数学建模社区-数学中国

标题: Energy-Aware Opportunistic Charging and Energy Distribution for Sustainable ... [打印本页]
作者: 杨利霞    时间: 2020-11-9 15:10
标题: Energy-Aware Opportunistic Charging and Energy Distribution for Sustainable ...
Energy-Aware Opportunistic Charging and Energy
) n9 Q& m8 t. t% Q% I5 w
Distribution for Sustainable Vehicular Edge and Fog

" U5 Z5 |# d- E6 a) z& i
Networks
3 ?+ ^5 C* D+ g
$ i5 _$ n$ P4 |* x
) b3 ~' i& J3 M, L5 k
The fast-growing popularity of electric vehicles
3 ?4 X) H9 i/ z" G+ t(EVs) poses complex challenges for the existing power grid
, t1 n: o7 B* rinfrastructure to meet the high demands at peak charging hours. 3 q0 a2 }$ h* D$ [( b) q
Discovering and transferring energy amongst EVs in mobile
# E& B2 z- E/ P2 Xvehicular edges and fogs is expected to be an effective solution for
& |3 E: Z/ P# G5 X7 b! E4 fbringing energy closer to where the demand is and improving the
4 Y2 X. M# Z% Zscalability and flexibility compared to traditional charging ; E7 }; N$ j  M+ K; |( }! {) `! b
solutions. In this paper, we propose a fully-distributed energy, z# r. g8 Y8 |+ N" d" s
aware opportunistic charging approach which enables distributed + P* c. z  @3 R! _0 ^7 ~8 x
multi-layer adaptive edge cloud platform for sustainable mobile & L! Q3 h0 P$ Q$ T
autonomous vehicular edges which host dynamic on-demand
, y2 R+ C- `2 w# z6 Dvirtual edge containers of on-demand services. We introduce a " Q$ E  n8 g: {; P# t7 D4 n
novel Reinforcement Learning (Q-learning) based SmartCharge 6 h4 p- |4 |" z  B7 z8 a, U* K
algorithm formulated as a finite Markov Decision Process. We
) S# z7 `& ^; u' U" v* N7 ]define multiple edge energy states, transitions and possible actions ( j9 G2 f: I" H$ t+ y: ?1 k" Y# L
of edge nodes in dynamic complex network environments which
  Z  ]; o, d$ n! A. j3 T6 H2 mare adaptively resolved by multilayer real-time multidimensional
5 h: j' V; D# Ypredictive analytics. This allows SmartCharge edge nodes to more
9 [$ k- m9 H  f# V' {accurately capture, predict and adapt to dynamic spatial-temporal 2 A7 G1 s7 H% Q) l
energy supply and demand as well as mobility patterns when ' ~/ i! d  y2 f
energy peaks are expected. More specifically, SmartCharge edge
, K5 ^7 @) w8 K/ }$ J! Knodes are able to autonomously and collaboratively understand
' d! }( f. `1 L) y5 @5 p0 e$ Cwhen (how soon) and where the geo-temporal peaks are expected
$ m  N& a% a$ T6 t- l: e6 Z6 ?to happen, thus enable better local prediction and more accurate
1 _0 o" L; C# \% f: |global distribution of energy resources. We provide multi-criteria % C8 }3 W7 B  r* S3 @
evaluation of SmartCharge against competitive protocols over
0 ~) C: V' _- `' w) treal-world San Francisco Cab mobility traces and in the presence
/ P9 H+ V: j* a. V0 m% v9 ]7 [of real-world users’ energy interest traces driven by Foursquare 7 F0 n8 {. n; M
San Francisco dataset. We show that SmartCharge successfully ' {( w  j# k& z! {5 _) f
predicts and mitigates congestion in peak charging hours, reduces
4 y* u7 [; u+ |( [# M5 Ithe waiting time between vehicles sending energy demand requests
  A- A- A' O( f# n$ y, x  y, D) ]and being successfully charged as well as significantly reduces the 2 _. H6 W, d# [( R( E, R
total number of vehicles in need of energy.
. U; ?8 ?& R- m
( `: i' k$ x9 \8 {' p1 h5 @( {2 U/ B/ l; p( d
" D" m9 H. p4 [/ j6 v+ i& }

! E/ h, V+ U- ]3 k' M: W; m

Energy-Aware Opportunistic Charging and Energy.pdf

1.17 MB, 下载次数: 0, 下载积分: 体力 -2 点



欢迎光临 数学建模社区-数学中国 (http://www.madio.net/) Powered by Discuz! X2.5