An Adaptive Data Placement Architecture in Multicloud Environments

Algorithm 1

Algorithm LSTM: LSTM network with sliding window.

	Input: The required length of the series to be forecast, a trained LSTM model .
	Output: Predicted future DAF;
(1)	= 0;
(2)	Feed the data in the last window into and get a prediction ;
(3)	whiledo
(4)	Slide the window forward by one step and put the newly predicted value at the end of the slide window;
(5)	Feed the data in the new window into and get another prediction
;
(6)	;
(7)	end while