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

. x! R% q$ }4 x

Networks

" k7 x: ^$ R2 H2 F/ q  p* ^+ @
- Z- y9 _5 B1 T! M2 j$ }0 q
The fast-growing popularity of electric vehicles
/ U. R- Z" ~  T( I2 h(EVs) poses complex challenges for the existing power grid
) D2 C  K+ i2 }$ a6 ~0 Vinfrastructure to meet the high demands at peak charging hours.
8 i$ y) V: ]3 O8 PDiscovering and transferring energy amongst EVs in mobile
4 `$ M! S2 a0 j. l( Gvehicular edges and fogs is expected to be an effective solution for
bringing energy closer to where the demand is and improving the
5 M* D% a7 O) U* H( f! k9 o9 Fscalability and flexibility compared to traditional charging
solutions. In this paper, we propose a fully-distributed energy
aware opportunistic charging approach which enables distributed
2 }7 C* h7 P5 f. E! z' }3 \multi-layer adaptive edge cloud platform for sustainable mobile
autonomous vehicular edges which host dynamic on-demand
* M" u/ {2 b0 F# R, C' N! {virtual edge containers of on-demand services. We introduce a
novel Reinforcement Learning (Q-learning) based SmartCharge
1 V% K! e! \% ]1 ?algorithm formulated as a finite Markov Decision Process. We
define multiple edge energy states, transitions and possible actions
) C2 [, N, t! p4 W' Nof edge nodes in dynamic complex network environments which
are adaptively resolved by multilayer real-time multidimensional
2 ~$ g& k$ A9 u4 Q9 i. P9 N. jpredictive analytics. This allows SmartCharge edge nodes to more
  x- {) N) t# f0 E4 daccurately 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
- L: }* q9 e8 g( ^nodes are able to autonomously and collaboratively understand
. j- ^0 U* x2 J$ R( N% ^6 q6 e* Dwhen (how soon) and where the geo-temporal peaks are expected
2 V6 N2 V# Q. s, ?. @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
1 u) s& Q: M" o( t: J* F, Qreal-world San Francisco Cab mobility traces and in the presence
8 T6 p) [: @2 d5 R( Y6 W: bof real-world users’ energy interest traces driven by Foursquare
San Francisco dataset. We show that SmartCharge successfully
predicts and mitigates congestion in peak charging hours, reduces
the waiting time between vehicles sending energy demand requests
% N4 G3 Q) ?  Z& iand being successfully charged as well as significantly reduces the
total number of vehicles in need of energy.


/ c9 O8 ^7 w0 t+ O' E3 m1 ^. l3 q
& o; u: U- W/ ~; P# p7 ]
) J! j- y, P/ x$ c