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

杨利霞

Energy-Aware Opportunistic Charging and Energy

# F. p* J2 m1 S. k: l

Distribution for Sustainable Vehicular Edge and Fog

Networks

9 ~! l. T/ h3 m4 s7 J8 d4 M9 H
The fast-growing popularity of electric vehicles
& f1 _, q" n. @$ d* l* A# A(EVs) poses complex challenges for the existing power grid
infrastructure to meet the high demands at peak charging hours.
% E2 u  j! m! Y* ]. x& ?& kDiscovering and transferring energy amongst EVs in mobile
! I  _9 D7 {( O: l; H  P& bvehicular edges and fogs is expected to be an effective solution for
' V% G+ ~, l6 fbringing 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
aware opportunistic charging approach which enables distributed
$ x; D  i1 @! Y. n$ @- o+ }+ omulti-layer adaptive edge cloud platform for sustainable mobile
4 o+ H; g8 |: a: R0 y5 }7 ?autonomous vehicular edges which host dynamic on-demand
7 n5 T- t  K: v+ r  R& y9 fvirtual edge containers of on-demand services. We introduce a
1 v' f* p4 Y" l! |$ W9 r, [novel Reinforcement Learning (Q-learning) based SmartCharge
! a0 O- Y$ [. M# B& |algorithm formulated as a finite Markov Decision Process. We
define multiple edge energy states, transitions and possible actions
0 B# n  `7 A) P& y( z4 a* Q$ @of edge nodes in dynamic complex network environments which
4 m+ V: O6 p9 Z% A- W! ~are adaptively resolved by multilayer real-time multidimensional
! h/ F! \2 N/ [. }- apredictive analytics. This allows SmartCharge edge nodes to more
7 Q$ i$ M& d4 k- Eaccurately capture, predict and adapt to dynamic spatial-temporal
$ B5 v0 T- {. W7 t$ [energy supply and demand as well as mobility patterns when
0 I& p  _% H% E) ?4 M2 z/ Benergy peaks are expected. More specifically, SmartCharge edge
3 E+ [+ A" }* S* G8 U/ ?! h* snodes are able to autonomously and collaboratively understand
when (how soon) and where the geo-temporal peaks are expected
- d( N+ @, W0 P+ V9 V! uto happen, thus enable better local prediction and more accurate
7 P) a7 D+ B+ ?. m3 z: Q  D' T2 a/ x$ Iglobal distribution of energy resources. We provide multi-criteria
4 ?1 k6 h3 |$ a5 ^' b5 V6 x9 Z' o* Eevaluation of SmartCharge against competitive protocols over
real-world San Francisco Cab mobility traces and in the presence
of real-world users’ energy interest traces driven by Foursquare
" A- S- A# H! r7 u9 G+ {San Francisco dataset. We show that SmartCharge successfully
. a1 B8 k; R# Apredicts and mitigates congestion in peak charging hours, reduces
the waiting time between vehicles sending energy demand requests
5 L  u. C" X: Zand being successfully charged as well as significantly reduces the
total number of vehicles in need of energy.

. t. j" P7 r: k. I, T

' V6 y% s' g) I- Z# {
3 e8 q$ u8 r  _0 W