Green Applications Awareness: NonLinear Energy Consumption Model for Green Evaluation

Green IT´ practices seek to enhance the sustainability of the information technology infrastructures and devices (platforms) to reach the good environmental, social and economic expectations. This enhancement could be achieved by eliminating or reducing the negative impact of IT on the environment through detecting the negative defects and exploiting the efficient green practices and guidelines to implement an eco-friendly green solution. However, it is primordial to detect these defects and collect the necessary knowledge about the negative impact on the environment. Especially, the impact related to the energy consumption in such platforms via measurement tools and metrics. In this paper, we propose a solution to measure the energy consumption of the mobile applications running on battery by establishing a nonlinear energy consumption model of the platform using the machine learning support vector machine (SVM) algorithm with the Gaussian Kernel. Our model will be further deployed to estimate the energy consumption at the application level based on the application´s usage of resources such as the processor, the memory and the communication network interfaces.