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

+ I2 I$ A2 [  \  e2 h

Networks

, y' G) E# p9 _* A" L

1 k, J( c, Y" C; f+ J0 e, pThe fast-growing popularity of electric vehicles
(EVs) poses complex challenges for the existing power grid
% G. t/ c" ?7 ?0 M7 `$ S. Q0 Winfrastructure to meet the high demands at peak charging hours.
5 m3 V7 [  v( ]+ q; P* D! V7 S; KDiscovering and transferring energy amongst EVs in mobile
) O9 C, `$ _6 n1 hvehicular edges and fogs is expected to be an effective solution for
bringing energy closer to where the demand is and improving the
' v. [2 j+ z- T( Y9 ascalability and flexibility compared to traditional charging
solutions. In this paper, we propose a fully-distributed energy
aware opportunistic charging approach which enables distributed
multi-layer adaptive edge cloud platform for sustainable mobile
autonomous vehicular edges which host dynamic on-demand
8 c/ C& n1 {, B' E* ^8 dvirtual edge containers of on-demand services. We introduce a
novel Reinforcement Learning (Q-learning) based SmartCharge
1 X  d" H! ~* @1 g! malgorithm formulated as a finite Markov Decision Process. We
+ o/ Y. u; q2 B7 R0 _define multiple edge energy states, transitions and possible actions
9 x4 w1 W. f! P5 o* b. x, P9 F1 T8 Vof edge nodes in dynamic complex network environments which
are adaptively resolved by multilayer real-time multidimensional
  b" \/ _( ^3 x' Qpredictive analytics. This allows SmartCharge edge nodes to more
) v: `% ^' U, g5 j+ x* ^4 R5 iaccurately capture, predict and adapt to dynamic spatial-temporal
7 S' \& m* |# q3 q& e/ t9 kenergy 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
: N1 B( ^* `8 m( A3 v( Rwhen (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
6 C8 {6 S* n5 s1 w; 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
San Francisco dataset. We show that SmartCharge successfully
$ e, w6 d6 Z; B7 [0 T6 Epredicts and mitigates congestion in peak charging hours, reduces
- J6 X) ^5 `1 D! Athe 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.
9 B  W: o  c) g) U3 v

0 T# U& G* U9 W5 E  r

" I; V9 S8 S; L