Cellular traffic prediction on blockchain-based mobile networks using LSTM model in 4G LTE network

【Author】 Kurri, Varun; Raja, Vishweshvaran; Prakasam, P.

【Source】PEER-TO-PEER NETWORKING AND APPLICATIONS

【影响因子】3.488

【Abstract】The various demands from cellular users are increasing day by day. A tower can be selected if the traffic through it at a specific time is predictable. Then a chosen set of issues can also be addressed. In the future, such prediction of traffic will help to identify networks that have better conditions with desired performance. To be specific, in this paper, the Long-Short Term Memory (LSTM) model has been proposed to predict the network traffic at a given 4G LTE cell tower. The LSTM model uses traffic data records of a network for one full year to predict its traffic pattern in a particular week. In addition to this, the 4G LTE access networks are operated via Blockchain. Each LTE tower acts as a separate node like a Peer-to-Peer network. The processes and conditions for accessing mobile networks are coded as smart contracts. Blockchain - Radio Access Network (B-RAN) establishes a secure connection between Access Point (AP) and User Equipment (UE) using smart contracts. If all the conditions of the contract code are satisfied, then data transmission takes place between the user and the AP. The proposed LSTM model on blockchain-enabled network APs to predict LTE data traffic gets validated. It is found that it makes the network encrypted, secure and improves its functioning. The superior performance of the proposed LSTM model justifies that the proposed multilayer LSTM improves the performance from 8.2% to 17.7% as compared to the Autoregressive Integrated Moving Average (ARIMA). The latter is the baseline prediction model.

【Keywords】Deep Learning; Blockchain; Artificial Intelligence; 4G LTE Network; LSTM; Traffic Prediction

【发表时间】2021 MAY

【收录时间】2022-01-02

【文献类型】

【主题类别】

--