Due to constant technological advancements, Smart Grids have the potential to significantly reduce energy consumption, while providing efficient energy management. However, their implementation requires a thorough col...
Due to constant technological advancements, Smart Grids have the potential to significantly reduce energy consumption, while providing efficient energy management. However, their implementation requires a thorough collection of data related to procedures of energy generation and distribution, as well as the inclusion of Circular Economy (CE) principles to ensure sustainability. Considering the impact of Industry 5.0, Digital Product Passports (DPPs) are a sufficient solution for the recording, presentation, and circularity of the respective data, combined with suitable crowdsourcing strategies for the integration of real-time data provided by consumers. This paper explores the potential implementation of DPPs, infused with crowdsourcing principles, for smart grid integration, through the design of a fundamental CE framework, which is further supported by a systematic literature review and a reference use- case scenario of its operational flow.
Crowd sensing is a way to obtain multiple sensing data onto users or mobile devices and is widely used in industrial Internet, smart city, smart medical, etc. However, when users upload sensing data involving sensitiv...
详细信息
The 5G information age requires a large number of marginal nodes distributed around users to provide digital services. By caching and processing data at edge nodes close to users, edge caching technology can effective...
详细信息
ISBN:
(纸本)9798350350227;9798350350210
The 5G information age requires a large number of marginal nodes distributed around users to provide digital services. By caching and processing data at edge nodes close to users, edge caching technology can effectively collaborate with cloud computing and edge computing to improve the transmission efficiency as well as network response time. Meanwhile, intelligent reflective surface (IRS) is a promising technology for achieving high reductions in hardware cost and power consumption as compared to traditional relaying systems. It provides reliable and scalable backhaul transmission for base stations and access points in ultra-dense networks, which is in line with the requirements of 5G green technology. Therefore, in this paper, we propose a collaborative edge caching method that effectively combines IRS-aided wireless communication and channel power-delay-profile to design joint caching decisions in a centralized manner through limited cache capacity, improving the quality of content delivery in information transmission. Then we proposed a deep deterministic policy gradient learning method based on the framework of deep reinforcement learning along with self-supervision learning to predict IRS phases and collaborative caching strategies. The numerical simulation results show that the proposed algorithm has better convergence speed and learning accuracy than that of the existing algorithms, and is expected to be applied for future massive and dynamical content delivery applications.
The widespread diffusion of Internet of Things (IoT) devices has led to an exponential growth in the volume of data generated at the edge of the network. With the rapid spread of machine learning (ML)-based applicatio...
The widespread diffusion of Internet of Things (IoT) devices has led to an exponential growth in the volume of data generated at the edge of the network. With the rapid spread of machine learning (ML)-based applications, performing compute and resource-intensive learning tasks at the edge has become a critical issue, resulting in the need for scalable and efficient solutions that can overcome the resource constraints of edge devices. This paper analyzes the problem of scaling ML applications and algorithms at the edge-cloud continuum from a distributedcomputing perspective. In particular, we first highlight the limitations of traditional distributed architectures (e.g., clusters, clouds, and HPC systems) when running ML applications that use data generated at the edge. Next, we discuss how to enable traditional ML algorithms combining the benefits of edge computing, such as low-latency processing and privacy preservation of personal user data, with those of cloud computing, such as virtually unlimited computational and storage capabilities. Our analysis provides insights into how properly separated parts of a ML application can be deployed across edge-cloud architectures in order to optimize its execution. More-over, examples of ML applications and algorithms appropriately adapted for the edge-cloud continuum are shown.
With the increasing demand for urban passenger transportation, the concept urban air mobility (UAM) has gained a lot of research interest. One idea is to employ fully autonomous air crafts. That is, using unmanned and...
With the increasing demand for urban passenger transportation, the concept urban air mobility (UAM) has gained a lot of research interest. One idea is to employ fully autonomous air crafts. That is, using unmanned and not remotely piloted aerial vehicles as a means of mass transit. Clearly, fully autonomous air taxis constitute a safety critical, time sensitive application. Efficient information management is a prominent requirement and the infrastructure for sensing and fast, reliable communication is the key to mitigate any harm in the aforesaid approach. Nevertheless, failures in such a system are inevitable and need to be addressed. This work investigates the significant aspect of building a fault-tolerant UAM communication network. We introduce a concept of distributed ground station architecture and a protocol for role delegation to improve system availability. This assures an uninterrupted service continuation fulfilling the high standards of safety requirements in an UAM system.
An analysis of drone detection methods was carried out in this paper. There is a reasoned choice of the optimal method for implementation based on the analysis of acoustic signals generated by drones. The set of metho...
详细信息
distributed training crossing multiple computing nodes and accelerators has been the mainstream solution for large model training. Precedent work on distributed deep learning (DDL) training acceleration has focused on...
详细信息
The security of Internet of Things (IoT) networks has become a major concern in recent years, as the number of connected objects continues to grow, thereby opening up more potential for malicious attacks. Supervised M...
详细信息
ISBN:
(数字)9798350369441
ISBN:
(纸本)9798350369458
The security of Internet of Things (IoT) networks has become a major concern in recent years, as the number of connected objects continues to grow, thereby opening up more potential for malicious attacks. Supervised Machine Learning (ML) algorithms, which require a labeled dataset for training, are increasingly employed to detect attacks in IoT networks. However, existing datasets focus only on specific types of attacks, resulting in ML-based solutions that struggle to generalize effectively. In this work, we address this limitation by introducing a new dataset that comprehensively covers most known attacks on IoT networks. We present GRASEC-IoT, a graph-based dataset specifically tailored for IoT networks, which provides structural information on attack patterns. This enables the utilization of Graph Neural Networks (GNNs), which have shown remarkable effectiveness across various domains. The dataset, its environment and scripts of attacks are publicly available [1].
Wireless sensor Networks of energy efficiency play an important role in determining the life of the network. Wireless sensor Network (WSN) is known for its less energy consumption property and is known as a highly res...
详细信息
暂无评论