Supercomputer power consumption prediction using machine learning, nonlinear algorithms, and statistical methods

This work describes various methods of time series prediction. It illustrates the differences between machine learning methods, nonlinear algorithms, and statistical methods in their approach to prediction, and tries to explain in depth the principles of some of the most widely used representatives of these types of prediction methods. All of these methods are then tested on a time series from the real world: the course of power consumption of a supercomputer infrastructure. The reader is gradually acquainted with data analysis, preprocessing, the principle of the methods, and finally with the prediction itself. The main benefit of the work is the final comparison of the results of this testing in terms of the accuracy of the predictions, and the time needed to calculate them.

Towards Optimal Supercomputer Energy Consumption Forecasting Method

Accurate prediction methods are generally very computationally intensive, so they take a long time. Quick prediction methods, on the other hand, are not very accurate. Is it possible to design a prediction method that is both accurate and fast? In this paper, a new prediction method is proposed, based on the so-called random time-delay patterns, named the RTDP method. Using these random time-delay patterns, this method looks for the most important parts of the time series’ previous evolution, and uses them to predict its future development. When comparing the supercomputer infrastructure power consumption prediction with other commonly used prediction methods, this newly proposed RTDP method proved to be the most accurate and the second fastest.

Power Consumption prediction of IoT application Protocols Based on Linear Regression

The advent of the Internet of Things (IoT) augurs new cutting-edge applications in modern life such as smart cities and smart grids. These applications require protocols more efficient for ensuring the reliability of data communications in the IoT networks. Many works state that IoT cannot meet their demands without application protocols improvement with Artificial Intelligence (AI) as IoT are expected to generate unprecedented traffic giving IoT researchers access to data that can help in studying and analyzing the demands and develop application protocols conceptions to meet the requirement of IoT applications. In literature, several works introduced AI in some layers of the TCP/IP model including wireless communication and routing. In this article, an evaluation of application protocols HTTP, MQTT, DDS, XMPP, AMQP, and CoAP has been presented; and subsequently, the power consumption prediction of MQTT and COAP based on the linear regression model is analyzed, in order to enhance data communications in IoT applications.