A IoT platform developed to monitor the energy consumption at data centers. Temperature, Humidity and Energy consumed in each of the Server Racks is acquired by Sensor Nodes. Sensor Nodes communicate to a Decision Hub wirelessly using the TI CC2500 RF module. The sensed data can be visualized as graphs and also be used to build a model to predict future energy nodes.
The high energy consumption in data centers is becoming a major concern because it leads to increased operating costs and also, pollution, as fuel is burnt to produce the required energy. While many techniques and methods have been proposed by various organizations and researchers to minimize the energy consumption, there has been considerably less work done in making a smart-energy management system that is capable of collecting the data available and make decisions based on the energy consumption patterns. In this work, a smart system is proposed that uses Internet of Things to gather data and a machine learning algorithm for decision making.
The implementation was carried out using Arduino and Beaglebone Black as the hardware kits to build the sensor nodes and data processing/ decision making unit. The communication is facilitated using XBee/CC2500 in SPI mode and is wireless. The Beaglebone Black was configured to run Debian Wheezy with all the codes to acquire, process and store the data was written in Python. The Beaglebone Black is additionally configured to serve the acquired data visualized as charts and logs to the administrator as web pages. The wireless communication is made secure with XXTEA algorithm implemented on both the transmitting sensor nodes and the receiver.The results were studied over a period of two months. From the data acquired, a primitive perceptron based learning rule was implemented to predict future energy consumption based on the data acquired from the sensor nodes.
This project was presented at the First International Workshop on Distributed Energy Networks at the Sixth ACM International Conference on Future Energy Systems (ACM e-Energy), Bangalore, India (2015). The paper can be accessed as PDF from the ACM Digital Library.