This paper focuses on enhancing the energy savings of EPON-based backhaul for 5G and beyond networks. Here, we introduce a novel technique of the desynchronization of wake-up cycles among Optical Network Units (ONUs) in Low-Power Mode (LPM). In this technique, the Optical Line Terminal (OLT) decides the wake-up slots of all ONUs such that they are spread out and staggered, maximizing the likelihood of fewer ONUs waking up simultaneously. We have shown that this technique can be implemented in addition to any of the existing protocols to improve the energy savings of the protocol. We formulate an optimization problem to achieve wake-up desynchronization while ensuring latency requirements. To address this problem, we present a polynomial-time 1-approximation algorithm. The convergence and complexity of the algorithm are analyzed. Through simulations, we illustrate a significant increase in energy savings and a reduction in the probability of delay violation by implementing our proposed method.

Many network faults are flooding the telecommunication companies in the form of Trouble Tickets (TT). Automation in managing these TTs is vital in increasing customer satisfaction. We develop a solution to address two challenges regarding TTs generated from fixed and mobile access network domains: prediction of resolution times and technician dispatch needs. Our study utilizes datasets from Telenor, a Swedish telecommunication operator, encompassing 35,000 access switches and 8,000 base stations. It incorporates 40,000 switch TTs and 22,000 mobile TTs during 2019-2023. None of the previous works studied multiple telecommunication domains or considered the time evolution of TTs. This work comprehensively studies several prediction models for the mentioned use cases and network domains. Our models successfully outperform the company baseline and best proposed state-of-the-art models. Within 1-hour confidence interval, our method can correctly predict shortest ranges of resolution times for 90% of switch TTs and 80% of mobile TTs. We also predict the necessity of dispatching workforce to the place with weighted F1 scores of respectively, 88% and 89% for switch and mobile TTs which shows high average accuracy of our system in prediction across both dispatch and non-dispatch TT classes to assist operation. With these scores, our model is capable of allocating resources automatically, enhancing customer satisfaction. We also studied the TTs evolution, for example, for switch TTs, within 15 minutes of creation time, prediction improves by 57% and 50%, for resolution and dispatch prediction, respectively.

Extended Reality (XR) is one of the most important 5G/6G media applications that will fundamentally transform human interactions. However, ensuring low latency, high data rate, and reliability to support XR services poses significant challenges. This letter presents a novel AI-assisted service provisioning scheme that leverages predicted frames for processing rather than relying solely on actual frames. This method virtually increases the network delay budget and consequently improves service provisioning, albeit at the expense of minor prediction errors. The proposed scheme is validated by extensive simulations demonstrating a multi-fold increase in supported XR users and also provides crucial network design insights.