| 1. |
- Minhaj, Syed Usama, et al.
(författare)
-
How SIC-enabled LoRa Fares under Imperfect Orthogonality?
- 2021
-
Ingår i: IWCMC 2021. - : IEEE. - 9781728186160 ; , s. 729-734
-
Konferensbidrag (refereegranskat)abstract
- With the increase of connected Internet-of-things (IoT) devices, the need for low-power wide-area networks (LP-WANs) is imminent, and LoRaWAN is one such technology that offers an elegant solution to the problem of long-range communication and battery consumption. A parameter of special interest in LoRaWAN is the spreading factor (SF), and it is often assumed that communication between different SFs is independent of each other. However, this claim has been practically debunked by many works, proving that SFs have imperfect orthogonality. To maximize connectivity and throughput, several techniques have been introduced, such as non-orthogonal-multiple-access (NOMA) and dynamic resource allocation. NOMA is getting a lot of attention recently, especially for IoT networks, because it embraces interference and tries to obtain desired information packets from corrupted ones. Furthermore, NOMA can be easily implemented on the base-station side by using the principle of successive interference cancellation (SIC). In this paper, we investigate how SIC, under the assumption of imperfect orthogonality of SF channels, can be used to increase the performance of the system. We find the expressions for success and coverage probability considering various SF allocation schemes and found the most efficient scheme for different scenarios.
|
|
| 2. |
- Minhaj, Syed Usama, et al.
(författare)
-
Intelligent Resource Allocation in LoRaWAN Using Machine Learning Techniques
- 2023
-
Ingår i: IEEE Access. - 2169-3536. ; 11, s. 10092-10106
-
Tidskriftsartikel (refereegranskat)abstract
- With the ubiquitous growth of Internet-of-things (IoT) devices, current low-power wide-area network (LPWAN) technologies will inevitably face performance degradation due to congestion and interference. The rule-based approaches to assign and adapt the device parameters are insufficient in dynamic massive IoT scenarios. For example, the adaptive data rate (ADR) algorithm in LoRaWAN has been proven inefficient and outdated for large-scale IoT networks. Meanwhile, new solutions involving machine learning (ML) and reinforcement learning (RL) techniques are shown to be very effective in solving resource allocation in dense IoT networks. In this article, we propose a new concept of using two independent learning approaches for allocating spreading factor (SF) and transmission power to the devices using a combination of a decentralized and centralized approach. SF is allocated to the devices using RL for contextual bandit problem, while transmission power is assigned centrally by treating it as a supervised ML problem. We compare our approach with existing state-of-the-art algorithms, showing a significant improvement in both network level goodput and energy consumption, especially for large and highly congested networks.
|
|
