TY  - JOUR
T1  - Spiking Neural Network-Based Backoff Scheme for Slotted-ALOHA Systems
AU  - Kang, Min Jeong 
AU  - Lee, Jung Hoon 
AU  - Jeong, Dong Geun 
JO  - The Journal of Korean Institute of Communications and Information Sciences
PY  - 2024
DA  - 2024/1/1
DO  - 10.7840/kics.2024.49.2.199
KW  - Backoff scheme
KW  - machine learning
KW  - slotted-ALOHA
KW  - spiking neural network
AB  - In this letter, we propose a spiking neural network (SNN)-based backoff scheme to enhance the performance of slotted-ALOHA systems, which operates with relatively low power and implementation complexity. In our scheme, an SNN model takes real-time input of observation data, such as transmission success and failure, from the system operating with binary exponential backoff (BEB), and returns the optimal contention window size. Through simulations, we show that our proposed scheme achieves higher performance compared to the traditional BEB, approaching the performance of the optimal backoff scheme numerically optimized.