Abstract
The fifth-generation (5G) network is presented as one of the main options for Industry 4.0 connectivity. To comply with critical messages, 5G offers the Ultra-Reliable and Low latency Communications (URLLC) service category with a millisecond end-to-end delay and reduced probability of failure. There are several approaches to achieve these requirements; however, these come at a cost in terms of redundancy, particularly the solutions based on multi-connectivity, such as Packet Duplication (PD). Specifically, this paper proposes a Machine Learning (ML) method to predict whether PD is required at a specific data transmission to successfully send a URLLC message. This paper is focused on reducing the resource usage with respect to pure static PD. The concept was evaluated on a 5G simulator, comparing between single connection, static PD and PD with the proposed prediction model. The evaluation results show that the prediction model reduced the number of packets sent with PD by 81% while maintaining the same level of latency as a static PD technique, which derives from a more efficient usage of the network resources.
Highlights
Wired communications have been widely used in industrial scenarios as new applications of automation and Artificial Intelligence (AI) with high mobility are rolled out.wired communications are costly in terms of installation and maintenance and cannot cover new use cases, such as mobility in factories
The first part of the test consists in obtaining a collection of Key Performance Indicators (KPIs) in order to train the Machine Learning (ML) part
Once the ML model has been trained, the second part of the test consists in evaluating the accuracy of the predictor, that is, the accuracy of predicting the latency by Master Node (MN)
Summary
Wired communications have been widely used in industrial scenarios as new applications of automation and Artificial Intelligence (AI) with high mobility are rolled out. The studies above cover Urban Macro (UMa) and Urban Micro (UMi) scenarios, but not the industrial scenario These techniques have shown their effectiveness in reducing latency and packet loss, they come at an additional cost, which derives from a less efficient usage of the network resources. Key Performance Indicator (S-KPI) [17] by observing the network conditions right before a critical transmission in the downlink and, based on that prediction, activate the PD technique (dynamic algorithm) [12,18] in industrial scenarios. E2E latency performance with single connection and a static PD (that is, always duplicating the packet regardless of network conditions) techniques and the resource consumption when using a static vs a dynamic PD approach (based on the proposed latency predictor).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
