The rapid expansion of electric vehicles (EVs) charging stations underscores the urgent need for robust anomaly detection systems capable of identifying potential malfunctions while preserving data privacy. Federated Learning (FL) has emerged as a promising solution, enabling collaborative model training without requiring raw data sharing. However, applying conventional FL approaches to charging station networks presents significant challenges, including non-independent and identically distributed (non-IID) data and gradient conflicts among clients. To address these challenges, we introduce FedPareto, a novel Pareto-optimal FL framework designed to manage gradient conflicts and counter malicious attacks in charging station anomaly detection. FedPareto features a gradient conflict-aware aggregation method, which adaptively adjusts client weights based on cosine similarity between gradients, and a gradient magnitude reshaping strategy to enhance model convergence. Theoretical analysis demonstrates that FedPareto achieves a convergence rate of O($\frac{1}{T}$) and attains Pareto-optimal solutions under standard smoothness and convexity assumptions. Extensive experiments on real-world charging station datasets validate FedPareto’s effectiveness. It outperforms state-of-the-art methods, exhibits better robustness against gradient-based attacks, and ensures equitable performance distribution across clients. These results highlight FedPareto’s potential as a reliable and scalable solution for anomaly detection in EV charging station networks.

With the widespread adoption of large language models (LLMs) like GPT, user experiences in various interactive applications have significantly improved. However, reports from OpenAI highlight that GPT clients are now facing high response delays and frequent interruptions, particularly during peak usage hours, due to limited computation resources. This challenge is expected to escalate as machines are interacting with GPT models at higher frequencies, with greater data volumes, and over longer lifecycles. A promising solution is to deploy LLMs across edge networks to efficiently distribute the huge resource demands. This work presents the very first efforts at exploring how to cost-effectively deploy expert models from a mixture of experts (MoE) LLM within edge networks. We introduce the expert models deployment in edge networks (EMD-EN) problem, focusing on optimizing deployment costs. To address this, we propose a novel least cost gain (LCG) measure for selecting appropriate physical nodes to host expert models and present a corresponding LCG-based expert models deployment (LCGEMD) algorithm. Extensive simulations show that our approach outperforms the benchmarks by an average of 17.31% and 36.98% in terms of deployment cost reduction.

Traffic state estimation (TSE) is critical in underpinning the route planning of intelligent transportation systems (ITS). In light of vertical split traffic data might be from various entities, such as municipal authority (MA) and multiple mobility providers (MPs), vertical federated learning (VFL)-based TSE is proposed to resolve the vertical data privacy issue. However, due to discrepancies in data collection and missing data imputation technologies of MPs, the data quality of MPs regarding the same road segment might vary. To this end, we propose a reliable VFL-based TSE framework, including data provider selection and VFL model training. Concretely, given the high-dimension nature of traffic data, the MA will train a tiny mutual information (MI) model for data provider selection. After that, the MA will split the well-trained MI model into sub-models and top models and deploy them on MPs and MA, respectively, so as to preserve the nature of VFL. Eventually, upon MI models, the most representative MP of each road segment is selected for a reliable VFL model. Numerical simulation on real-world datasets shows that our framework augments the performance of traffic flow and traffic density by 11.23% and 21.15% in comparison with the baseline without data provider selection.

The surge in Internet video traffic driven by 5G advancement strains network infrastructure. Edge computing emerges as a solution for video distribution, yet faces challenges from limited cache capacity and dynamic user requests. To address these challenges, we propose IceCache - a recommendationdriven edge Caching architecture for the life cycle of video streaming. IceCache enhances Quality of Experience (QoE) while reducing backhaul traffic through two-stage caching: cache placement before playback, dynamic prefetching and cache admission during playback. A user behavior simulation integrating recommender systems was developed to evaluate the proposed caching strategy. Experiments on real-world MovieLens and synthetic datasets validated the strategy's performance.

federated graph learning (FGL) has emerged as a promising paradigm for privacy-preserving collaborative learning in Social Internet of Things (SIoT), where nodes form complex interconnected networks. Existing FGL approaches face significant challenges including model degradation in handling nonindependent and identically distributed (non-IID) data and maintaining model performance across heterogeneous nodes. This article proposes framework via layer-wised clustering (FedLWC), a novel layer-wised clustering framework inspired by evolutionary processes is proposed to enhance the effectiveness of FGL. FedLWC designs three key aspects: 1) a fisher information matrix-based layer selection mechanism that identifies and evaluates critical model layers, which can reduce parameter redundancy; 2) a layer intersection clustering algorithm that preserves common key layers while accommodating local features; and 3) an adaptive layer merge strategy that effectively combines global shared layers with clustered key layers. To make sure that the proposed approach is rigorous, we conduct theoretical convergence analysis for the proposed framework under non-IID conditions. Extensive experiments on multiple benchmark graph datasets demonstrate FedLWC’s performance, achieving an average accuracy improvement of 7.01% compared to state-of-the-art federated learning methods.

Advanced AI-Generated Content (AIGC) technologies have injected new impetus into teleoperation, enhancing its security and efficiency. Edge AIGC networks have been introduced to meet the stringent low-latency requirements of teleoperation. However, the inherent uncertainty of AIGC service quality and the need to incentivize AIGC service providers (ASPs) make the design of a robust incentive mechanism essential. This design is particularly challenging due to uncertainty and information asymmetry, as teleoperators have limited knowledge of the remaining resource capacities of ASPs. To this end, we propose a distributionally robust optimization (DRO)-based contract theory to design robust reward schemes for AIGC task offloading. Notably, our work extends the contract theory by integrating DRO, addressing the fundamental challenge of contract design under uncertainty. In this paper, we employ contract theory to model information asymmetry while utilizing DRO to capture the uncertainty in AIGC service quality. Given the inherent complexity of the original DRO-based contract theory problem, we reformulate it into an equivalent, tractable bi-level optimization problem. To efficiently solve this problem, we develop a Block Coordinate Descent (BCD)-based algorithm to derive robust reward schemes. Simulation results on our unitybased teleoperation platform demonstrate that the proposed method improves teleoperator utility by 2.7% to 10.74% under varying degrees of AIGC service quality shifts and increases ASP utility by 60.02% compared to the SOTA method, i.e., Deep Reinforcement Learning (DRL)-based contract theory. The code and data are publicly available at https://github.com/Zijun0819/DROContract-Theory

Integrating low-light image enhancement techniques, in which diffusion-based AI-generated content (AIGC) models are promising, is necessary to enhance nighttime teleoperation. Remarkably, the AIGC model is computation-intensive, thus necessitating the allocation of AIGC tasks to edge servers with ample computational resources. Given the distinct cost of the AIGC model trained with varying-sized datasets and AIGC tasks possessing disparate demand, it is imperative to formulate a differential pricing strategy to optimize the utility of teleoperators and edge servers concurrently. Nonetheless, the pricing strategy formulation is under information asymmetry, i.e., the demand (e.g., the difficulty level of AIGC tasks and their distribution) of AIGC tasks is hidden information to edge servers. Additionally, manually assessing the difficulty level of AIGC tasks is tedious and unnecessary for teleoperators. To this end, we devise a framework of AIGC task allocation assisted by the Vision Language Model (VLM)-empowered contract theory, which includes two components: VLM-empowered difficulty assessment and contract theory-assisted AIGC task allocation. The first component enables automatic and accurate AIGC task difficulty assessment. The second component is capable of formulating the pricing strategy for edge servers under information asymmetry, thereby optimizing the utility of both edge servers and teleoperators. The simulation results demonstrated that our proposed framework can improve the average utility of teleoperators and edge servers by$10.88 \sim 12.43\%$and$1.4\! \sim \!2.17\%$, respectively.

In the emerging applications of edge computing (e.g., unmanned factories and meta-verse), network requests are required to be securely and reliably delivered in the form of service function chains (SFCs). To enhance security, security-aware SFs are employed in the SFC, and this type of SFC is referred to as the security-aware SFC (S-SFC). For reliability, service providers can employ a dedicated backup SFC to protect the primary one. However, no existing works addressed the SFC deployment mechanisms that jointly consider SFC reliability and security. For this, here, we investigate the problem of jointly embedding and protecting a security-aware SFC. To efficiently compose, embed, and protect an S-SFC, we propose the S-SFC asymmetric protection concept, which allows the primary and backup SFCs not necessarily to follow an identical structure as the traditional SFC dedicated protection does. Next, we formulate the problem of S-SFC composing, embedding, and protection (S-SFCEP) and prove its NP-hardness. To tackle this problem, we formulate an efficient algorithm, namely, sub-chain-based S-SFC deployment (SCB-SD). Our extensive simulation results show that the proposed SCB-SD outperforms the state-of-the-art benchmarks by an average of 13.86% and 23.19%, respectively.

Since the data samples on client devices are usually non-independent and non-identically distributed (non-IID), this will challenge the convergence of federated learning (FL) and reduce communication efficiency. This paper proposes FedQMIX, a node selection algorithm based on multi-agent reinforcement learning(MARL), to address these challenges. Firstly, we observe a connection between model weights and data distribution, and a clustering algorithm can group clients with similar data distribution into the same cluster. Secondly, we propose a QMIX-based mechanism that learns to select devices from clustering results in each communication round to maximize the reward, penalizing the use of more communication rounds and thereby improving the communication efficiency of FL. Finally, experiments show that FedQMIX can reduce the number of communication rounds by 11% and 30% on the MNIST and CIFAR-10 datasets, respectively, compared to the baseline algorithm(Favor).

Since fog nodes are resource-constrained and imperfectly trusted heterogeneous devices, guaranteeing a real-time response to Internet of Things (IoT) tasks while optimizing system energy consumption remains a significant challenge. To overcome this, we first propose a acrlong DBC-enabled cloud–fog collaborative task scheduling architecture. Second, a task scheduling model is constructed to optimize system energy consumption and task deadline violation time while adhering to the IoT task response time restriction. Finally, two blockchain-enabled task scheduling algorithms are developed: 1) the reputation-based priority-aware algorithm (DB_RP) and 2) the accelerated ant colony system algorithm (DB_AACS). Extensive experiments are conducted to assess the proposed algorithm in four dimensions: 1) task completion rate; 2) system makespan; 3) system energy consumption; and 4) task deadline violation time. The experimental results demonstrate that the proposed algorithm is superior to the existing literature, and the acceleration strategy in DB_AACS is effective.

Due to an increasing amount of users, service providers are paying more attentions on how to properly tackle the User Allocation (UA) problem. In the literature, few solutions to the UA problem took into account the heterogeneity of devices and the complexity of the network. Therefore, the paper takes these two factors into account and studies the UA problem in Non-Orthogonal Multiple Access (NOMA)-Based heterogeneous edge computing scenarios. To solve the above problem, we propose the Heuristic Ant colony Systems (HAS) algorithm, which aims to enhance the number of allocated users while reducing the overall deadline violation time. Extensive evaluations that employ a public dataset demonstrate the benefits of our proposed approach.

With the rapid development of the mobile Internet and the Internet of Things (IoT), the conventional centralized cloud computing environment is facing severe challenges, such as high latency, and low bandwidth which significantly reduces the user experience for the applications of Virtual Reality (VR), HD Video, etc. Mobile Edge Computing (MEC) architecture can shift several tasks to devices on the edge of the mobile network, decreasing the service time and relieving the flow pressure of the core network. Combining Software Defined Networking (SDN) and MEC, this paper proposes a MEC network model based on SDN and builds test models on physical devices. A set of network testing experiments is carried out to evaluate the performance of the topology. Meanwhile, motivated by the demand for quick processing of surveillance video, an intelligent video processing acceleration application is deployed on the testing platform and cloud computing platform. Under the control of a Floodlight controller, it shows that the MEC scheme proposed in this paper has better performance when carrying latency-sensitive services.