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

杨利霞

Energy-Aware Opportunistic Charging and Energy

; _$ Y$ J+ Q) ~

Distribution for Sustainable Vehicular Edge and Fog

Networks

) p; V$ F- [3 h+ R, m
8 I- t2 A2 i" J; X5 U# |( [) h4 |& k( u9 pThe fast-growing popularity of electric vehicles
1 u. ^4 x% K$ U+ P; O0 Y(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
2 z0 P4 b, u4 G. t+ rbringing energy closer to where the demand is and improving the
6 n3 ]1 s) i, V: P: p  tscalability and flexibility compared to traditional charging
solutions. In this paper, we propose a fully-distributed energy
. o% ^) q$ [$ Xaware opportunistic charging approach which enables distributed
  U3 N: ?' r9 Y  x3 f( Fmulti-layer adaptive edge cloud platform for sustainable mobile
autonomous vehicular edges which host dynamic on-demand
1 e) Z+ s( x9 B- \: xvirtual edge containers of on-demand services. We introduce a
6 _1 K1 r% S7 Q6 \6 L4 znovel Reinforcement Learning (Q-learning) based SmartCharge
3 {* I$ a  i0 W- calgorithm formulated as a finite Markov Decision Process. We
% U* }8 H. z' B& d  wdefine 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
/ C, K2 h! U' T0 @: U7 c  {predictive analytics. This allows SmartCharge edge nodes to more
, C" ]9 M* o5 k9 g1 d7 Baccurately 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
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
evaluation of SmartCharge against competitive protocols over
4 ~6 G, f# \& U( A9 ureal-world San Francisco Cab mobility traces and in the presence
/ T# L# o- g' ?; `of real-world users’ energy interest traces driven by Foursquare
1 }5 F0 Z  N' a5 ^0 H( T( _  U' ~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
8 T2 ~+ [1 m- V% M7 E6 n0 |and being successfully charged as well as significantly reduces the
total number of vehicles in need of energy.


0 y# P* r/ S3 j
. a' P( d+ O+ y+ V, W+ b, p