Shared use of unlicensed spectrum in practice for coexistence with WiFi is rather complex and to achieve optimum usage can be highly challenging. While maximal utilization is desirable for unlicensed LTE, it is essentially important not to disturb WiFi activity in the unlicensed channel when designing a coexistence scheme. Opportunistic exploitation of idle gaps, or white spaces, in the WiFi channel for unlicensed LTE transmissions enables achieving the above objectives. However, complex analytical approaches to the opportunistic coexistence problem require considerable computation and might result in excessive latency, which would be undesirable. Machine learning schemes may reduce the computational complexity and hence not only reduce the latency but also help with energy consumption in wireless communications systems.
We propose a novel algorithm based on reinforcement learning technique for the problem of opportunistic coexistence of unlicensed LTE and WiFi. The proposed approach in particular is based on Q-Learning, which provides a robust and model-free decision-making framework that enables online and distributive coexistence of small cells with WiFi. Our approach takes into account the latency imposed on WiFi activity by employing carrier sensing at the base station, and aims to minimize it, while maximizing unlicensed LTE utilization of the idle spectral resources.
The 5G system is about to be developed and the devices in IoT systems are expected to grow exponentially. There are many challenges that come with this development and growth – one of which is how to efficiently use the available bandwidth. With devices needing to continuously exchange information via shared channels, deciding if, when and how much to transmit in efficient ways becomes important, especially when data stream flows continuously. Since transmission causes a drain on battery power, another challenge is how to design sensing and communication protocols that are energy efficient. The key objective here is to integrate cognitive abilities to these devices and device-to-device interactions to enable coordinated decision making that enhances the efficiency of the overall system. By integrating cognition, we mean enabling the sensors to exploit and mine available (and possibly correlated) data. In this presentation, we review some of the capabilities needed in 5G and IoT and show application of machine learning to make significant energy savings.
- N. Rastegardoost and B. Jabbari, "A Machine Learning Algorithm for Unlicensed LTE and WiFi Spectrum Sharing," 2018 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), 2018, pp. 1-6, doi: 10.1109/DySPAN.2018.8610489.
- B. Jabbari, "Keynote talk #1: Machine learning and cognitive communications for 5G and IoT," 2018 International Conference on Advanced Technologies for Communications (ATC), 2018, doi: 10.1109/ATC.2018.8587598.