A Deep Learning-based approach to VM behavior identification in - PowerPoint PPT Presentation

A Deep Learning-based approach to VM behavior identification in cloud systems Matteo Stefanini, Riccardo Lancellotti, Lorenzo Baraldi, Simone Calderara University of Modena and Reggio Emilia Department of engineering “Enzo Ferrari” CLOSER 2019, May., 2-4, Heraklion, Greece 1

C l o u d C o mp u t i n g C h a l l e n g e s ● C r i t i c a l o p e r a t i o n s i n C l o u d d a t a c e n t e r s – M o n i t o r i n g ( o v e r l o a d e d / u n d e r u t i l i z e d V M s a n d H o s t s ) – M a n a g e m e n t ( h u g e b i n p a c k i n g p r o b l e m ) ● M a i n c h a l l e n g e : S c a l a b i l i t y – V o l u m e o f d a t a f o r m o n i t o r i n g – S i z e ( a n d d i m e n s i o n a l i t y ) o f o p t i m i z a t i o n p r o b l e m ● C u r r e n t s o l u t i o n – O v e r s i m p l i fj c a t i o n o f t h e p r o b l e m CLOSER 2019, May., 2-4, Heraklion, Greece 2

I d e n t i fj c a t i o n o f V M s ● A l t e r n a t i v e a p p r o a c h : – E x p l o i t s i m i l a r i t y i n V M s : ( c l a s s e s , n o t i n s t a n c e s ) – R e d u c e d p r o b l e m s i z e ( l e s s d a t a , l e s s V M s ) CL1 CL2 VM VM VM VM VM VM VM VM VM VM VM VM VM VM VM VM ● P r o b l e m : h o w t o c l a s s i f y V M s ? – F a s t a n d a c c u r a t e c l a s s i fj c a t i o n CLOSER 2019, May., 2-4, Heraklion, Greece 3

S t a t e o f t h e a r t ● T r a d e - o fg a c c u r a c y / s p e e d – F a s t c l a s s i fj c a t i o n i s n o t a c c u r a t e – A c c u r a t e c l a s s i fj c a t i o n t a k e s t i m e – C a n n o t b e a p p l i e d t o o n - d e m a n d V M s i n p u b l i c C l o u d ● A d a p t i v e G r a y A r e a T E c h n i q u e ( A G A T E ) – A d d a c o n fj d e n c e v a l u e t o c l a s s i fj c a t i o n – F a s t a n d a c c u r a t e c l a s s i fj c a t i o n o f V M s s o m e – S t i l l u n s a t i s f a c t o r y → P r o p o s a l o f a d i fg e r e n t a p p r o a c h CLOSER 2019, May., 2-4, Heraklion, Greece 4

D e e p L e a r n i n g mo d e l ● I n p u t : t i m e s e r i e s o f W s a m p l e s o f s e v e r a l V M s m e t r i c s ● O u t p u t : c l a s s b e l o n g i n g p r o b a b i l i t i e s ● M u l t i p l e l a y e r s ( n u m b e r d e p e n d i n g o n t h e i n p u t s i z e ) ● T w o m o d e l s : – D e e p C o n v : b a s e d o n c o n v o l u t i v e n e t w o r k s F o c u s o n p a t t e r n s b e t w e e n s a m p l e s – D e e p F F T : b a s e d o n F a s t F o u r i e r T r a n s f o r m a t i o n F o c u s o n s p e c t r a l d o m a i n ( n o v e l D e e p L e a r n i n g a p p r o a c h ) CLOSER 2019, May., 2-4, Heraklion, Greece 5

D e e p L e a r n i n g mo d e l ● G e n e r a l s t r u c t u r e : – I n p u t l a y e r ( p r e - p r o c e s s i n g o f s a m p l e s ) – P r o c e s s i n g b l o c k s ( m u l t i p l e l a y e r s ) – F u l l y c o n n e c t e d l a y e r ( a n d s o f t m a x c l a s s i fj e r ) ● D e e p C o n v : – S t a n d a r d m o d e l ● D e e p F F T : – P e r f o r m s F F T i n i n p u t l a y e r CLOSER 2019, May., 2-4, Heraklion, Greece 6

M o d e l r e p r e s e n t a t i o n Class Frequency Time OR Softmax probabilities Block 4 Block 3 Block 2 Block 1 Fully Connected layer Input metrics (data flattened) (channels) CLOSER 2019, May., 2-4, Heraklion, Greece 7

P r o c e s s i n g b l o c k ● E a c h p r o c e s s i n g b l o c k c o n t a i n s – A c t i v a t i o n f u n c t i o n ( R e L U ) – B a t c h N o r m a l i z a t i o n – 1 - D i m e n s i o n a l c o n v o l u t i o n ● E a c h b l o c k : – R e d u c e s b y 2 t h e i n p u t s i z e ( s t r i d e = 2 ) – D o u b l e s t h e n u m b e r o f c h a n n e l s ● N u m b e r o f b l o c k s : CLOSER 2019, May., 2-4, Heraklion, Greece 8

I mp l e me n t a t i o n d e t a i l s ● I m p l e m e n t a t i o n b a s e d o n P y t o r c h – I n - h o u s e i m p l e m e n t a t i o n o f F F T ● S o u r c e c o d e a v a i l a b l e – C o d e i n g i t r e p o s i t o r y – S e e p a p e r f o r d e t a i l s ● D e p l o y m e n t o n C I N E C A d a t a c e n t e r CLOSER 2019, May., 2-4, Heraklion, Greece 9

E x p e r i me n t a l s e t u p ● D a t a f r o m a r e a l d a t a c e n t e r ( e - h e a l t h a p p ) ● T w o c l a s s e s o f V M s : – We b s e r v e r s – D B M S ● T r a c e s d i v i d e d i n c h u n k s w i t h d i fg e r e n t w i n d o w – 1 s a m p l e e v e r y 5 m i n – 4 s a m p l e s ( 2 0 m i n s ) → 2 5 6 s a m p l e s ( 2 1 h r s ) CLOSER 2019, May., 2-4, Heraklion, Greece 10

E x p e r i me n t a l s e t u p ● 1 6 m e t r i c s ( v i r t u a l i z e d H W / g u e s t O S ) CLOSER 2019, May., 2-4, Heraklion, Greece 11

D e e p L e a r n i n g p e r f o r ma n c e CLOSER 2019, May., 2-4, Heraklion, Greece 12

C o mp a r i s o n w i t h A G A T E CLOSER 2019, May., 2-4, Heraklion, Greece 13

C o n c l u d i n g r e ma r k s ● C h a l l e n g e : s c a l a b i l i t y o f m o n i t o r i n g / m a n a g e m e n t i n C l o u d d a t a c e n t e r s → V M s i d e n t i fj c a t i o n ● C o m p l e x t o a c h i e v e f a s t a n d a c c u r a t e i d e n t i fj c a t i o n ● P r o p o s a l o f a D e e p L e a r n i n g - b a s e d a p p r o a c h ● O u t p e r f o r m s s t a t e o f t h e a r t ( A G A T E ) ● S u i t a b l e a l s o f o r o n - d e m a n d V M s CLOSER 2019, May., 2-4, Heraklion, Greece 14

F u t u r e r e s e a r c h d i r e c t i o n s ● T h o r o u g h e v a l u a t i o n i n c a s e s w i t h l i m i t e d / l o w - q u a l i t y d a t a ● I d e n t i fj c a t i o n o f n e w c l a s s e s : – A u t o - e n c o d e r s / t r i g g e r s i n N N – I n t e g r a t i o n w i t h A G A T E ● G e n e r a t i v e A d v e r s a r i a l N e t w o r k f o r w o r k l o a d g e n e r a t i o n CLOSER 2019, May., 2-4, Heraklion, Greece 15

A Deep Learning-based approach to VM behavior identification in cloud systems Matteo Stefanini, Riccardo Lancellotti, Lorenzo Baraldi, Simone Calderara University of Modena and Reggio Emilia Department of engineering “Enzo Ferrari” CLOSER 2019, May., 2-4, Heraklion, Greece 16