The　energy-consumption　of　data　center　in　cloud　computing　is　a　heated　issues.　This　paper　focuses　on　the　challenges　of　operation　and　power　management　in　cloud　platform,　and　presents　a　GMARIMA　model,　which　is　simultaneously　exploiting　autoregressive　integrated　moving　average(ARIMA　model)　and　GM(1,1)　model.　This　combination　is　used　for　CPU　and　Memory　in　the　cloud　computing　experiment　to　model,　test　and　forecast.　The　experiments　revealed　the　GM-ARIMA　model,　in　the　minimum　amount　of　history　record,　is　an　efficient　and　feasible　model　for　the　limited　sampled　forecasting.