Details

Autor(en) / Beteiligte

• Bandani, Anil Kumar
• Riyazuddien, Shaik
• Bidare Divakarachari, Parameshachari
• Patil, Sujata N.
• Arvind Kumar, G.

Titel

Multiplicative long short-term memory-based software-defined networking for handover management in 5G network

Ist Teil von

• Signal, image and video processing, 2023-09, Vol.17 (6), p.2933-2941

Ort / Verlag

London: Springer London

Erscheinungsjahr

2023

Quelle

SpringerNature Journals

Beschreibungen/Notizen

• In recent years, the 5G network faces more traffic congestion due to the increasing number of mobile operators. In the networking field, learning methods are widely used to reduce the cost and increase flexibility and scalability. Network Function Virtualization is used to set the hardware functions as well as Software-Defined Networking (SDN) helps to concentrate the programming setup. SDN is a key method designed at sustaining high data traffic in next-generation 5G networks. Conversely, the compact deployment of small cells introduces numerous challenges such as frequent handovers, inconsistencies, interfaces, and so on. The software-defined 5G network is one important technique to solve these problems. Moreover, due to the separation of control and data signaling in 5G technology, the operation of handover should be performed. Therefore, Multiplicative Long Short-Term Memory (mLSTM)-based resource estimation strategy is proposed in this study to solve the handover problem. Finally, analyze the observed delays using the densification ratio metric to evaluate the standard and suggested handover procedures for proposed mLSTM which depends on user count. While related to the traditional SDN technique, the proposed mLSTM reduces the handover delay by 4.28 ms.