In recent years, federated learning has been able to provide an effective solution for data privacy protection, so it has been widely used in financial, medical, and other fields. However, traditional federated learning still suffers from single-point server failure, which is a frequent issue from the centralized server for global model aggregation. Additionally, it also lacks an incentive mechanism, which leads to the insufficient contribution of local devices to global model training. In this paper, we propose a blockchain-based decentralized federated learning method, named BD-FL, to solve these problems. BD-FL combines blockchain and edge computing techniques to build a decentralized federated learning system. An incentive mechanism is introduced to motivate local devices to actively participate in federated learning model training. In order to minimize the cost of model training, BD-FL designs a preference-based stable matching algorithm to bind local devices with appropriate edge servers, which can reduce communication overhead. In addition, we propose a reputation-based practical Byzantine fault tolerance (R-PBFT) algorithm to optimize the consensus process of global model training in the blockchain. Experiment results show that BD-FL effectively reduces the model training time by up to 34.9% compared with several baseline federated learning methods. The R-PBFT algorithm can improve the training efficiency of BD-FL by 12.2%.

No abstract

Authentication is an important requirement for the security of edge computing applications. The existing authentication schemes either frequently rely on third-party trusted authorities, leading to the security risk of user information disclosure, or have high authentication overhead, causing certain pressure on the computation and communication of lightweight terminal equipment in the edge environment. In this paper, we proposed a blockchain-based anonymous authentication scheme for edge computing environments. We first designed a blockchain-based authentication architecture to store a small number of authentication elements in the blockchain network, and provide a decentralized and trusted authentication environment to ensure device anonymity and improve the security of authentication processes. Then, an elliptic cryptographic curve-based authentication scheme is proposed. It uses the chameleon hash function to dynamically generate the authentication data according to the elements stored in the blockchain and negotiate the session key, which effectively reduces the computational overhead in the authentication process. The experimental results show that the proposed scheme achieves a secure authentication process and effectively reduces the authentication overhead by up to 43.16% compared to three state-of-the-art schemes.

With the rise of latency-sensitive and computationally intensive applications in mobile edge computing (MEC) environments, the computation offloading strategy has been widely studied to meet the low-latency demands of these applications. However, the uncertainty of various tasks and the time-varying conditions of wireless networks make it difficult for mobile devices to make efficient decisions. The existing methods also face the problems of long-delay decisions and user data privacy disclosures. In this paper, we present the FDRT, a federated learning and deep reinforcement learning-based method with two types of agents for computation offload, to minimize the system latency. FDRT uses a multi-agent collaborative computation offloading strategy, namely, DRT. DRT divides the offloading decision into whether to compute tasks locally and whether to offload tasks to MEC servers. The designed DDQN agent considers the task information, its own resources, and the network status conditions of mobile devices, and the designed D3QN agent considers these conditions of all MEC servers in the collaborative cloud-side end MEC system; both jointly learn the optimal decision. FDRT also applies federated learning to reduce communication overhead and optimize the model training of DRT by designing a new parameter aggregation method, while protecting user data privacy. The simulation results showed that DRT effectively reduced the average task execution delay by up to 50% compared with several baselines and state-of-the-art offloading strategies. FRDT also accelerates the convergence rate of multi-agent training and reduces the training time of DRT by 61.7%.

Using the MRC (Miss Rate Curve) to guide cache capacity allocation is a common method in the storage system. However, optimal resource allocation is an NP-complete problem due to the cache performance cliff. Existing studies ignore this phenomenon or they use partitioning technology to eliminate it without considering the performance potential behind the cliff. This paper delves into this potential and proposes a cliff-aware cache resource allocation algorithm based on the inherent relationship between the capacity and the hit rate. Experiments show that these requests where the latency is less than 130 µs is increased by 33.3%. The proposed method obtains a significant cost reduction in DRAM and improves the hitting ratio of the cache layer.