The integration of Mobile Edge Computing (MEC) and Blockchain has emerged as an efficient approach to support the development of secure and delay-sensitive Internet of Things (IoT) applications. Despite these advantages, blockchain-enabled IoT systems face a fundamental challenge because the security and trust benefits of blockchain are accompanied by additional computation and communication overheads that can degrade latency and energy efficiency in resource-constrained environments. This paper develops a unified multi-objective optimization framework for task offloading and resource allocation in blockchain-enabled IoT networks. The considered system architecture incorporates IoT devices, MEC servers, and a cloud data center while explicitly modeling blockchain operations as part of the offloading process. A multi-objective optimization problem is formulated to jointly minimize total system latency and energy consumption while maximizing the aggregate reputation of the selected blockchain management nodes. To solve this problem, two evolutionary solution approaches are employed. The Non-dominated Sorting Genetic Algorithm II (NSGA-II) is used to identify Pareto-optimal trade-off solutions, and a Genetic Algorithm (GA) is adopted to solve a weighted-sum scalarized formulation. Comprehensive simulation results indicate a demonstrable trade-off between latency and energy consumption. Specifically, the analysis reveals that prioritizing high-reputation nodes for blockchain consensus roles significantly reduces transaction verification latency, thereby enhancing the overall system performance despite the operational overheads. The framework allows stakeholders to select solutions that best meet specific IoT application requirements.

Network connectivity exposes network infrastructure and assets to vulnerabilities exploitable by attackers. Safeguarding these assets necessitates implementing security countermeasures. However, deploying countermeasures incurs various costs, including preparation and deployment time. Therefore, an Intrusion Response System (IRS) must consider both security and Quality of Service (QoS) costs when dynamically selecting countermeasures to address detected attacks. To address this challenge, we introduce a joint Security-vs-QoS optimization problem akin to the Weighted Set Cover Problem (WSCP), which is NP-complete. We propose two learning-based solutions leveraging Multi-Objective Reinforcement Learning and Deep Q-learning to navigate the security and QoS cost trade-off. Through extensive simulations under diverse settings, we validate the performance of our proposed solution, compare it with benchmark methods, and evaluate it using a project-derived 5G cybersecurity dataset.

Federated Split Learning (FSL) has emerged as a transformative paradigm that synergizes the parallel processing and scalability of Federated Learning (FL) with the computational efficiency and enhanced privacy of Split Learning (SL). This comprehensive survey provides a systematic exploration of FSL, beginning with a detailed taxonomy of Distributed Machine Learning (DML) paradigms, tracing the progression from foundational concepts to advanced frameworks such as Federated Split Transfer Learning (FSTL) and Generalized Federated Split Transfer Learning (GFSTL). It then delves into the core challenges inherent to FSL, including privacy and security risks, system and data heterogeneity, computational and system constraints, communication overhead, and model optimization complexities. The heart of the survey presents a detailed categorization and analysis of FSL's diverse applications across key domains, including the Internet of Things (IoT) and Edge Computing (EC), wireless networks, healthcare, vehicular networks, Large Language Models (LLMs), and Earth Observation (EO). To ground this research, the survey further discusses standardized evaluation methodologies and implementation frameworks, followed by a quantitative visualization of survey data and research trends. The work concludes by synthesizing critical research gaps and outlining promising future directions. By synthesizing insights from over 100 recent research articles and providing a critical analysis of evaluation methodologies, this survey offers an essential roadmap for researchers and practitioners developing scalable, efficient, and privacy-aware distributed intelligence for the 6G and AI era.

With the growing demand for multimedia services, Dynamic Adaptive Streaming over HTTP (DASH) has become a key solution for delivering high-quality video content. In this work, we consider an Edge-DASH scenario and formulate a joint optimization problem that involves four critical aspects: bitrate allocation, user-to-server assignment, caching, and bandwidth allocation. Due to the complexity of the joint problem, we decompose it into sub-problems and address them separately. To solve the resulting sub-problems, we employ deep reinforcement learning, specifically the Deep Deterministic Policy Gradient (DDPG) method, for three of them, and develop a heuristic solution for the fourth. Simulation results demonstrate that our approach enhances performance across multiple metrics, including improved video delivery, reduced buffer underflow and overflow, and more efficient caching, which collectively enable greater utilization of edge resources for streaming. Moreover, we evaluated inference latency across edge and cloud hardware, confirming sub- to few-millisecond performance suitable for real-time deployment. This showcases the benefits of combining learning-based and heuristic techniques to meet the growing demand for adaptive video streaming in edge computing environments.

Dynamic Adaptive Streaming over HTTP (DASH) is a promising solution to enhance the Quality of Experience (QoE) of mobile video services. In this paper, we consider an Edge-DASH scenario where two problems of Bitrate Allocation (BrA) and user-to-server allocation (USA) have been jointly formulated. Then, we exploit Deep Reinforcement Learning (DRL) algorithm to solve the USA problem and select the streaming point for users, which can be streaming from the Edge, Macro layer or cloud, and deliver the users the most appropriate bitrate respecting the QoE by solving the BrA problem. In the simulation results, we have demonstrated that our Deep Deterministic Policy Gradient (DDPG) outperforms the traditional solution in terms of bitrate allocation.

The rapid emergence of 5G technology brings new cybersecurity challenges that hold significant implications for our economy, society, and environment. Among these challenges, ensuring the effectiveness of Intrusion Detection Mechanisms (IDMs) in monitoring networks and detecting 5G-related cyberattacks is of utmost importance. However, optimizing cybersecurity levels and selecting appropriate IDMs remain as critical and ongoing challenges. This work considers multiple pre-deployed distributed Security Agents (SAs) across the network, each capable of running various IDMs, where they differ by their effectiveness in detecting the attacks (referred to as security term) and the consumption of resources (referred to as Quality of Service (QoS) costs). We formulate a joint security and QoS utility function leveraging the Cobb–Douglas production utility function. There are several parameters that impact the joint objective problem, including the set of elasticity parameters, that reflect the importance of the two objectives. We derive an optimal set of elasticity parameters in closed form to identify the balancing point where both objectives have equal utility values. Through comprehensive simulations, we demonstrate that increasing the detection level of SAs enhances the security utility while simultaneously diminishing the QoS utility, as more computational, bandwidth, and monetary resources are utilized for IDM processing. After optimization, our mechanism can strike an effective balance between cybersecurity and QoS overhead while demonstrating the importance of different parameters in the joint problem.

The advent of 5G technology introduces new - and potentially undiscovered - cybersecurity challenges, with unforeseen impacts on our economy, society, and environment. Interestingly, Intrusion Detection Mechanisms (IDMs) can provide the necessary network monitoring to ensure - to a big extent - the detection of 5G-related cyberattacks. Yet, how to realize the attack surface of 5G networks with respect to the detected risks, and, consequently, how to optimize the cybersecurity levels of the network, remains an open critical challenge. In respect, this work focuses on deploying multiple distributed Security Agents (SAs) that can run different IDMs over various network components and proposes a cybersecurity mechanism for optimizing the network’s attack surface with respect to the Quality of Service (QoS). The proposed approach relies on a new closed-form utility function to describe the trade-off between cybersecurity and QoS and uses multi-objective optimization to improve the selection of each SA detection level. We demonstrate via simulations that before optimization, an increase in the detection level of SAs brings a direct decrease in QoS as more computational, bandwidth and monetary resources are utilized for IDM processing. Thereby, after optimization, we demonstrate that our mechanism can strike a balance between cybersecurity and QoS while showcasing the impact of the importance of different objectives of the joint optimization.

With the rapid advancement of intelligent transportation systems (ITS) and vehicular communications, vehicular edge computing (VEC) is emerging as a promising technology to support low-latency ITS applications and services. In this paper, we consider the computation offloading problem from mobile vehicles/users in a heterogeneous VEC scenario, and focus on the network- and base station selection problems, where different networks have different traffic loads. In a fast-varying vehicular environment, computation offloading experience of users is strongly affected by the latency due to the congestion at the edge computing servers co-located with the base stations. However, as a result of the non-stationary property of such an environment and also information shortage, predicting this congestion is an involved task. To address this challenge, we propose an on-line learning algorithm and an off-policy learning algorithm based on multi-armed bandit theory. To dynamically select the least congested network in a piece-wise stationary environment, these algorithms predict the latency that the offloaded tasks experience using the offloading history. In addition, to minimize the task loss due to the mobility of the vehicles, we develop a method for base station selection. Moreover, we propose a relaying mechanism for the selected network, which operates based on the sojourn time of the vehicles. Through intensive numerical analysis, we demonstrate that the proposed learning-based solutions adapt to the traffic changes of the network by selecting the least congested network, thereby reducing the latency of offloaded tasks. Moreover, we demonstrate that the proposed joint base station selection and the relaying mechanism minimize the task loss in a vehicular environment.

Abstract: Security, Trust and Reliability are crucial issues in mobile 5G networks from both hardware and software perspectives. These issues are of significant importance when considering implementations over distributed environments, i.e., corporate Cloud environment over massively virtualized infrastructures as envisioned in the 5G service provision paradigm. The SANCUS1 solution intends providing a modular framework integrating different engines in order to enable next‐generation 5G system networks to perform automated and intelligent analysis of their firmware images at massive scale, as well as the validation of applications and services. SANCUS also proposes a proactive risk assessment of network applications and services by means of maximising the overall system resilience in terms of security, privacy and reliability. This paper presents an overview of the SANCUS architecture in its current release as well as the pilots use cases that will be demonstrated at the end of the project and used for validating the concepts.

In a mobile edge computing (MEC) network, mobile devices, also called edge clients, offload their computations to multiple edge servers that provide additional computing resources. Since the edge servers are placed at the network edge, e.g., cell-phone towers, transmission delays between edge servers and edge clients are shorter compared to those of cloud computing. In addition, edge clients can offload their tasks to other nearby edge clients with available computing resources by exploiting the Fog Computing (FC) paradigm. A major challenge in MEC and FC networks is to assign the tasks from edge clients to edge servers, as well as to other edge clients, in such a way that their tasks are completed with minimum energy consumption and minimum processing delay. In this paper, we model task offloading in MEC as a constrained multi-objective optimization problem (CMOP) that minimizes both the energy consumption and task processing delay of the mobile devices. To solve the CMOP, we design an evolutionary algorithm that can efficiently find a representative sample of the best trade-offs between energy consumption and task processing delay, i.e., the Pareto-optimal front. Compared to existing approaches for task offloading in MEC, we see that our approach finds offloading decisions with lower energy consumption and task processing delay.

Computation sharing is one of the most promising services in fog computing allowing the Fog Nodes (FNs) to share among themselves data and tasks to be computed. In case of battery powered-FNs, energy consumption becomes an issue. Simultaneous Wireless Information and Power Transfer (SWIPT) is a recently introduced technology enabling data and power transfer through microwave links among different nodes. In this work, we have considered the presence of a battery powered FN able to simultaneously share data and harvest energy from a Fog Access Point (F-AP), supposed to be plugged to the electrical network. The aim of this work is to define two suitable bounds able to drive the offloading decision to be taken by the battery powered FN, based on the estimated packet generation time, with the aim of having a stable energy system. We have further studied the impact of bandwidth and packet size on the two bounds. Simulation results demonstrate the impact of SWIPT-based offloading decision algorithm on network in terms of latency and network lifetime.

Edge Computing refers to a recently introduced approach aiming to bring the storage and computational capabilities of the cloud to the proximity of the edge devices. Edge Computing is one of the main techniques enabling Fog Computing and Networking. Among several application scenarios, the urban scenario seems one of the most attractive for exploiting edge computing approaches. However, in an urban scenario, mobility becomes a challenge to be addressed, affecting the edge computing. By gaining from the the presence of two types of devices, Fog Nodes (FNs) and Fog-Access Points (F-APs), the idea in this paper is that of exploiting Device to Device (D2D) communications between FNs for assisting computation offloading requests between FNs and F-APs by exchanging status information related to the F-APs. With this knowledge, this paper proposes a partial offloading approach where the optimal tasks amount to be offloaded is estimated for minimizing the outage probability due to the mobility of the devices. In order to reduce the outage probability we have further considered a relaying approach among F-APs. Moreover, the impact of the number of tasks that each F-AP can manage is shown in terms of task processing delay. Numerical results show that the proposed approaches allow to achieve performance closer to the lower bound, by reducing the outage probability and the task processing delay.

Fog Computing offers storage and computational capabilities to the edge devices by reducing the traffic at the fronthaul. A fog environment can be seen as composed by two main classes of devices, Fog Nodes (FNs) and Fog-Access Points (F-APs). At the same time, one of the major advances in 5G systems is decoupling the control and the data planes. With this in mind we are here proposing an optimization technique for a mobile environment where the Device to Device (D2D) communications between FNs act as a control plane for aiding the computational offloading traffic operating on the data plane composed by the FN - F-AP links. Interactions in the FNs layer are used for exchanging the information about the status of the F-AP to be exploited for offloading the computation. With this knowledge, we have considered the mobility of FNs and the F-APs' coverage areas to propose a partial offloading approach where the amount of tasks to be offloaded is estimated while the FNs are still within the coverage of their F-APs. Numerical results show that the proposed approaches allow to achieve performance closer to the ideal case, by reducing the data loss and the delay.

Fog computing is a fascinating paradigm which has drawn attention recently by bringing the cloud capabilities closer to the users. A fog computing infrastructure can be seen as composed by two layers: one including Fog Nodes (FNs) and another the Fog Access Points (F-APs). While FNs are usually battery operated, the F-APs are instead connected to the electrical networks having unlimited energy. Moreover, F-APs facilitate the computation of tasks due to their higher storage and computational capabilities compared to the FNs. Considering FN energy consumption and task processing delay, we propose a suboptimal partial offloading technique aiming at exploiting jointly both FNs and F-APs. The simulation results demonstrate how partial offloading has a profound impact on the network lifetime and reduces energy consumption and task processing delay by comparing the single and two layer architectures.