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

Networks

The fast-growing popularity of electric vehicles
(EVs) poses complex challenges for the existing power grid
4 ]  C: i. o& }. z. o3 _; S4 rinfrastructure to meet the high demands at peak charging hours.
; w; {, P! m) c' B# T( LDiscovering and transferring energy amongst EVs in mobile
: t: {7 M( ^% e5 ^8 d' i  qvehicular edges and fogs is expected to be an effective solution for
4 Y- y" z' k: B) k- q: _bringing energy closer to where the demand is and improving the
2 n# t, k# K4 n% v% Kscalability and flexibility compared to traditional charging
solutions. In this paper, we propose a fully-distributed energy
. P$ `7 n3 z& K0 ?4 g6 a6 X# eaware opportunistic charging approach which enables distributed
. G1 Q( T7 P: Xmulti-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
* m6 L  D5 x  r* ^define multiple edge energy states, transitions and possible actions
* E) C1 `- X. {of edge nodes in dynamic complex network environments which
* {9 G; l  @# P6 d2 Eare adaptively resolved by multilayer real-time multidimensional
predictive analytics. This allows SmartCharge edge nodes to more
accurately capture, predict and adapt to dynamic spatial-temporal
. t/ |; u* h2 ]; l8 a& g  ienergy supply and demand as well as mobility patterns when
5 \) ?% }: N8 j+ l+ C; y4 G5 Yenergy peaks are expected. More specifically, SmartCharge edge
. k' v/ b- ^  A3 c, Y. C9 pnodes 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
' M" y! q( F2 G- s' X) }global distribution of energy resources. We provide multi-criteria
* s5 N' j% P: 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
3 U. x. H' o' i# ^! ]7 ZSan 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
and being successfully charged as well as significantly reduces the
( o9 Z8 y, J( b& f9 S' B% J4 Q- Mtotal number of vehicles in need of energy.
1 P# c; T  V, g$ k) o


7 q5 o8 F- n. t% y
2 _* G' \8 p; G2 D9 k& V% c/ k' w