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

杨利霞

Energy-Aware Opportunistic Charging and Energy

% V3 B% \, o& r$ `: M

Distribution for Sustainable Vehicular Edge and Fog

Networks

* q+ k0 p/ W5 {+ S' g
* A* {5 B, q2 n7 h0 E  ^
+ s/ m% D4 U7 t# a) Z% YThe fast-growing popularity of electric vehicles
(EVs) poses complex challenges for the existing power grid
infrastructure to meet the high demands at peak charging hours.
Discovering and transferring energy amongst EVs in mobile
vehicular edges and fogs is expected to be an effective solution for
8 J; t4 }9 `  t- cbringing energy closer to where the demand is and improving the
scalability and flexibility compared to traditional charging
) b: d7 A. n( X  a' Y' asolutions. In this paper, we propose a fully-distributed energy
# o0 O; X# A7 zaware opportunistic charging approach which enables distributed
% k+ i" d6 }1 pmulti-layer adaptive edge cloud platform for sustainable mobile
autonomous vehicular edges which host dynamic on-demand
8 K$ _8 G* x2 h  {9 Svirtual edge containers of on-demand services. We introduce a
novel Reinforcement Learning (Q-learning) based SmartCharge
algorithm formulated as a finite Markov Decision Process. We
# v. l5 W- Y2 `/ r& Kdefine multiple edge energy states, transitions and possible actions
of edge nodes in dynamic complex network environments which
; j* V, T. Q6 `; x; tare adaptively resolved by multilayer real-time multidimensional
$ B; t+ s# Z! T' I+ apredictive analytics. This allows SmartCharge edge nodes to more
$ q* \9 W) Q, G, \accurately capture, predict and adapt to dynamic spatial-temporal
; ]( }$ r! d$ `energy supply and demand as well as mobility patterns when
+ z; Z5 }# o" ?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
& |2 _& f6 ?4 A; x& U3 {# d! \to happen, thus enable better local prediction and more accurate
global distribution of energy resources. We provide multi-criteria
  M0 M+ t9 r: K' ~, ?2 tevaluation of SmartCharge against competitive protocols over
real-world San Francisco Cab mobility traces and in the presence
- K3 P. d" q! S# ?of real-world users’ energy interest traces driven by Foursquare
4 [  p7 g8 O5 s# z+ n! \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
and being successfully charged as well as significantly reduces the
total number of vehicles in need of energy.

, e1 {! W, k* ]+ `! m' B% ^
" s# ~- C5 `* X5 Q0 x
. M" k, j/ m6 X7 f1 i( ]# w
& i, A8 j1 a3 j( X2 L/ d