Unsupervised Neural Predictor to Auto-administrate the Cloud Infrastructure

Due to all the pollutants generated by it and the steady increases in its rates, energy consumption has become a key issue. Cloud computing is an emerging model for distributed utility computing and is being considered as an attractive opportunity for saving energy through central management of computational resources. Obviously, a substantial reduction in energy consumption can be made by powering down servers when they are not in use. This work presents a resources provisioning approach based on an unsupervised predictor model in the form of an unsupervised, recurrent neural network based on a self-organizing map. Unsupervised learning in computers has for long been considered as the desired ambition of computer problems. Unlike conventional prediction-learning methods which assign credit by means of the difference between predicted and actual outcomes, the proposed study assigns credit by means of the difference between temporally successive predictions. We have shown that the proposed approach gives promising results.