Energy-Aware Opportunistic Charging and Energy Distribution for Sustainable ...

杨利霞

Energy-Aware Opportunistic Charging and Energy

Distribution for Sustainable Vehicular Edge and Fog

: [8 M# ~5 T0 O9 V- F2 t

Networks

6 k7 p2 y) x( F5 [The fast-growing popularity of electric vehicles
(EVs) poses complex challenges for the existing power grid
) T4 w1 M% O9 S/ h- }infrastructure to meet the high demands at peak charging hours.
) D- [( w' s# z2 a# {% RDiscovering and transferring energy amongst EVs in mobile
& x& q( i" d# f7 B& G. rvehicular edges and fogs is expected to be an effective solution for
bringing energy closer to where the demand is and improving the
. ~& r) Y6 H, t' k' Q9 uscalability and flexibility compared to traditional charging
solutions. In this paper, we propose a fully-distributed energy
aware opportunistic charging approach which enables distributed
  `) a( D$ q* wmulti-layer adaptive edge cloud platform for sustainable mobile
( _9 B7 O+ ^. Mautonomous vehicular edges which host dynamic on-demand
/ B& X& @. m+ C* W( A' v, X- Ivirtual edge containers of on-demand services. We introduce a
! u& n) i' \2 R, ?4 unovel Reinforcement Learning (Q-learning) based SmartCharge
algorithm formulated as a finite Markov Decision Process. We
define multiple edge energy states, transitions and possible actions
9 @) S. X: e( a( K# h/ d* {6 b0 Fof edge nodes in dynamic complex network environments which
are adaptively resolved by multilayer real-time multidimensional
/ S/ N) R" I+ i1 Kpredictive analytics. This allows SmartCharge edge nodes to more
accurately capture, predict and adapt to dynamic spatial-temporal
energy supply and demand as well as mobility patterns when
energy peaks are expected. More specifically, SmartCharge edge
nodes are able to autonomously and collaboratively understand
when (how soon) and where the geo-temporal peaks are expected
& J& C7 l0 }* l8 L7 y; }to happen, thus enable better local prediction and more accurate
global distribution of energy resources. We provide multi-criteria
evaluation of SmartCharge against competitive protocols over
real-world San Francisco Cab mobility traces and in the presence
' J0 {8 o( M& aof real-world users’ energy interest traces driven by Foursquare
( @6 V  ]" f0 I5 e- PSan Francisco dataset. We show that SmartCharge successfully
$ ^' A3 }; t: @* |  vpredicts and mitigates congestion in peak charging hours, reduces
/ e! o* o) O6 w! b, r% U$ wthe waiting time between vehicles sending energy demand requests
and being successfully charged as well as significantly reduces the
; V2 u% d0 W7 _' c. {total number of vehicles in need of energy.
, T1 a, H  c$ R( ?3 f

8 U: t7 Q' b, |$ l9 O  \' w

4 {+ v( o7 q- [3 `% L