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

3 r/ |, a1 [) T0 D' ]" k

The fast-growing popularity of electric vehicles
(EVs) poses complex challenges for the existing power grid
2 R" j$ a# }) d4 [& minfrastructure to meet the high demands at peak charging hours.
$ h5 W, v# T5 Z; i% r) yDiscovering and transferring energy amongst EVs in mobile
/ _5 u2 n) i6 _vehicular edges and fogs is expected to be an effective solution for
bringing 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
: @9 W0 M; \, s/ H. H) lmulti-layer adaptive edge cloud platform for sustainable mobile
* k1 W7 r$ _! F' d* ]5 @5 K7 @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
3 n  A2 |0 j8 B# F# _- T8 T! @algorithm formulated as a finite Markov Decision Process. We
/ }; G' F7 n- vdefine multiple edge energy states, transitions and possible actions
1 S- r, H  s$ D  k: M# iof edge nodes in dynamic complex network environments which
5 R* d+ W9 [5 m3 P( H/ V0 t& }are adaptively resolved by multilayer real-time multidimensional
* A1 `& j: s7 B& D9 Jpredictive analytics. This allows SmartCharge edge nodes to more
accurately capture, predict and adapt to dynamic spatial-temporal
energy supply and demand as well as mobility patterns when
+ I, L" j  r: i' B" yenergy 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
/ ^/ H" u$ F7 O; Y0 Jto happen, thus enable better local prediction and more accurate
global distribution of energy resources. We provide multi-criteria
5 g8 A% S7 \8 b8 r& Yevaluation of SmartCharge against competitive protocols over
real-world San Francisco Cab mobility traces and in the presence
( A3 c- Q$ R0 j6 @  H, uof real-world users’ energy interest traces driven by Foursquare
7 I; t3 T2 R. }2 O) Y9 u9 XSan 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
total number of vehicles in need of energy.

7 I$ m& W" I8 a/ J4 s3 m5 o


# {1 G4 ~0 |& Z1 l/ d