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

7 a0 q8 m- _) ~6 H  R

Networks

0 n& a! d7 {" H# X. g3 w
+ Q, T( V& R( c% |% [The fast-growing popularity of electric vehicles
, W& X5 ?  T7 Q. M# z: z$ @(EVs) poses complex challenges for the existing power grid
infrastructure to meet the high demands at peak charging hours.
5 u9 }% y7 E: u' F- SDiscovering and transferring energy amongst EVs in mobile
: ~+ W/ v  ~: p$ q" h& f) svehicular edges and fogs is expected to be an effective solution for
bringing energy closer to where the demand is and improving the
( N7 S, `% m6 s4 C% _scalability and flexibility compared to traditional charging
- H7 H- s& Z2 g6 esolutions. In this paper, we propose a fully-distributed energy
aware opportunistic charging approach which enables distributed
8 F% [5 N3 @0 C7 z# Hmulti-layer adaptive edge cloud platform for sustainable mobile
autonomous vehicular edges which host dynamic on-demand
virtual 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
, `' V1 A7 ~" s3 y5 ~" `# R' Xdefine multiple edge energy states, transitions and possible actions
0 L7 a- e7 b! u- Vof 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
4 M1 _, ^0 X! s- Z1 j4 C8 eaccurately capture, predict and adapt to dynamic spatial-temporal
energy supply and demand as well as mobility patterns when
( t1 ^  K' E" d) L9 F/ q- P7 denergy peaks are expected. More specifically, SmartCharge edge
7 n  T# D+ ^( u( Y& p; D& xnodes are able to autonomously and collaboratively understand
when (how soon) and where the geo-temporal peaks are expected
& y7 {! y  ]8 S3 q, L  Bto happen, thus enable better local prediction and more accurate
  O# r3 G2 z9 \  c3 T1 ^( a0 Jglobal distribution of energy resources. We provide multi-criteria
evaluation of SmartCharge against competitive protocols over
- z: Z) F: m. g5 g9 treal-world San Francisco Cab mobility traces and in the presence
of real-world users’ energy interest traces driven by Foursquare
' I, _- a* w( i7 Z; c( ^San Francisco dataset. We show that SmartCharge successfully
9 X/ {8 W1 Z3 F  M. upredicts and mitigates congestion in peak charging hours, reduces
+ w# n0 l6 W) g4 F* C5 qthe waiting time between vehicles sending energy demand requests
6 J1 n6 x( ~8 G, ]0 f/ \( Pand being successfully charged as well as significantly reduces the
total number of vehicles in need of energy.
  r* k% Q6 s) ?3 u" h/ J1 H. l

: F2 q* G& {6 \9 ?; A# o  h
6 Y6 g/ [- C) ?7 P3 U! x: F
) Z6 @# G9 O) y7 }% k