Homogeneous Learning: Self-Attention Decentralized Deep Learning

Federated learning (FL) has been facilitating privacy-preserving deep learning in many walks of life such as medical image classification, network intrusion detection, and so forth. Whereas it necessitates a central parameter server for model aggregation, which brings about delayed model communication and vulnerability to adversarial attacks. A fully decentralized architecture like Swarm Learning allows peer-to-peer communication among distributed nodes, without the central server. One of the most challenging issues in decentralized deep learning is that data owned by each node are usually non-independent and identically distributed (non-IID), causing time-consuming convergence of model training. To this end, we propose a decentralized learning model called Homogeneous Learning (HL) for tackling non-IID data with a self-attention mechanism. In HL, training performs on each round’s selected node, and the trained model of a node is sent to the next selected node at the end of each round. Notably, for the selection, the self-attention mechanism leverages reinforcement learning to observe a node’s inner state and its surrounding environment’s state, and find out which node should be selected to optimize the training. We evaluate our method with various scenarios for two different image classification tasks. The result suggests that HL can achieve a better performance compared with standalone learning and greatly reduce both the total training rounds by 50.8% and the communication cost by 74.6% for decentralized learning with non-IID data.

Homogeneous Learning: Self-Attention Decentralized Deep Learning

Federated learning (FL) has been facilitating privacy-preserving deep learning in many walks of life such as medical image classification, network intrusion detection, and so forth. Whereas it necessitates a central parameter server for model aggregation, which brings about delayed model communication and vulnerability to adversarial attacks. A fully decentralized architecture like Swarm Learning allows peer-to-peer communication among distributed nodes, without the central server. One of the most challenging issues in decentralized deep learning is that data owned by each node are usually non-independent and identically distributed (non-IID), causing time-consuming convergence of model training. To this end, we propose a decentralized learning model called Homogeneous Learning (HL) for tackling non-IID data with a self-attention mechanism. In HL, training performs on each round’s selected node, and the trained model of a node is sent to the next selected node at the end of each round. Notably, for the selection, the self-attention mechanism leverages reinforcement learning to observe a node’s inner state and its surrounding environment’s state, and find out which node should be selected to optimize the training. We evaluate our method with various scenarios for two different image classification tasks. The result suggests that HL can achieve a better performance compared with standalone learning and greatly reduce both the total training rounds by 50.8% and the communication cost by 74.6% for decentralized learning with non-IID data.

Equivalent Sliding Mode Controller for Stability of DC Microgrid

DC microgrids are gaining popularity due to their lack of reactive power compensation, frequency synchronization, and skin effect problems. However, DC microgrids are not exempted from stability issues. The stability of DC microgrids based on decentralized architecture is presented in this paper. Centralized architecture can degrade system performance and reliability due to the failure of a single central controller. Droop with proportional integral (PI) controller based on decentralized architecture is being used for DC microgrid stability. However, droop control requires a tradeoff between voltage regulation and droop gain. Further, global stability through PI controller cannot be verified and controller parameters cannot be optimized with different operating conditions. To address limitations, an equivalent sliding mode (SM) controller is proposed for a DC microgrid system in this paper. Detailed simulations are carried out, and results are presented, which show the effectiveness of an equivalent SM controller.

SBTMS: Scalable Blockchain Trust Management System for VANET

With many advances in sensor technology and the Internet of Things, Vehicle Ad Hoc Network (VANET) is becoming a new generation. VANET’s current technical challenges are deploying decentralized architecture and protecting privacy. Because Blockchain features are decentralized, distributed, mass storage, and non-manipulation features, this paper designs a new decentralized architecture using Blockchain technology called Blockchain-based VANET. Blockchain-based VANET can effectively resolve centralized problems and mutual distrust between VANET units. To achieve this, it is needed to provide scalability on the blockchain to run for VANET. In this system, our focus is on the reliability of incoming messages on the network. Vehicles check the validity of the received messages using the proposed Bayesian formula for trust management system and some information saved in the Blockchain. Then, based on the validation result, the vehicle computes a rate for each message type and message source vehicle. Vehicles upload the computed rates to Roadside Units (RSUs) in order to calculate the net reliability value. Finally, RSUs using a sharding consensus mechanism generate blocks, including the net reliability value as a transaction. In this system, all RSUs collaboratively maintain the latest updated Blockchain. Our experimental results show that the proposed system is effective, scalable and dependable in data gathering, computing, organization, and retrieval of trust values in VANET.

A Blockchain-based Edge Computing Architecture for the Internet of Things

The Internet of Things (IoT) is experiencing widespread adoption across industry sectors ranging from supply chain management to smart cities, buildings, and health monitoring. However, most software architectures for IoT deployment rely on centralized cloud computing infrastructures to provide storage and computing power, as cloud providers have high economic incentives to organize their infrastructure into clusters. Despite these incentives, there has been a recent shift from centralized to decentralized architecture that harnesses the potential of edge devices, reduces network latency, and lowers infrastructure cost to support IoT applications. This shift has resulted in new edge computing architectures, but many still rely on centralized solutions for managing applications. A truly decentralized approach would offer interesting properties required for IoT use cases. To address these concerns, we introduce a decentralized architecture tailored for large scale deployments of peer-to-peer IoT sensor networks and capable of run-time application migration. The solution combines a blockchain consensus algorithm and verifiable random functions to ensure scalability, fault tolerance, transparency, and no single point of failure. We build on our previously presented theoretical simulations with many protocol improvements and an implementation tested in a use case related to monitoring a Slovenian cultural heritage building located in Bled, Slovenia.

Integration of IoT and Blockchain

present, we are in the world of digital revolution. Use of smartphones and internet accelerated due to the impact of the novel Covid-19 virus. The whole world started to turn digital. The industrialization of Internet of Things (IoT) enables more devices to connect and communicate which leads to many data transfer transactions. The architecture of IoT is centralized. The distributed and decentralized architecture of Blockchain can be used to provide secure and scalable transactions of IoT devices. Blockchain is a distributed ledger technology, which provides secure data transactions that cannot be tampered and altered. In this paper, we provide advantages and challenges of integrating IoT and Blockchain. We also provide different architectures and algorithms proposed by researchers to provide secure data transactions. We shall also shed light on the future research directions of integrating Blockchain and IoT.

Blockchain during COVID-19: The Technology to Help Society

At the end of 2019, a new coronavirus was reported in the form of unknown pneumonia: It was the beginning of the SARS-CoV-2 pandemic. It is crucial to develop the strategies to manage this new pandemic in order to improve their effectiveness, as opposed to the ones adopted in 2003 during the SARS pandemic. In 17 years, new digital technologies and tools have been created; therefore, we can take advantage of them in the social management of the pandemic. The aim of our paper is to evaluate how blockchain technology can be used and what advantages it brings in managing an emergency situation such as of the COVID-19 pandemic. In particular, the effects of the adoption of this technology will be assessed when applied both to the management of the information flow between health infrastructures, and to track monetary, technical, and medical supply donations to hospital structures. We therefore propose a high-level, decentralized architecture that assists in administrating large-scale information and stores the gathered data in a blockchain supervised by the authorities. The distrust suffered by institutions today, the fear experienced in the last year due to the pandemic, and the birth of a technology that allows for the creation of reliable networks, pose thoughtful challenges to be faced to recover trust and hope for the future again.

Secure Digital E-Voting System using Blockchain Technology

Technology has great positive impacts on numerous aspects of our social life. Designing a globally connected architecture enables simple access to a range of resources and services. Furthermore, technology rather just like the internet has been a fertile ground for innovation and creativity. The blockchain technology is presented as a game-changer for several existing and emerging technologies. With its immutability property and decentralized architecture, it's taking center stage in many services as an equalization factor to the current parity between consumers and big corporations/governments. one among the fields during which blockchain application is used is E-voting. The target of such a scheme would be to produce a decentralized architecture to run and support a voting scheme that's open, fair, and independently verifiable. this might propose a possible new e-voting protocol that utilizes the blockchain as a transparent box. The protocol helps to attain fundamental e-voting properties additionally as offer a degree of decentralization.