26 October 2022 in IEEE Access
Radio access network (RAN) technologies continue to evolve, with Open RAN gaining the most recent momentum. In the O-RAN specifications, the RAN intelligent controllers (RICs) are software-defined orchestration and automation functions for the intelligent management of RAN. This article introduces principles for machine learning (ML), in particular, reinforcement learning (RL) applications in the O-RAN stack. Furthermore, we review the state-of-the-art research in wireless networks and cast it onto the RAN framework and the hierarchy of the O-RAN architecture. We provide a taxonomy for the challenges faced by ML/RL models throughout the development life-cycle: from the system specification to production deployment (data acquisition, model design, testing and management, etc.). To address the challenges, we integrate a set of existing MLOps principles with unique characteristics when RL agents are considered. This paper discusses a systematic model development, testing and validation life-cycle, termed: RLOps. We discuss fundamental parts of RLOps, which include: model specification, development, production environment serving, operations monitoring and safety/security. Based on these principles, we propose the best practices for RLOps to achieve an automated and reproducible model development process. At last, a holistic data analytics platform rooted in the O-RAN deployment is designed and implemented, aiming to embrace and fulfil the aforementioned principles and best practices of RLOps.
5 February 2018 in IEEE Transactions on Communications
We consider a lossy multicast network in which the reliability is provided by means of Random Linear Network Coding. Our goal is to characterise the performance of such network in terms of the probability that a source message is delivered to all destination nodes. Previous studies considered coding over large finite fields, small numbers of destination nodes or specific, often impractical, channel conditions. In contrast, we focus on a general problem, considering arbitrary field size and number of destination nodes, as well as a realistic channel. We propose a lower bound on the probability of successful delivery, which is more accurate than the approximation commonly used in the literature. In addition, we present a novel performance analysis of the systematic version of RLNC. The accuracy of the proposed performance framework is verified via extensive Monte Carlo simulations, where the impact of the network and code parameters are investigated. Specifically, we show that the mean square error of the bound for a ten-user network can be as low as 9 · 10−5 for non-systematic RLNC.
1 December 2017 in IEEE Transactions on Industrial Informatics
Networks deployed in real-world conditions have to cope with dynamic, unpredictable environmental temperature changes. These changes affect the clock rate on network nodes, and can cause faster clock de-synchronization compared to situations where devices are operating under stable temperature conditions. Wireless network protocols such as Time-Slotted Channel Hopping (TSCH) from the IEEE 802.15.4-2015 standard are affected by this problem, since they require tight clock synchronization among all nodes for the network to remain operational. This paper proposes a method for autonomously compensating temperature-dependent clock rate changes. After a calibration stage, nodes continuously perform temperature measurements to compensate for clock drifts at run-time. The method is implemented on low-power IoT nodes and evaluated through experiments in a temperature chamber, indoor and outdoor environments, as well as with numerical simulations. The results show that applying the method reduces the maximum synchronization error more than 10 times. In this way, the method allows reduce the total energy spent for time synchronization, which is practically relevant concern for low data rate, low energy budget TSCH networks, especially those exposed to environments with changing temperature.
3 February 2023 in Scientific Reports
A new method for multimodal sensor fusion is introduced. The technique relies on a two-stage process. In the first stage, a multimodal generative model is constructed from unlabelled training data. In the second stage, the generative model serves as a reconstruction prior and the search manifold for the sensor fusion tasks. The method also handles cases where observations are accessed only via subsampling i.e. compressed sensing. We demonstrate the effectiveness and excellent performance on a range of multimodal fusion experiments such as multisensory classification, denoising, and recovery from subsampled observations.