19 July 2021 in IEEE Transactions on Network and Service Management
One of the main challenges when it comes to deploying Network Slices is slicing the Radio Access Network (RAN). Indeed, managing RAN resources and sharing them among network slices is an increasingly difficult task, which needs to be properly designed. The goal is to improve network performance and introduce flexibility and greater utilization of network resources by accurately and dynamically provisioning the activated network slices with the appropriate amounts of resources to meet their diverse requirements. In this paper, we propose a data-driven RAN slicing mechanism based on a resource sharing algorithm running at the Slice Orchestrator (SO) level. This algorithm computes the necessary radio resources to be used by each deployed network slice. These resources are adjusted periodically based on current estimates of achievable throughput performance derived from channel quality information, and in particular from the Channel Quality Indicator (CQI) values of the users of each network slice retrieved from the RAN. CQI information is reported to base stations by the User Equipment (UE) following standard procedures, but extracting and frequently reporting it from base stations to the SO may result in significant communication overhead. To mitigate this overhead while maintaining at the SO level an accurate view of UE channel qualities, we propose a machine learning approach to infer the stability of UE channel conditions, as well as predictive schemes to reduce the CQI reporting intensity based on the inferred channel status. Through extensive simulations, we demonstrate the efficiency of our data-driven RAN slicing framework, which allows to meet the stringent requirements of two main classes of network slices in 5G, i.e., enhanced Mobile Broadband (eMBB) and Ultra-Reliable and Low-Latency Communication (URLLC).
21 February 2021 in International Journal of Communication Systems
30 December 2024 in IEEE Sensors Journal
Detection and classification of anomalies in industrial applications has long been a focus of interest in the research community. The integration of computational and physical systems has increased the complexity of interactions between processes, leading to vulnerabilities in both the physical and cyber layers. This work presents a model structure for anomaly detection in Internet of Things (IoT)-enabled industrial Cyber-Physical Systems (CPSs), enabled by Wireless Sensor Networks (WSNs). The model comprises three primary data blocks in the cyber layer: sensor-based data acquisition, data fusion to convert raw data into useful information, and analytics for decision-making. The rationale behind these blocks highlights the critical role of anomaly detection and is demonstrated through three use cases, namely fault selection in power grids, anomaly detection in an industrial chemical process, and prediction of the CO 2 level in a room. Furthermore, we integrate Explainable AI (XAI) algorithms into an IoT-based system to enhance error detection and correction, while fostering user engagement by offering useful insights into the decision-making process. Our numerical results demonstrate high accuracy in anomaly detection across these scenarios, significantly improving system reliability and enabling timely interventions, which could ultimately reduce operational risks.