Search-and-rescue (SAR) operations in collapsed buildings requires sensing systems that are reliable, fast, and robust to cluttered environments. This paper introduces OHL-CIR, a simulation-driven framework for RF-based human detection and localization beneath rubble. By generating a large and diverse dataset of channel impulse responses (CIRs), the framework enables reproducible evaluation across multiple rubble scenarios. OHL-CIR employs a two-stage inference pipeline: binary classification for victim presence, followed by regression for 2D localization. Results show detection accuracy above 95% across all categories and sub-centimeter localization errors. A precision–stability tradeoff is observed: Gradient Boosting achieves the finest precision in structured settings, while Random Forest maintains robustness under diverse rubble conditions. CIR analyses confirm physics-consistent perturbations and density maps demonstrate how predictions can guide UAV search paths. These findings position OHL-CIR as both accurate and interpretable, with strong potential for deployment in UAV-assisted SAR and broader applications in IoT localization and future 6G systems.

This paper presents a reliability analysis framework for distributed computing in extreme edge computing (XEC) with limited information availability. XEC pushes computation to the outermost boundaries of networks by leveraging consumer-owned devices, known as Extreme Edge Devices (XEDs). Unlike traditional distributed systems with defined computational resource states, XEC operates under uncertainty due to consumer device usage patterns, varying computational capacities, and local scheduling algorithms. In this work, we address discrete task assignment particularly. The framework analyzes scenarios for computational reliability assessments with minimal knowledge of XED capabilities and service requirements. The framework adapts to different levels of available information, from operational limits to historical performance data, providing refined reliability estimates. The aim of this work is to provide generalized reliability models for distributed computing in XEC that allow decision-makers (e.g. service orchestrators) to make informed decisions about task allocation, service placement, and resource allocation under uncertainty in XEC. Simulations and experimental analysis demonstrate the framework's effectiveness in estimating reliability under various system conditions.

Extreme Edge Computing (XEC) is a serverless edge computing paradigm where computational tasks are offloaded to and from extreme edge devices (XEDs). XEDs, a subset of IoT devices that consists of consumer-owned devices capable of offering computational resources. Being data-rich, XEDs can facilitate the training of more accurate Machine Learning (ML) models. However, their unpredictable computational behavior, which follows the consumers’ usage, and transient availability pose challenges that traditional Federated Learning (FL) approaches may struggle to address. To this end, we propose a new framework for decentralized FL in XEC systems designed to address the computational reliability of XEDs and optimize the computational resource allocation. Moreover, to encourage XEDs’ participation in the FL training process, we introduce an Auction-based incentive mechanism. This mechanism models the interactions between XEDs, considering both the computational characteristics and the data quality of XEDs. Furthermore, we present two solution approaches: an optimization approach and a heuristic approach, each introducing a complexity-performance trade-off. Finally, we evaluate and demonstrate the effectiveness of our proposed framework in improving the performance and reliability of XEDs in decentralized learning environments.

Edge computing seeks to optimize service provision over enterprise-owned infrastructure near the end-user at the network’s edge. However, it misses out on the opportunity to utilize user-owned hardware at the extreme edge of the network as workers in a sharing economy. In this work, we build upon the existing Incentive Vacation Queueing (IVQ) model and develop the Virtual Kiosk Model (VKM) to analyze service availability and the dynamics of multiple workers’ participation in the provision of a service on the extreme edge. We formulate an optimization problem to minimize total cost of incentive payments while maintaining service availability under temporal constraints. We propose the Model-based Incentive Strategy at the Edge (MISE) algorithm to iteratively adjust incentives in real-time. MISE is compared against traditional numerical optimizers and a baseline naive approach that greedily focuses on minimizing incentives. Our findings demonstrate that MISE ensures sustained service availability without overburdening the workers at a cost acceptable to the service provider, striking a crucial balance in the management of extreme edge computing resources.

The conventional approach for Federated Learning (FL) is to train a global model by averaging local models trained on local data sets. However, given the limited computing resources at the mobile-edge nodes, unreliable models may be received from the Edge Nodes (ENs), which can lead to a significant performance degradation in the FL. Thus, this paper proposes a reliable and age sensitive FL framework that captures the dynamic nature of the local data and computing resources at each participating EN. Specifically, we formulate two optimization problems to select the optimal subset of ENs that can upload their local models in each round of the global model training, given a limited learning cost budget. The first problem aims at selecting the most reliable ENs that should cooperate to complete the FL process, while considering stationary data distributions at different ENs. The second problem aims at minimizing the average age of information experienced by each EN while selecting the most reliable ENs, given fast changing data distributions. Efficient solutions are proposed for the two problems with a worst-case linear complexity. Our Results, leveraging a real-world dataset, depict the efficiency of our solutions in obtaining a better performance compared to conventional FL approach.

The extremely heavy global reliance on IoT devices is causing enormous amounts of data to be gathered and shared in IoT networks. Such data need to efficiently be used in training and deploying of powerful artificially intelligent models for better future event detection and decision making. However, IoT devices suffer from many limitations regarding their energy budget, computational power, and storage space. Therefore, efficient solutions have to be studied and proposed for addressing these limitations. In this paper, we propose an energy-efficient Hierarchical Federated Learning (HFL) framework with optimized client-edge association and resource allocation. This was done by formulating and solving a communication energy minimization problem that takes into consideration the data distribution of the clients and the communication latency between the clients and edges. We also implement an alternative less complex solution leveraging Reinforcement Learning (RL) that provides a fast user-edge association and resource allocation response in highly dynamic HFL networks. The proposed two solutions are compared with several state-of-the-art client-edge association techniques, leveraging MNIST dataset. Moreover, we study the trade-off between minimizing the per-round energy consumption and Kullback-Leibler Divergence (KLD) of the data distribution, and its effect on the total energy consumption.

Mobile Edge Learning (MEL) is a learning paradigm that facilitates training of Machine Learning (ML) models over resource-constrained edge devices. MEL consists of an orchestrator, which represents the model owner of the learning task, and learners, which own the data locally. Enabling the learning process requires the model owner to motivate learners to train the ML model on their local data and allocate sufficient resources. The time limitations and the possible existence of multiple orchestrators open the doors for the resource allocation problem. As such, we model the incentive mechanism and resource allocation as a multi-round Stackelberg game, and propose a Payment-based Time Allocation (PBTA) algorithm to solve the game. In PBTA, orchestrators first determine the pricing, then the learners allocate each orchestrator a timeslot and determine the amount of data and resources for each orchestrator. Finally, we evaluate the PBTA performance and compare it against a recent state-of-the-art approach.

Mobile Edge Learning (MEL) is a decentralized learning paradigm that enables resource-constrained IoT devices to either learn a shared model without sharing the data, or to distribute the learning task with the data to other IoT devices and utilize their available resources. In the former case, IoT devices (a.k.a learners) need to be assigned an orchestrator to facilitate the learning and models' aggregation from different learners. Whereas in the latter case, IoT devices act as orchestrators and look for learners with available resources to distribute the learning task to. However, the coexistence of multiple learning problems in an environment with limited resources poses the learners-orchestrator assignment problem. To this end, we aim to develop an energy-efficient learner assignment and task allocation scheme, in which each orchestrator gets assigned a group of learners based on their communication channel qualities and computational resources. We formulate and solve a multi-objective optimization problem to minimize the total energy consumption and maximize the learning accuracy. To reduce the solution complexity, we also propose a lightweight heuristic algorithm that can achieve near-optimal performance. The conducted simulations show that our proposed approaches can execute multiple learning tasks efficiently and significantly reduce energy consumption compared to current state-of-art methods.

The recent pandemic along with the rapid increase in the number of patients that require continuous remote monitoring imposes several challenges to support the high quality of services (QoS) in remote health applications. Remote-health (r-health) systems typically demand intense data collection from different locations within a strict time constraint to support sustainable health services. On the contrary, the end-users with mobile devices have limited batteries that need to run for a long time, while continuously acquiring and transmitting health-related information. Thus, this paper proposes an adaptive deep reinforcement learning (DRL) framework for network selection over heteroge-neous r-health systems to enable continuous remote monitoring for patients with chronic diseases. The proposed framework allows for selecting the optimal network(s) that maximizes the accumulative reward of the patients while considering the patients' state. Moreover, it adopts an adaptive compression scheme at the patient level to further optimize the energy consumption, cost, and latency. Our results depict that the proposed framework outperforms the state-of-the-art techniques in terms of battery lifetime and reward maximization.

The rapid production of mobile and wearable devices along with the wireless applications boom is continuing to evolve everyday. This motivates network operators to integrate and exploit wireless spectrum across multiple radio access networks to cope with such intensive demand, while improving quality of service. However, it is crucial to develop innovative network selection techniques that consider heterogeneous networks characteristics, while meeting applications' quality requirements. Thus, this paper develops an optimal network selection with resource allocation scheme over heterogeneous networks that aims to optimize the latency, cost, and energy consumption, while accounting for data compression at the edge. Indeed, our framework could significantly enhance the performance of wireless healthcare systems by enabling data transfer from patients edge nodes to the cloud in cost-effective and energy-efficient manner, while maintaining strict Quality of Service (QoS) requirements of health applications. Our simulation results depict that our solution significantly outperforms state-of- the-art techniques in terms of energy consumption, latency, and cost.

The rapid evolution of remote health monitoring applications is foreseen to be a crucial solution for facing an unpredictable health crisis and improving the quality of life. However, such applications come with many challenges, including: the transmission of a large amount of private medical data and the limited power budget for battery-operated devices. Thus, this article proposes an intelligent, secure, and energy-efficient (I-SEE) framework for secure and energy-efficient medical data transmission, leveraging the potential of physical-layer security. In particular, we incorporate a practical secrecy metric, namely, the secrecy outage probability (SOP), along with the adaptive compression at the edge for providing a secure solution for health monitoring applications. In the proposed framework, we first formulate an optimization problem that maximizes the energy efficiency, while maintaining quality-of-service constraints of the health application. Second, we propose a deep reinforcement learning process that obtains the optimal strategy for secure data transmission. Specifically, a multiobjective reward function is defined to optimize energy efficiency and distortion, resulting from the compression scheme. Then, a deep deterministic policy gradients (DDPGs) algorithm, named Static-DDPG is proposed to solve our problem efficiently. Third, the problem is extended to consider the battery lifetime maximization with varying channel conditions. Indeed, a Dynamic-DDPG algorithm is proposed in order to allow the edge to adapt to the environment dynamics while maximizing its battery lifetime. The conducted simulations validate the efficiency of the proposed algorithms in terms of finding the optimal policy that addresses the tradeoff between the considered conflicting objectives, along with the battery lifetime maximization