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

杨利霞

Energy-Aware Opportunistic Charging and Energy

4 y( A( u9 h. W4 N$ v; w8 V, s

Distribution for Sustainable Vehicular Edge and Fog

; M  N4 u+ e9 U* i5 b5 e! T

Networks

  Z3 k4 e% G( W7 X
9 s+ M+ O1 `5 U( c4 ~
The fast-growing popularity of electric vehicles
(EVs) poses complex challenges for the existing power grid
2 e7 {) w0 Q1 ?3 ~) |% p  m+ {infrastructure to meet the high demands at peak charging hours.
- i1 v+ @) I# p  Q* P3 [. R- CDiscovering and transferring energy amongst EVs in mobile
vehicular edges and fogs is expected to be an effective solution for
bringing energy closer to where the demand is and improving the
2 J( c/ E: ^9 Z  kscalability and flexibility compared to traditional charging
  V; x1 v0 s  _3 b6 Msolutions. In this paper, we propose a fully-distributed energy
: o2 ]; n! G; Y3 K  vaware opportunistic charging approach which enables distributed
5 V6 p% Y. _8 c. v) h% {multi-layer adaptive edge cloud platform for sustainable mobile
5 Z& ?+ s1 c8 s9 R: H6 `autonomous vehicular edges which host dynamic on-demand
! D" m" x  @+ R7 e: S' |9 ovirtual edge containers of on-demand services. We introduce a
! y6 g+ h1 b: c3 A, B) Lnovel Reinforcement Learning (Q-learning) based SmartCharge
algorithm 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
; u2 d$ O; B% T! N5 Apredictive analytics. This allows SmartCharge edge nodes to more
. Q7 }) g5 L8 }7 ~5 R; w4 |! maccurately capture, predict and adapt to dynamic spatial-temporal
0 S  Y3 X) z& ^+ B/ {5 h) `0 o$ oenergy supply and demand as well as mobility patterns when
' P7 p; q4 v7 R! a4 U4 g9 |! }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
to happen, thus enable better local prediction and more accurate
global distribution of energy resources. We provide multi-criteria
4 Z8 Q' ~# O% c* D5 `4 V- s! jevaluation of SmartCharge against competitive protocols over
+ e" X/ v2 y( l+ \real-world San Francisco Cab mobility traces and in the presence
of real-world users’ energy interest traces driven by Foursquare
* J% S; C% t: A6 m, JSan Francisco dataset. We show that SmartCharge successfully
  K" I' ~: @4 o4 _" R2 m5 epredicts 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
6 e: Y, f/ W) ]total number of vehicles in need of energy.


, z5 v: [3 E: \- |