Federated Learning (FL) is an emerging approach in edge computing for collaboratively training machine learning models among multiple devices, which aims to address limited bandwidth, system heterogeneity, and privacy issues in traditional centralized training. However, the existing federated learning methods focus on learning a shared global model for all devices, which may not always be ideal for different devices. Such situations become even worse when each edge device has its own data distribution or task. In this paper, we study personalized federated learning in which our goal is to train models to perform well for individual clients. We observe that the initialization in each communication round causes the forgetting of historical personalized knowledge. Based on this observation, we propose a novel Personalized Federated Learning (PFL) framework via self-knowledge distillation, named pFedSD. By allowing clients to distill the knowledge of previous personalized models to current local models, pFedSD accelerates the process of recalling the personalized knowledge for the latest initialized clients. Moreover, self-knowledge distillation provides different views of data in feature space to realize an implicit ensemble of local models. Extensive experiments on various datasets and settings demonstrate the effectiveness and robustness of pFedSD.

Federated learning, as one enabling technology of edge intelligence, has gained substantial attention due to its efficacy in training deep learning models without data privacy and network bandwidth concerns. However, due to the heterogeneity of the edge computing system and data, many methods suffer from the “ client-drift ” issue that could considerably impede the convergence of global model training: local models on clients can drift apart, and the aggregated model can be different from the global optimum. To tackle this issue, one intuitive idea is to guide the local model training by global teachers, i.e. , past global models, where each client learns the global knowledge from past global models via adaptive knowledge distillation techniques. Inspired by these insights, we propose a novel approach for heterogeneous federated learning, F ed GKD, which fuses the knowledge from historical global models and guides local training to alleviate the “ client-drift ” issue. In this paper, we evaluate F ed GKD through extensive experiments across various CV and NLP datasets (i.e., CIFAR-10/100, Tiny-ImageNet, AG News, SST5) under different heterogeneous settings. The proposed method is guaranteed to converge under common assumptions and outperforms the state-of-the-art baselines in the non-IID federated setting.

The dc–dc modular multilevel converter (dc–dc MMC) with a medium-frequency ac-link transformer is a promising candidate for the modern electric ship medium voltage dc power system to provide galvanic isolation, flexible voltage regulation, and fault ride through ability. However, the steady states and dynamics of such an isolated dc–dc MMC are rather complicated because it contains many state variables. Moreover, the on-ship requirements further complicate the system design. This paper thus proposes the modeling and control of such a dc–dc MMC. Based on the fact that such a dc–dc MMC is controlled by the phase-shifted operation, the fundamental period averaging (FPA) method is applied to obtain the steady-state and small-signal models, and based on the on-ship requirements, the modulation index control as well as the simple but efficient competitive dual closed loops (a voltage loop for normal condition and a current loop for overload condition) are designed. It is proved that the FPA method can preserve the necessary model information about the dc–dc MMC, and the proposed controllers can be well designed based on the steady-state and small-signal FPA models by compromising the on-ship requirements. The analysis and design results are verified by the simulations and experiments.

Transportation carbon emission is a significant contributor to the increase of greenhouse gases, which directly threatens the change of climate and human health. Under the pressure of the environment, it is very important to master the information of transportation carbon emission in real time. In the traditional way, we get the information of the transportation carbon emission by calculating the combustion of fossil fuel in the transportation sector. However, it is very difficult to obtain the real-time and accurate fossil fuel combustion in the transportation field. In this paper, we predict the real-time and fine-grained transportation carbon emission information in the whole city, based on the spatio-temporal datasets we observed in the city, that is taxi GPS data, transportation carbon emission data, road networks, points of interests (POIs), and meteorological data. We propose a three-layer perceptron neural network (3-layerPNN) to learn the characteristics of collected data and infer the transportation carbon emission. We evaluate our method with extensive experiments based on five real data sources obtained in Zhuhai, China. The results show that our method has advantages over the well-known three machine learning methods (Gaussian Naive Bayes, Linear Regression, and Logistic Regression) and two deep learning methods (Stacked Denoising Autoencoder and Deep Belief Networks).

Currently, edge devices generate massive amounts of data. Considering the heavy burden of network and service delay requirements of delay-sensitive applications, processing the data at network edge is appropriate. However, limited capacities of edge devices often influence the service quality. Effective offloading is widely used to address this issue. But when facing device heterogeneity problem and task complexity increase, service quality degradation and resource utility decrease occur due to unreasonable task distribution. Since conventional offloading strategies show limited performance in complex environment, we are motivated to design a useful dynamic regional resource scheduling framework considering multiple indexes. Thus, in this paper we first propose a double offloading framework to simulate the offloading in real edge scenario which consists of different edge servers and devices. Then we formulate the offloading as a Markov Decision Process (MDP) and utilize a deep reinforcement learning (DRL) algorithm named asynchronous advantage actor-critic (A3C) as the offloading decision making strategy to balance the workload and finally reduce the overhead in terms of energy and time. Comparison experiments for local computing and wide-used DRL algorithm DQN are conducted in a comprehensive benchmark and the results show that our work performs much better on self-adjusting and overhead reduction.

Network applications involve massive heterogeneous data fusion and analysis. Artificial intelligence can significantly improve the convenience and user experience, but it requires a lot of storage, bandwidth, and computing resources. Multiaccess edge computing (MEC) extends intelligence services to IoT devices through offloading approaches and joint processing, which solves the resource bottleneck. However, designing advanced collaboration technology to offload tasks to MEC servers is still challenging. Heuristic algorithms and deep reinforcement learning (DRL)-based approaches have been proposed to offload tasks and minimize application latency. However, heuristic algorithms heavily depend on accurate mathematical models for the MEC system, and DRL does not make fair use of the relationship between devices in the MEC graph. To solve this, we propose a task offloading mechanism based on graph neural network (GNN), which can directly learn on graph data with messages passing and aggregation. We propose a graph reinforcement learning-based offloading (GRLO) framework, which models MEC as an acyclic graph and the offloading policy by graph state migration. GRLO combines GNN with the actor-critic network and trains offloading decision makers without labels. To efficiently train the GRLO, we propose a method that quickly explores action space and approaches the optimal solution. The numerical results show that the GRLO has lower latency compared to baselines while having generalization ability to new environments and topologies. Moreover, we verified the effectiveness of GRLO on a prototype.