Power management using AI-based IOT systems

Abstract

The Internet of Things (IoT) concept is expected to evolve the interest of each industry, medicine, and others. The main forces behind the huge data gathering were the IoT devices built into the sensor. One of the biggest challenges has been the maintenance of those huge data sets. A massive IoT (mIoT) refers to the continuous collection of huge quantities of data with sensors. Therefore, self-adaptive algorithms based on AI are required to aggregate, evaluate and effectively understand all program objects. It is imperative to control the energy carefully due to the increase in large datasets and power-hungry IoT gadgets. It is critical to combine mIoT using AI-based approaches to fairly distribute power levels to small portable devices. The connection between the lifetime of the mIoT and the information flow found that as information rates increase, more energy is lost, reducing the service life of mIoT networks. With more sensor nodes, the power would be appropriately distributed across the transverse layers. By analyzing key characteristics and data sets, this research suggests a new Improved Random Energy Optimization Algorithm (IIRBEOA) for mIoT systems to address these issues. According to an experimental survey, the proposed IRBEOA exceeds its Baseline rival in terms of practical control and implementation of energy.

Keywords

• mIoT
• Power management
• Energy optimization
• Artificial intelligence