In smart electric grid systems, various sensors and Internet of Things (IoT) devices are used to collect electrical data at substations. In a traditional system, a multitude of energy-related data from substations needs to be migrated to central storage, such as Cloud or edge devices, for knowledge extraction that might impose severe data misuse, data manipulation, or privacy leakage. This motivates to propose anomaly detection system to detect threats and Federated Learning to resolve the issues of data silos and privacy of data. In this article, we present a framework to identify anomalies in industrial data that are gathered from the remote terminal devices deployed at the substations in the smart electric grid system. The anomaly detection system is based on Long Short-Term Memory (LSTM) and autoencoders that employs Mean Standard Deviation (MSD) and Median Absolute Deviation (MAD) approaches for detecting anomalies. We deploy Federated Learning (FL) to preserve the privacy of the data generated by the substations. FL enables energy providers to train shared AI models cooperatively without disclosing the data to the server. In order to further enhance the security and privacy properties of the proposed framework, we implemented homomorphic encryption based on the Paillier algorithm for preserving data privacy. The proposed security model performs better with MSD approach using HE-128 bit key providing 97% F1-score and 98% accuracy for K=5 with low computation overhead as compared with HE-256 bit key. 

Artificial intelligence (AI) is a key enabler for future 6G networks. Currently, related architecture works propose AI-based applications and network services that are dedicated to specific tasks (e.g., improving the performance of RAN with AI). These proposed architectures offer a unique way to collect data, process it, and extract features from data for each AI-based application. However, this dedicated approach creates AI-silos that hinder the integration of AI in the networks. In other words, such AI-silos create a set of AI-models and data for AI-based applications that only work within a single dedicated task. This single-task approach limits the end-to-end integration of AI in the networks. In this work, we propose a network architecture to deploy AI-based applications, at different network domains, that prevents AI-silos by offering reusable data and models to ensure scalable deployments. We describe the architecture, provide workflows for the end-to-end management of AI-based applications, and show the viability of the architecture through multiple use cases.

Increasing complexity and data-generation rates in cyber-physical systems and the industrial Internet of things are calling for a corresponding increase in AI capabilities at the resource-constrained edges of the Internet. Meanwhile, the resource requirements of digital computing and deep learning are growing exponentially, in an unsustainable manner. One possible way to bridge this gap is the adoption of resource-efficient brain-inspired “neuromorphic” processing and sensing devices, which use event-driven, asynchronous, dynamic neurosynaptic elements with colocated memory for distributed processing and machine learning. However, since neuromorphic systems are fundamentally different from conventional von Neumann computers and clock-driven sensor systems, several challenges are posed to large-scale adoption and integration of neuromorphic devices into the existing distributed digital–computational infrastructure. Here, we describe the current landscape of neuromorphic computing, focusing on characteristics that pose integration challenges. Based on this analysis, we propose a microservice-based conceptual framework for neuromorphic systems integration, consisting of a neuromorphic-system proxy, which would provide virtualization and communication capabilities required in distributed systems of systems, in combination with a declarative programming approach offering engineering-process abstraction. We also present concepts that could serve as a basis for the realization of this framework, and identify directions for further research required to enable large-scale system integration of neuromorphic devices.

Traffic safety applications and other communication systems for vehicles together with data collection sensors have the potential to improve road safety. For this to be viable however, it is important that the data collection and communication can be trusted so that erroneous or malicious data does not impact the use cases of the applications. This paper studies current and upcoming solutions to such problems and how they can be modified and applied to meet both technical requirements as well as the needs of relevant stakeholders. The paper defines the TruVeLedger framework using technology from the fields of distributed ledgers and vehicular ad hoc networks (VANETs) to create a trusted platform. The paper considers the viability of different approaches to such a platform as well as defining a verifiable trusted communication protocol for vehicular networks. 

Privata 5G nätverk – antingen som en del av ett publikt eller som ett helt eget mobilnät erbjuder möjliga lösningar på ett antal av de utmaningar som finns kring WiFi och trådlösa uppkopplingar i logistik och produktion. Tekniken börjar bli väletablerad och antalet leverantörer ökar snabbt samtidigt som priser för infrastrukturen sjunker i pris. Förutom att femte generationens mobilnät löser problem kring mobilitet och uppkoppling så finns ett antal intressanta funktioner såsom positionering och standardiserad edge computing för lokala digitala tjänster. Dessa funktioner bör dock ses som en del av en framtida uppgradering snarare än något som finns tillgängligt idag (dock inte så långt bort in i framtiden). Alla de besökta sågverken hade liknande utmaningar kring trådlös uppkoppling och i vissa fall har även 4G-baserade lösningar börjat användas – med gott resultat.

Tyvärr fick vi inte konkreta priser från de operatörer och leverantörer som dialog fördes med men via vissa leverantörer kan man ändå få en viss indikation (se t ex AWS erbjudande där det för ett privat nät med två radioaccespunkter ligger på ca 140 KSEK / månad totalt).

To ensure traffic safety and proper operation of vehicular networks, safety messages or beacons are periodically broadcasted in Vehicular Adhoc Networks (VANETs) to neighboring nodes and road side units (RSU). Thus, authenticity and integrity of received messages along with the trust in source nodes is crucial and highly required in applications where a failure can result in life-threatening situations. Several digital signature based approaches have been described in literature to achieve the authenticity of these messages. In these schemes, scenarios having high level of vehicle density are handled by RSU where aggregated signature verification is done. However, most of these schemes are centralized and PKI based where our goal is to develop a decentralized dynamic system. Along with authenticity and integrity, trust management plays an important role in VANETs which enables ways for secure and verified communication. A number of trust management models have been proposed but it is still an ongoing matter of interest, similarly authentication which is a vital security service to have during communication is not mostly present in the literature work related to trust management systems. This paper proposes a secure and publicly verifiable communication scheme for VANET which achieves source authentication, message authentication, non repudiation, integrity and public verifiability. All of these are achieved through digital signatures, Hash Message Authentication Code (HMAC) technique and logging mechanism which is aided by blockchain technology.

Information-centric networking (ICN) technology matches many major requirements of vehicular ad hoc networks (VANETs) in terms of its connectionless networking paradigm accordant with the dynamic environments of VANETs and is increasingly being applied to VANETs. However, wireless transmissions of packets in VANETs using ICN mechanisms can lead to broadcast storms and channel contention, severely affecting the performance of data dissemination. At the same time, frequent changes of topology due to driving at high speeds and environmental obstacles can also lead to link interruptions when too few vehicles are involved in data forwarding. Hence, balancing the number of forwarding vehicular nodes and the number of copies of packets that are forwarded is essential for improving the performance of data dissemination in information-centric networking for vehicular ad-hoc networks. In this paper, we propose a context-aware packet-forwarding mechanism for ICN-based VANETs. The relative geographical position of vehicles, the density and relative distribution of vehicles, and the priority of content are considered during the packet forwarding. Simulation results show that the proposed mechanism can improve the performance of data dissemination in ICN-based VANET in terms of a successful data delivery ratio, packet loss rate, bandwidth usage, data response time, and traversed hops.

The Internet has traditionally been a device-orientedarchitecture where devices with IP addresses are first-classcitizens, able to serve and consume content or services, and theirowners take part in the interaction only through those devices.The Internet of People (IoP) is a recent paradigm where devicesbecome proxies of their users, and can act on their behalf. Torealize IoP, new policies and rules for how devices can take actionsare required. The role of context information grows as devicesact autonomously based on the environment and existing socialrelationships between their owners. In addition, the social profilesof device owners determine e.g. how altruistic or resourceconservingthey are in collaborative computing scenarios. In thispaper we focus on community formation in IoP, a prerequisitefor enabling collaborative scenarios, and discuss main challengesand propose potential solutions.

The cross-site linking function is widely adopted by online social networks (OSNs). This function allows a user to link her account on one OSN to her accounts on other OSNs. Thus, users are able to sign in with the linked accounts, share contents among these accounts and import friends from them. It leads to the service integration of different OSNs. This integration not only provides convenience for users to manage accounts of different OSNs, but also introduces usefulness to OSNs that adopt the cross-site linking function. In this paper, we investigate this usefulness based on users' data collected from a popular OSN called Medium. We conduct a thorough analysis on its social graph, and find that the service integration brought by the crosssite linking function is able to change Medium's social graph structure and attract a large number of new users. However, almost none of the new users would become high PageRank users (PageRank is used to measure a user's influence in an OSN). To solve this problem, we build a machine-learning-based model to predict high PageRank users in Medium based on their Twitter data only. This model achieves a high F1-score of 0.942 and a high area under the curve (AUC) of 0.986. Based on it, we design a system to assist new OSNs to identify and attract high PageRank users from other well-established OSNs through the cross-site linking function.