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

Networks

The fast-growing popularity of electric vehicles
" {! c) d' K# X# n1 G(EVs) poses complex challenges for the existing power grid
, S! Y; L: q! d4 \0 z) H0 Hinfrastructure to meet the high demands at peak charging hours.
3 ~8 g' {" m- z" aDiscovering and transferring energy amongst EVs in mobile
: H& ~" W3 [5 r7 ]3 G4 cvehicular edges and fogs is expected to be an effective solution for
bringing energy closer to where the demand is and improving the
scalability and flexibility compared to traditional charging
solutions. In this paper, we propose a fully-distributed energy
5 X9 h! X  S; M% Z' j# L6 @6 G4 paware opportunistic charging approach which enables distributed
! W" b0 C5 i( N/ emulti-layer adaptive edge cloud platform for sustainable mobile
autonomous vehicular edges which host dynamic on-demand
( p( V1 B8 L5 h, t% J/ mvirtual edge containers of on-demand services. We introduce a
  w# z3 B8 ~" ~novel Reinforcement Learning (Q-learning) based SmartCharge
0 |% z% l) u5 n( Z! b) O8 ^3 malgorithm formulated as a finite Markov Decision Process. We
define multiple edge energy states, transitions and possible actions
of edge nodes in dynamic complex network environments which
are adaptively resolved by multilayer real-time multidimensional
predictive analytics. This allows SmartCharge edge nodes to more
accurately capture, predict and adapt to dynamic spatial-temporal
/ ~! g% B& G" ienergy supply and demand as well as mobility patterns when
energy peaks are expected. More specifically, SmartCharge edge
3 m, m8 Q" I: s" Vnodes are able to autonomously and collaboratively understand
when (how soon) and where the geo-temporal peaks are expected
to happen, thus enable better local prediction and more accurate
global distribution of energy resources. We provide multi-criteria
, F( x2 v5 g  Z9 u  Y. a  zevaluation of SmartCharge against competitive protocols over
real-world San Francisco Cab mobility traces and in the presence
2 Q4 g3 R: p( `8 C* }' uof real-world users’ energy interest traces driven by Foursquare
San Francisco dataset. We show that SmartCharge successfully
8 K0 x. v" Y0 \% t$ Q1 M9 ~predicts and mitigates congestion in peak charging hours, reduces
1 R1 T3 F! r: _3 Lthe 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.


( f: Q% a: B. Y" S8 _' w
8 v7 @& J/ P$ x1 C- c: u
2 o7 F6 o# R/ K( g7 l