Paper Title
Intelligent Traffic Load Prediction Algorithm for the Internet of Things

Abstract
Traffic analysis and use of past information (network traffic data) are important criteria for a smart proactive approach for network management, planning tasks, efficient channel assignment, and resource management in the Internet of Things (IoT). Due to the rapid rise in sensing data and the need for a quick response within the IoT distribution network, high-speed transmission, and resource management have emerged as major issues. Assigning appropriate channels within the wireless IoT distribution network is a fundamental guarantee of high-speed transmission and better research management. The high traffic load dynamics, however, renders the traditional fixed channel assignment algorithms and resource management algorithms ineffective for IoT. In addition, existing network traffic load prediction algorithms used in IoT has a poor prediction accuracy which is not good for real-time traffic. As a result, this paper integrates a machine learning algorithm namely Linear Regression (LR) algorithm and deep learning algorithm namely Artificial Neural Network (ANN) algorithm. The designed Linear Regression Artificial Neural Network (LRANN) algorithm performs traffic load prediction in order to ensure better channel assignment, resource allocation, network management, and task planning which resulted in high-speed transmission of real-time traffic in IoT. Simulation results showed that the proposed LRANN algorithm performs better than the state-of-the-art algorithm used in IoT for high-speed transmission and has a prediction accuracy of 94.5%. Keywords - Internet of Things (IoT), Network Management, Planning Tasks, Efficient Channel Assignment, Resource Management, LRANN algorithm