In recent years, the electrical consumption of data centers has increased considerably leading to a rise in the expenditure bill and in greenhouse gas emissions. Several existing on/off algorithms reduce energy consumption in data centers or Clouds by turning off unused (idle) machines. However, the turning off/on of servers consumes a certain amount of energy and also induces the wear and tear of disks. Based on the data streaming paradigm which deals with large amount of data on-line, we present in this paper MERCi-MIsS, a proposal whose aim is to save energy in data centers and Clouds and tackle the above tradeoff problems without degrading, as much as possible, the quality of services of the system. MERCi-MIsS dynamically estimates the future workload based on the recent past workload, deciding if servers should then be turned either on or off. We have implemented MERCi-MIsS on top of Twitter Storm. Evaluation results from experiments using real traces from Grid’5000 confirm the effectiveness and efficiency of MERCi-MIsS algorithm to save energy and avoid disk damage while the quality of service is only slightly degraded.