Deep Tailored Dynamic Registration in B5G/6G with Lightweight Recurrent Model

Registration areas (RAs) play a pivotal role in the localization of UEs in B5G/6G mobile networks for instant service delivery, as they define a region where the network is certain of UE presence in active and idle modes. A UE must update its registration with the network when it changes its RA, hence, it is desirable to increase RA sizes to minimize registration updates but this elevates the paging overhead and vice versa. Conventionally, RAs are manually defined at the network initiation and they largely remain static afterward. This preliminary study proposes a tailored dynamic registration approach, where a dynamic RA is tailored for a UE according to its movement pattern and rate. This is achieved through a Lightweight Recurrent deep learning Model (LRM) that approximates the region of UE presence for the next defined period. The proposed input sequence aggregation and output sequence compression mechanisms in LRM significantly reduce the computational footprint. The preliminary evaluation with open-source dataset confirms that tailored dynamic registration achieves tradeoff between paging and registration and reduces their signaling overheads by an average 54% and 65%, respectively, compared to conventional static RAs. Further, an average 51% reduction in learning time by LRM showcases its robustness and practical viability.