Abstract
An IoT is the communication of sensing devices linked to the Internet in order to communicate data. IoT devices have extremely critical reliability with an efficient and robust network condition. Based on enormous growth in devices and their connectivity, IoT contributes to the bulk of Internet traffic. Prediction of network traffic is very important function of any network. Traffic prediction is important to ensure good system efficiency and ensure service quality of IoT applications, as it relies primarily on congestion management, admission control, allocation of bandwidth to the system, and the identification of anomalies. In this paper, a complete overview of IoT traffic forecasting model using classic time series and artificial neural network is presented. For prediction of IoT traffic, real network traces are used. Prediction models are evaluated using MAE, RMSE, and R -squared values. The experimental results indicate that LSTM- and FNN-based predictive models are highly sensitive and can therefore be used to provide better performance as a timing sequence forecast model than the conventional traffic prediction techniques.
Highlights
The Internet of Things (IoT) are communicating devices with sensing capability that are connected to the Internet which enables collecting and sharing of data without human intervention
The vector autoregression moving average (VARMA) is a mixture between vector autoregressive (VAR) and VMA and a generalized Auto-Regressive Integrated Moving Average (ARIMA) model for stationary multivariate time sets. It is defined by parameters “x” and “y.” It is similar to ARIMA, which is able to behave as an AR model by setting “y” as 0 and “x” as 0 as an MA model
Prediction of IoT traffic in the recent years has attracted an insightful attention for enhancing resource and bandwidth utilization
Summary
The Internet of Things (IoT) are communicating devices with sensing capability that are connected to the Internet which enables collecting and sharing of data without human intervention. The need for optimized bandwidth management and new network monetization models has been brought about This is why the growth of mobile IoT brings individuals, systems, data, and items together to improve the relevance and value of network connections and to increase network traffic contribution [6]. Congestion management, induction control, network assignment of bandwidth, and detecting malicious applications are based on accurate predictions of traffic at end points This allows for effective distribution of resources to ensure consistent service quality. (i) The related techniques for traffic prediction are explored and implemented for comparative study of the existing methods with the proposed LSTM method and feedforward neural networks (FNN) prediction method (ii) To use the network bandwidth optimally, to reduce the over consumption of the IoT channels, FNN and LSTM are proposed which are more efficient than the existing ARIMA- and VARMA-based techniques (iii) The problem of insufficient data of IoT devices and unavailability of historical data, a time series-based learning model has been introduced in this paper.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
