Federated learning is a privacy-preserving machine learning technique that trains models across multiple devices holding local data samples without exchanging them. There are many challenging issues in federated learning, such as coordinating participants’ activities, arbitrating their benefits, and aggregating models. Most existing solutions employ a centralized approach, in which a trustworthy central authority is needed for coordination. Such an approach incurs many disadvantages, including vulnerability to attacks, lack of credibility, and difficulty in calculating rewards. Recently, blockchain was identified as a potential solution for addressing the abovementioned issues. Extensive research has been conducted, and many approaches, methods, and techniques have been proposed. There is a need for a systematic survey to examine how blockchain can empower federated learning. Although there are many surveys on federated learning, few of them cover blockchain as an enabling technology. This work comprehensively surveys challenges, solutions, and future directions for blockchain-empowered federated learning (BlockFed). First, we identify the critical issues in federated learning and explain why blockchain provides a potential approach to addressing these issues. Second, we categorize existing system models into three classes: decoupled, coupled, and overlapped, according to how the federated learning and blockchain functions are integrated. Then we compare the advantages and disadvantages of these three system models, regard the disadvantages as challenging issues in BlockFed, and investigate corresponding solutions. Finally, we identify and discuss the future directions, including open problems in BlockFed.

Large language models (LLMs) have shown great success in content generation and intelligent intelligent decision-making for IoT systems. Traditionally, LLMs are deployed on the cloud, incurring prolonged latency, high bandwidth costs, and privacy concerns. More recently, edge computing has been considered promising in addressing such concerns because edge devices are closer to data sources. However, edge devices are cursed by their limited resources and can hardly afford LLMs. Existing studies address such a limitation by offloading heavy workloads from edge to cloud or compressing LLMs via model quantization. These methods either still rely heavily on the remote cloud or suffer substantial accuracy loss. This work is the first to deploy LLMs on a collaborative edge computing environment, in which edge devices and cloud servers share resources and collaborate to infer LLMs with high efficiency and no accuracy loss. We design EdgeShard, a novel approach to partition a computation-intensive LLM into affordable shards and deploy them on distributed devices. The partition and distribution are non-trivial, considering device heterogeneity, bandwidth limitations, and model complexity. To this end, we formulate an adaptive joint device selection and model partition problem and design an efficient dynamic programming algorithm to optimize the inference latency and throughput. Extensive experiments of the popular Llama2 serial models on a real-world testbed reveal that EdgeShard achieves up to 50% latency reduction and 2x throughput improvement over the state-of-the-art.

Nowadays, a great number of healthcare data are generated every day from both medical institutions and individuals. Healthcare information exchange (HIE) has been proved to benefit the medical industry remarkably. To store and share such large amount of healthcare data is important while challenging. In this paper, we propose BlocHIE, a Blockchain-based platform for healthcare information exchange. First, we analyze the different requirements for sharing healthcare data from different sources. Based on the analysis, we employ two loosely-coupled Blockchains to handle different kinds of healthcare data. Second, we combine off-chain storage and on-chain verification to satisfy the requirements of both privacy and authenticability. Third, we propose two fairness-based packing algorithms to improve the system throughput and the fairness among users jointly. To demonstrate the practicability and effectiveness of BlocHIE, we implement BlocHIE in a minimal-viable-product way and evaluate the proposed packing algorithms extensively.

Supply chain management (SCM) is fundamental for gaining financial, environmental and social benefits in the supply chain industry. However, traditional SCM mechanisms usually suffer from a wide scope of issues such as lack of information sharing, long delays for data retrieval, and unreliability in product tracing. Recent advances in blockchain technology show great potential to tackle these issues due to its salient features including immutability, transparency, and decentralization. Although there are some proof-of-concept studies and surveys on blockchain-based SCM from the perspective of logistics, the underlying technical challenges are not clearly identified. In this paper, we provide a comprehensive analysis of potential opportunities, new requirements, and principles of designing blockchain-based SCM systems. We summarize and discuss four crucial technical challenges in terms of scalability, throughput, access control, data retrieval and review the promising solutions. Finally, a case study of designing blockchain-based food traceability system is reported to provide more insights on how to tackle these technical challenges in practice.

This paper discusses how the state-of-the-art techniques in cyber-physical systems facilitate building smart warehouses to achieve the promising vision of industry 4.0. We focus on four significant issues when applying CPS techniques in smart warehouses. First, efficient CPS data collection: when limited communication bandwidth meets numerous CPS devices, we need to make more effort to study efficient wireless communication scheduling strategies. Second, accurate and robust localization: localization is the basis for many fundamental operations in smart warehouses, but still needs to be improved from various aspects like accuracy and robustness. Third, human activity recognition: human activity recognition can be applied in human–computer interaction for remote machine operations. Fourth, multi-robot collaboration: smart robots will take the place of humans to accomplish most tasks particularly in a harsh environment, and smart and fully-distributed robot collaborating algorithms should be investigated. Finally, we point out some challenging issues in the future CPS-based smart warehouse, which could open some new research directions.