Limited Communication Resources Research Articles

Semi-Supervised Federated Learning Over Heterogeneous Wireless IoT Edge Networks: Framework and Algorithms

Federated learning (FL) is a promising paradigm for future sixth-generation wireless systems to underpin network edge intelligence for smart cities applications. However, most of the data collected by the Internet of Things devices in such applications is unlabeled, necessitating the use of semi-supervised learning. Existing studies have introduced solutions to run semi-supervised FL; however, they overlooked the inherent critical impacts of the wireless characteristics at the network edge. We fill this gap by proposing novel solutions to run semi-supervised FL over wireless network edge, considering the limited computation and communication resources and deadline constraints and realizing that unlabeled data can be automatically labeled during the training rounds to improve the performance of the global model. The problem is first formulated as an optimization problem followed by a two-phase solution. In the first phase, we propose a bisection-based algorithm to find the transmit power and local processing speed that optimally fit the new injected labeled data. In the second phase, we propose three algorithms to control the local updates and injected samples that meet the deadline constraint. We analyze the performance of each algorithm concerning the tradeoffs between learning performance, training time, and total energy consumption. Targeting two applications in smart cities, human activity recognition and object detection, we conduct extensive simulations using realistic federated data sets under nonindependent and identically distributed settings. Numerical results show that the proposed algorithms effectively utilize unlabeled samples while accounting for the characteristics of wireless edge networks in smart cities.

HPoC: A Lightweight Blockchain Consensus Design for the IoT

The research topics of this paper are the data security of the edge devices and terminals of the Internet of Things (IoT) and the consensus design of a lightweight blockchain for the Internet of Things. These devices have self-organization capabilities to overcome the bandwidth delay and service-congestion problems caused by excessive concentration in existing scenarios, but they face the challenges of limited computing, storage, and communication resources. As a result, a non- financial lightweight blockchain consensus design with low energy consumption, low latency, and greater stability should be investigated. We propose a hierarchical proof-of-capability (HPoC) consensus mechanism combined with the asynchronous proof-of-work (PoW) mechanism for improving the computing capacity, storage capacity, and communication capacity of IoT edge devices that can generate blocks with low latency, low power consumption, and strong stability in resource-constrained edge device nodes, while ensuring that the security of the edge devices is enhanced asynchronously. We simulated a smart-home scenario, with the number of device nodes ranging from 15 to 75, and conducted comparative experiments between HPoC and PoW based on different difficulty bits. The experimental results showed that HPoC is a consensus mechanism with scalability and stability that can flexibly adjust time consumption and accurately select nodes with strong capabilities to generate blocks in heterogeneous devices.

Predictive Closed-Loop Remote Control Over Wireless Two-Way Split Koopman Autoencoder

Real-time remote control over wireless is an important yet challenging application in fifth-generation and beyond due to its mission-critical nature under limited communication resources. Current solutions hinge on not only utilizing ultrareliable and low-latency communication (URLLC) links but also predicting future states, which may consume enormous communication resources and struggle with a short prediction time horizon. To fill this void, in this article we propose a novel two-way Koopman autoencoder (AE) approach wherein: 1) a sensing Koopman AE learns to understand the temporal state dynamics and predicts missing packets from a sensor to its remote controller and 2) a controlling Koopman AE learns to understand the temporal action dynamics and predicts missing packets from the controller to an actuator co-located with the sensor. Specifically, each Koopman AE aims to learn the Koopman operator in the hidden layers while the encoder of the AE aims to project the nonlinear dynamics onto a lifted subspace, which is reverted into the original nonlinear dynamics by the decoder of the AE. The Koopman operator describes the linearized temporal dynamics, enabling long-term future prediction and coping with missing packets and closed-form optimal control in the lifted subspace. Simulation results corroborate that the proposed approach achieves a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$38\times $ </tex-math></inline-formula> lower mean squared control error at 0-dBm signal-to-noise ratio (SNR) than the nonpredictive baseline.

Clustered Vehicular Federated Learning: Process and Optimization

Federated Learning (FL) is expected to play a prominent role for privacy-preserving machine learning (ML) in autonomous vehicles. FL involves the collaborative training of a single ML model among edge devices on their distributed datasets while keeping data locally. While FL requires less communication compared to classical distributed learning, it remains hard to scale for large models. In vehicular networks, FL must be adapted to the limited communication resources, the mobility of the edge nodes, and the statistical heterogeneity of data distributions. Indeed, a judicious utilization of the communication resources alongside new perceptive learning-oriented methods are vital. To this end, we propose a new architecture for vehicular FL and corresponding learning and scheduling processes. The architecture utilizes vehicular-to-vehicular(V2V) resources to bypass the communication bottleneck where clusters of vehicles train models simultaneously and only the aggregate of each cluster is sent to the multi-access edge (MEC) server. The cluster formation is adapted for single and multi-task learning, and takes into account both communication and learning aspects. We show through simulations that the proposed process is capable of improving the learning accuracy in several non-independent and-identically-distributed (non-i.i.d) and unbalanced datasets distributions, under mobility constraints, in comparison to standard FL.

Intelligent Event-Based Fuzzy Dynamic Positioning Control of Nonlinear Unmanned Marine Vehicles Under DoS Attack.

This article addresses the dynamic positioning control problem of a nonlinear unmanned marine vehicle (UMV) system subject to network communication constraints and deny-of-service (DoS) attack, where the dynamics of UMV are described by a Takagi-Sugeno (T-S) fuzzy system (TSFS). In order to save limited communication resource, a new intelligent event-triggering mechanism is proposed, in which the event triggering threshold is optimized by a Q -learning algorithm. Then, a switched system approach is proposed to deal with the aperiodic DoS attack occurring in the communication channels. With a proper piecewise Lyapunov function, some sufficient conditions for global exponential stability (GES) of the closed-loop nonlinear UMV system are derived, and the corresponding observer and controller gains are designed via solving a set of matrix inequalities. A benchmark nonlinear UMV system is adopted as an example in simulation, and the simulation results validate the effectiveness of the proposed control method.

State estimation of complex-valued neural networks with leakage delay: A dynamic event-triggered approach

In this paper, the problem of state estimation is investigated for a class of discrete-time complex-valued neural networks (CVNNs) with both leakage delay and discrete time-varying delays. The signal transmission from output sensors to state estimator is implemented via a shared wireless network with limited communication resources. For the aim of reducing the consumption of limited communication resources, the transmission strategy based on dynamic event-triggering is introduced to determine when the updating of the output measurement should be carried out. By taking use of some properties of Hermitian matrix and constructing an appropriate Lyapunov–Krasovskii functional, a sufficient criterion is derived for ensuring the asymptotical stability of the estimation error system without separating the CVNN to its real-part system and imagination one is derived, which is quite different from those approach used in exiting literature. The gain matrix for estimator is designed by resorting to a set of feasible solutions of linear matrix inequalities (LMIs) with complex-valued variables. A numerical example and its simulation results are given to illustrate the validity of the theoretical result.

Distributed time-varying out formation-containment tracking of multi-UAV systems based on finite-time event-triggered control

Considering the limited communication resources and slow convergence speed of multi-unmanned aerial vehicle (UAV) systems, this paper presents a finite-time even-triggered control framework for multi-UAV systems to achieve formation-containment tracking control. First, a virtual leader with time-varying output is introduced so that the trajectory of the whole system can be manipulated in real time. Second, the finite-time control enables that the systematic error converge to a small neighborhood of origin in finite time. Third, in order to save communication resources, an event-triggering function is developed to generate the control event sequences, which avoids continuous update of the controller. Rigorous proof shows the finite-time stability of the proposed control algorithm, and Zeno behavior is strictly excluded for each UAV. Finally, some numerical simulations are given to verify the effectiveness of the proposed controllers.

Neural network‐based event‐triggered cluster quasi‐consensus for unknown multiagent systems with directed topology

AbstractThis paper studies cluster quasi‐consensus problem for a class of unknown nonlinear multiagent systems (MASs) with directed communication topology. First, a distributed continuous neural network (NN)‐based adaptive protocol is presented for solving this problem by introducing reference model to each agent. Then, taking limited communication resource and energy consumption into account, a distributed event‐triggered cluster quasi‐consensus protocol is proposed. Different from the existing results, two event‐triggered mechanisms are constructed in the proposed event‐triggered protocol to reduce communication load and control update frequency as possible. The sufficient conditions that guarantee cluster quasi‐consensus under the both proposed protocols are obtained, respectively. Zeno behavior is proved to be excluded. Finally, simulation results verify the effectiveness of the proposed protocols.

Event-Triggered Cooperative Formation Control for Autonomous Surface Vehicles Under the Maritime Search Operation

To improve the autonomy of maritime search and rescue (SAR) operation, this paper concentrates on the formation control problem for autonomous surface vehicles (ASVs) with the limited communication resource. A novel parallel search guidance, considering the maneuvering characteristics of ASVs, is developed to guide the formation to execute the automatic SAR operation. That can guarantee that the corresponding guidance law is highly efficient, self-driving and suitable for the large-scale formation. Combined with the guidance principle, a formation control algorithm is proposed by fuse of the event-triggered control and neural networks (NNs). In the proposed scheme, the gain uncertainty of actuators is effectively compensated requiring no prior information around the model structure. Unlike the existing results, the proposed event-triggered mechanism can activate synchronously both the controller and the NNs weight estimator. Considerable effort has been made to guarantee the semi-global uniform ultimate bounded (SGUUB) stability. Finally, two examples are illustrated to verify the effectiveness of the algorithm.

Data-Driven Event-Triggered Platoon Control under Denial-of-Service Attacks

This paper proposes an event-triggered model-free adaptive platoon control (MFAPC) solution for non-linear vehicle systems under denial-of-service (DoS) attacks. First, the non-linear vehicle system is transformed into an equivalent linear data model using the dynamic linearization technique. Second, to save limited communication resources and reduce the influence of cyber attacks, a novel event-triggered mechanism and attack compensation method are designed. Then, based on the equivalent linear data model, a new resilient event-triggered MFAPC algorithm is developed to achieve the vehicle platoon control objective under DoS attacks. Finally, the effectiveness of the proposed control scheme is verified using an example.

Chattering-free nested adaptive terminal sliding mode control for PEMFC air supply system with event-triggered communication

Aiming at the proton exchange membrane fuel cell air supply system subject to time-varying external load, system uncertainty and limited network communication resources, a chattering-free event-triggered nested adaptive terminal sliding mode controller is first developed to achieve the tracking control of oxygen excess ratio. First, an integral terminal sliding mode function with recursive structure is designed to eliminate the reaching phase of sliding mode control and ensure that the high-frequency switching term only appears in the first derivative of control law. Then, to alleviate the communication burden, an event-triggered control strategy is adopted for the controller-to-actuator channel. Furthermore, a nested dual-layer adaptive law is constructed to adaptively update the robust gain without overestimation, so as to counteract the composite disturbance composed of the lumped system uncertainty and event-triggering error, which does not require priori upper bounds of the composite disturbance and its derivative. Besides, it is theoretically proved that the output tracking error can converge to the origin in finite time and the Zeno behavior can be strictly excluded. Finally, the adaptability and superiority of the proposed event-triggered nested adaptive terminal sliding mode controller are fully validated by a series of numerical simulations and comparative analysis.

MR-TopoMap: Multi-Robot Exploration Based on Topological Map in Communication Restricted Environment

Multi-robot exploration in unknown environments is a fundamental task for a multi-robot system, involving inter-robot communication through messages among the robots. However, in a restricted communication environment, the limited communication resources become the system's bottleneck due to a large amount of data in the occupancy grid map. Hence, to enhance multi-agent exploration in communication-constrained environments, this letter develops a method to build topological maps while the robot moves in the environment and an exploration strategy based on the created topological map. The latter map comprises a set of vertices and edges connecting the vertices, where each vertex represents a specific area embedded with a descriptor extracted by visually observing this area and recognizing it utilizing descriptors. Each robot has its local grid map stored for path planning, not shared between them. Considering the exploration task, a robot's ability to choose a proper direction depends on the other robot's locations and the unexplored areas. Our exploration framework is evaluated on the Gazebo simulator and real robots, increasing the exploration efficiency by 23% <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 77%. Compared with the occupancy grid map scheme, our method's data transfer is reduced by 84% <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 90%.

Cooperative Localization in Mobile Robots Using Event-Triggered Mechanism: Theory and Experiments

This article addresses a new cooperative localization problem for a team of mobile robots subject to limited communication resources. First, we develop a decentralized event-triggered cooperative localization (DECL) algorithm for multirobot system such that each robot localizes itself with minimum communication exchange between robots. Then, using an event-triggered mechanism we propose an optimization framework to achieve a balance between estimation performance and communication rate. Simulation results show the main benefits of the event-triggered mechanism. Also, experimental results using four e-puck2 mobile robots demonstrate the effectiveness of the proposed method. Note to Practitioners—Multiple mobile robots are able to implement certain tasks that are beyond the capabilities of individual robots. In multirobot system, the accurate localization of each robot in the team is essential for a successful operation. Existing cooperative localization approaches neglect some realistic limitations of mobile robots, such as battery capacity and communication bandwidth. Especially, this issue is important when the number of sensors, actuators, and robots in the team increases. This article was motivated by these realistic limitations of mobile robots and it suggests a new approach for cooperative localization based on event-triggered mechanism. Motived by the aforementioned discussion, our objective is to design and implement the event-triggered cooperative localization for a group of e-puck2 robots. Our theoretical analysis and experimental results show that we achieve a tradeoff between localization accuracy and communication resources.

Investigation of the competitive nature of eMBB and mMTC 5G services in conditions of limited communication resource.

The main contribution of the investigation is the Markov model of the process of resource allocation management between subscribers of eMBB and mMTC services within the 5G cluster. The proposed model, considers the organization of the channel resource in the format of resource blocks. The presented model allows to estimate the average duration of IoT sessions, the average number of active multimedia/IoT sessions, the average number of channel resource units occupied by multimedia/IoT traffic, the average number of resource blocks occupied by multimedia/IoT traffic. The metrics are generalized by three management schemes of the investigated process: balanced, competitive and perspective. The first and third schemes enable static/dynamic distribution of channel resources into reserved and common segments for subscribers of eMBB and mMTC services. The proposed model is illustrated with an example showing how to assess the availability and efficiency of channel resource use of the 5G cluster of the cyber-physical system of the Situation Center of the Department of Information Technology of Vinnytsia City Council (Vinnytsia, Ukraine). The article also shows how to use the proposed model to select the 5G network parameters to keep the probabilities of rejection of multimedia and IoT requests below a set threshold.

Research on Discrete Artificial Bee Colony Cache Strategy of UAV Edge Network

Unmanned aerial vehicle edge networks (UENs) can reduce the cache load of the core network and improve system performance to provide users with efficient content services. However, the time-varying characteristics of content popularity in UENs lead to a low accuracy of popularity prediction, and the capacity limitations of wireless channel conditions lead to a lower cache hit rate than the rates of traditional fiber-optic-based cache strategies. Therefore, this paper proposes the discrete artificial bee colony cache strategy of UENs (DABCCSU). First, the information–dynamics–dissemination model of UENs (IDDMU) is established to deduce the coupling relationship between the channel capacity and the service probability in IDDMU. The influence of the service probability change on the content dissemination process is discussed, and the content popularity in UENs is predicted by the state iteration matrix. Then, the discrete artificial bee colony cache (DABCC) optimization algorithm is proposed. The action function of the artificial bee colony is designed as a random action based on the historical cache strategy. The discrete cache strategy is used as an optimization variable, and the popularity prediction result obtained by IDDMU is used to maximize the cache hit rate. DABCC provides the optimal cache strategy for the UENs, and effectively improves the cache hit rate. The simulation result shows that the accuracy of DABCCSU in content popularity prediction is more than 90%, which achieves a good prediction effect. In terms of cache performance, the average cache hit rate of DABCCSU is 91.62%, which is better than the 51.09% of the Least Recently Used (LRU) strategy, 89.27% of the Greedy Algorithm (GA) and 54.26% of Binary Particle Swarm Optimization (BPSO). In addition, the cache hit rate of DABCCSU under different cache capacities is better than that of LRU, GA, and BPSO, showing a relatively stable performance. It shows that DABCCSU can achieve excellent content popularity prediction, and it can also maximize the cache hit rate under limited communication resources and cache resources to provide UENs with the optimal content cache strategy, and provides users with high-quality content services.

AoI-aware energy control and computation offloading for industrial IoT

In Industrial Internet of Things (IIoT), a large volume of data is collected periodically by IoT devices, and timely data routing and processing are important requirements. Age of Information (AoI), which is a metric to evaluate the freshness of status information in data processing, has become one of the most important objectives in IIoT. In this paper, considering limited communication, computation and energy resources on IoT devices, we jointly study the optimal AoI-aware energy control and computation offloading problem within a dynamic IIoT scenario with multiple IoT devices and multiple edge servers. Based on extensive analysis of real-life IoT dataset, Markovian queueing models are constructed to capture the dynamics of IoT devices and edge servers, and their corresponding analyses are provided. With the quantitative analytical results, we formulate a dynamic Markov decision problem with the objective of minimizing the long-term energy consumption while satisfying AoI constraints for real-time data processing. To solve the problem, we apply Deep Reinforcement Learning (DRL) techniques for adapting to large-scale dynamic IIoT environments, and design an intelligent Energy Control and Computation Offloading (ECCO) algorithm. Extensive simulation experiments are conducted based on real-world dataset, and the comparison results illustrate the superiority of our ECCO algorithm over both existing DRL and non-DRL algorithms.

Projective quasi-synchronization of coupled memristive neural networks with uncertainties and impulsive effect.

The dynamic behavior of memristive neural networks (MNNs), including synchronization, effectively keeps the robotic stability against numerous uncertainties from the mimic of the human brain. However, it is challenging to perform projective quasi-synchronization of coupled MNNs with low-consumer control devices. This is partly because complete synchronization is difficult to realize under various projective factors and parameter mismatch. This article aims to investigate projective quasi-synchronization from the perspective of the controller. Here, two approaches are considered to find the event-triggered scheme for lag synchronization of coupled MNNs. In the first approach, the projective quasi-synchronization issue is formulated for coupled MNNs for the first time, where the networks are combined with time-varying delays and uncertainties under the constraints imposed by the frequency of controller updates within limited system communication resources. It is shown that our methods can avoid the Zeno-behavior under the newly determined triggered functions. In the second approach, following classical methods, a novel projective quasi-synchronization criterion that combines the nonlinear property of the memristor and the framework of Lyapunov-Krasovskii functional (LKF) is proposed. Simulation results indicate that the proposed two approaches are useful for coupled MNNs, and they have less control cost for different types of quasi-synchronization.

Federated Learning Over Wireless IoT Networks With Optimized Communication and Resources

To leverage massive distributed data and computation resources, machine learning in the network edge is considered to be a promising technique, especially for large-scale model training. Federated learning (FL), as a paradigm of collaborative learning techniques, has obtained increasing research attention with the benefits of communication efficiency and improved data privacy. Due to the lossy communication channels and limited communication resources (e.g., bandwidth and power), it is of interest to investigate fast responding and accurate FL schemes over wireless systems. Hence, we investigate the problem of jointly optimized communication efficiency and resources for FL over wireless Internet of Things (IoT) networks. To reduce complexity, we divide the overall optimization problem into two subproblems, i.e., the client scheduling problem and the resource allocation problem. To reduce the communication costs for FL in wireless IoT networks, a new client scheduling policy is proposed by reusing stale local model parameters. To maximize successful information exchange over networks, a Lagrange multiplier method is first leveraged by decoupling variables, including power variables, bandwidth variables, and transmission indicators. Then, a linear-search-based power and bandwidth allocation method is developed. Given appropriate hyperparameters, we show that the proposed communication-efficient FL (CEFL) framework converges at a strong linear rate. Through extensive experiments, it is revealed that the proposed CEFL framework substantially boosts both the communication efficiency and learning performance of both training loss and test accuracy for FL over wireless IoT networks compared to a basic FL approach with uniform resource allocation.

Resource-Efficient Platooning Control of Connected Automated Vehicles Over VANETs

This paper is concerned with distributed cooperative longitudinal platooning control of connected automated vehicles over resource-constrained vehicular ad-hoc networks. First, a general platoon-based control framework is constructed, which simultaneously accounts for unknown leader control input, external disturbances, intermittent data samplings and transmissions, various spacing policies, and different vehicle-to-vehicle communication topologies. To alleviate excessive occupancy of the limited communication resources, an adaptive Zeno-free event-triggered communication mechanism is developed to determine when the sampling and transmission actions of vehicular data should be performed among interacting vehicles. Then, a scalable co-design approach for the desired adaptive platoon controller as well as event triggering condition is developed. One promising feature of the proposed platooning control strategy is that it is independent on the platoon scale or any global knowledge of the associated communication topology, and thus implementable on each vehicle in a scalable manner. Finally, several numerical case studies are conducted to verify the efficacy of the derived approach.

Adaptive appointed-time formation tracking control for multiple spacecraft with collision avoidance under a dynamic event-triggered mechanism

This paper focuses on the appointed-time formation control problem for multiple spacecraft with limited communication and control resources. The control objective is to make each spacecraft move along its reference trajectory with guaranteed tracking performance while avoiding collision with each other. To this end, we attempt to propose an event-triggered formation tracking control protocol to achieve this objective. Firstly, a sliding mode manifold containing formation tracking and velocity errors is designed. Then, a group of prescribed performance constraints are imposed on the transient and steady-state behaviors of the newly defined sliding mode manifold, to derive a formation controller with performance guarantees and appointed-time convergence. By integrating the artificial potential function, a collision-free control term is devised, which is plus after the foregoing formation tracking controller to avoid the collision between the neighboring spacecraft. Furthermore, to reduce unnecessary data transmission and improve resource utilization, a dynamic event-triggered strategy is proposed to determine when the developed controller updates. In this case, the threshold parameter in triggering condition is dynamically changed over time rather than being fixed, in order to achieve a desired balance between communication frequency and system performance. Compared with the existing works, the major advantage of the proposed control protocol is that the formation tracking performance, the collision avoidance and the communication transmission preservation can be assured simultaneously. Finally, comparative simulations illustrate the effectiveness of the proposed protocol.