efficiency.

Performance Analysis of Cross-Layer Design for Internet of Underwater Things

Underwater communication is a diverse and complex environment and has many problems. There are many problems in modeling and operating underwater networks. Physical and data link layer specifications for underwater networking should be taken into account in terms of quality of service metrics. In this study, we construct an underwater simulation environment as a cross-layer design consisting of physical and data link layers for the Internet of Underwater Things (IoUT) Network. The IoUT network has sensors with various priorities, a central node as a hub and a gateway as a buoy. The underwater sensors communicate with CSMA/ CA-based IEEE 802.15.6 protocol on low frequencies. For a more realistic communication channel, all the features of the acoustic channel are designed and performance analyzes are discussed. In addition, the proposed IoUT is compared with terrestrial network results in terms of bit error rate, signal-to-noise ratio, packet loss ratio, end-to-end delay, radio receiver utilization, and throughput. We claim that we have made a realistic IoUT network, especially for divers, autonomous underwater vehicles with specific sensors, or for similar purposes.

Cross-layer greedy forwarding algorithm for VANET

In recent years, vehicular communication systems have taken an important place in Intelligent Transport Systems (ITS). These systems are designed on self-organizing networks, known as Vehicular Ad hoc NETworks (VANETs). Their objective is to struggle against road safety problems and road traffic congestion by integrating information and communication technologies in road infrastructures and vehicles. VANET differs from other types of ad hoc networks by high mobility and very dynamic topology. Consequently, the design of an efficient VANET routing protocol becomes a challenging task. Many routing schemes with QoS (Quality of Service) have been proposed in the literature for VANET, to satisfy the performances required by the different applications running upon such networks. Cross-layer designs, which make it possible to exchange and share information between the different layers of the network, have shown to be efficient in VANETs. This paper proposes an improved version of the geographic Greedy algorithm as a cross-layer routing protocol for VANETs. The cooperation between the network layer and the lower layers involves three cyber-physical parameters: Speed, position and Signal-to-Noise Ratio (SNR). The simulation results over the Network Simulator-3 (NS3) demonstrated the effectiveness of the proposed solution in terms of end-to-end delay, throughput and packet delivery ratio.

Cross-layer design for real-time grid operation: Estimation, optimization and power flow

In this paper, we propose a combined Online Feedback Optimization (OFO) and dynamic estimation approach for a real-time power grid operation under time-varying conditions. A dynamic estimation uses grid measurements to generate the information required by an OFO controller, that incrementally steers the controllable power injections set-points towards the solutions of a time-varying AC Optimal Power Flow (AC-OPF) problem. More concretely, we propose a quadratic programming-based OFO that guarantees satisfying the grid operational constraints, like admissible voltage limits. Within the estimation, we design an online power flow solver that efficiently computes power flow approximations in real time. Finally, we certify the stability and convergence of this combined approach under time-varying conditions, and we validate its effectiveness on a simulation with a test feeder and high resolution consumption data.

Cross-Layer Design for UAV-Based Streaming Media Transmission

Unmanned Aerial Vehicle (UAV)-based streaming media transmission may become unstable when the bit rate generated by the source load exceeds the channel capacity owing to the UAV location and speed change. The change of the location can affect the network connection, leading to reduced transmission rate; the change of the flying speed can increase the video payload due to more I-frames. To improve the transmission reliability, in this paper we design a Client-Server-Ground&User (C-S-G&U) framework, and propose an algorithm of splitting-merging stream (SMS) for multi-link concurrent transmission. We also establish multiple transport links and configure the routing rules for the cross-layer design. The multi-link transmission can achieve higher throughput and significantly smaller end-to-end delay than a single-link especially in a heavy load situation. The audio and video data are packaged into the payload by the Real-time Transport Protocol (RTP) before being transmitted over the User Datagram Protocol (UDP). The forward error correction (FEC) algorithm is implemented to promote the reliability of the UDP transmission, and an encryption algorithm to enhance security. In addition, we propose a Quality of Service (QoS) strategy so that the server and the user can control the UAV to adapt its transmission mode dynamically, according to the load, delay, and packet loss. Our design has been implemented on an engineering platform, whose efficacy has been verified through comprehensive experiments.

Cross Layer Based Dynamic Traffic Scheduling Algorithm for Wireless Multimedia Sensor Network

The data traffic volume is generally huge in multimedia networks since it comprises multimodal sensor nodes also communication takes place with variable capacity during video transmission. The data should be processed in a collision free mode. Therefore, the packets should be scheduled and prioritized dynamically. Dynamic traffic scheduling and optimal routing protocol with cross layer design is proposed here to select the energy efficient nodes and to transmit the scheduled data effectively. At first, the optimal routes are discovered by selecting the best prime nodes then the packets are dynamically scheduled on the basis of severity of data traffic. The proposed method works in two stages such as (i) Selection of chief nodes and (ii) Dynamic packet scheduling. The first stage of this mechanism is chief node selection and these chief nodes are selected for optimal routing. Selection of chief nodes is done by estimating the distance between the nodes, and energy value of the nodes. This stage makes the network energy efficient. The second stage is involved with dynamic scheduling of packets and sending the packets with respect to the Packet Priority of queue index key value. Real-time data packets (PQP1) have very high priority and it is scheduled using Earliest Deadline First Scheduling (EDFS) algorithm when compared to non-real time data packets (PQP2 and PQP3) which is scheduled on basis of First Come First Serve (FCFS) manner. This process minimizes the congestion and avoids the unnecessary transmission delay. Therefore, the results are analyzed through the simulation process and the efficiency of the proposed methodology is 56% better than the existing methodologies.

An Efficient Cross Layer Design of Stability Based Clustering Scheme Using Ant Colony Optimization in VANETs

An Efficient Cross Layer Design of Stability Based Clustering Scheme Using Ant Colony Optimization in VANETs

Research on Communication and Monitoring of Construction Machinery under the Framework of Wireless Sensor Network

Aiming at the problem that the current wireless sensor network performance is low and cannot meet the requirements of high-precision synchronous acquisition of mechanical vibration signals, this paper proposes a synchronous acquisition method (SACD) based on cross-layer design. Based on this monitoring mode, an experimental platform is constructed to conduct a vibration signal measurement experiment, and compared with the wired vibration signal test and analysis method. The results show that the vibration monitoring mode based on the wireless sensor network can meet the basic requirements of mechanical vibration monitoring applications.