Dynamic routing versus static routing

1
Dynamic routing versus static routing

• Prof. drs. Dr. Leon Rothkrantz
• http//www.mmi.tudelft.nl
• http//www.kbs.twi.tudelft.nl

2
Outline presentation

• Problem definition
• Static routing Dijkstra shortest path algorithm
• Dynamic traffic data (historical data, real time
  data)
• Dynamic routing using 3D-Dijkstra algorithm
• Travel speed prediction using ANN
• Personal intelligent traveling assistant (PITA)
• PITA in cars and in trains

3
Introduction

• Problem definition
• Find the shortest/fastest route from A to B using
  dynamic route information.
• Research if dynamic routing results in shorter
  traveling time compared to shortest path
• Is it possible to route a traveler on his route
  in dynamically changing environments ?

4
(Non-) congested road
5
Traffic
6
Testbed graph of highways
7
MONICA networkMany sensors/wires along the road
to measure the speed of the cars
8
Smart Road

• Many sensors (smart sensors) along a road
• Sensor devices set up a wireless ad-hoc network
• Sensor in the car is able to communicate with the
  road
• Congestion, icy roads can be detected by the
  sensors and communicated along the network, to
  inform drivers remote in place and time
• GPS, GSM can be included in the sensornetworks
• Wireless communication by wired
  lamppost/streetlights

9
(No Transcript)
10
Real speed on a road segment during peak hour
11
3 dimensional graphUse 3D Dijkstra
12
Why not search in this 3 dim. graph ?

• This will become a giant graph
• - constructing such a 3 dimensional graph
  (estimating travel times) would take too much
  time
• - performance of shortest path algorithm for
  such a graph will be very poor

13
Shortest path via dynamic routing
14
Expert systemBased on knowledege/experience of
daily cardriver

• Translate routes to trajectories between
  junctions and assign labels entrance, route, file
  and exit to each trajectory

• (entrance kleinpolderplein ypenburg)
• (route ypenburg prins_claus)
• (file prins_claus badhoevedorp)
• (route badhoevedorp nieuwe_meer)
• (exit nieuwe_meer coenplein)

15
Design (1)
16
Schematic overview of a PR route.
17
Design (2)
18
Static car and public transport routes
19
Dynamic car route
20
PR route
21
Expert system

• Translate routes to trajectories between
  junctions and assign labels entrance, route, file
  and exit to each trajectory

• (entrance kleinpolderplein ypenburg)
• (route ypenburg prins_claus)
• (file prins_claus badhoevedorp)
• (route badhoevedorp nieuwe_meer)
• (exit nieuwe_meer coenplein)

22
Example alternative routesusing expert knowledge
23
Implementation in CLIPS
24
Results of dynamic routing

• Based on historical traffic speed data dynamic
  routing is able to save approximately 15 of
  travel time
• During special incidents (accidents, road work,)
  savings in travel time increases
• During peak hours savings decreases

25
User preferences

• Shortest travel time
• Preference routing via highways, secondary roads
  minimized
• Preferred routing (not) via toll routes
• Fastest route or shortest route
• Route with minimal of traffic jams

26
Traffic

• Current systems developed at TUDelft
• Prediction of travel time using ANN (trained on
  historical data)
• Model of speed as function of time average over
  road segments/trajectories
• Static routing using Dijkstra algorithm
• Dynamic routing using 3D Dijkstra
• Dynamic routing using Ant Based Control algorithm
• Personal Traveling Assistant online end of 2008

27
NN Classifiers

• Feed-Forward BP Network
• single-frame input
• two hidden layers
• logistic output function in hidden and output
  layers
• full connections between layers
• single output neuron

28
NN Classifiers
(continued)

• Time Delayed Neural Network
• multiple frames input
• coupled weights in first hidden layer for
  time-dependency learning
• logistic outputfunction in hidden and output
  layers

29
NN Classifiers
(continued)

• Jordan RecursiveNeural Network
• single frame input
• one hidden layer
• logistic output functionin hidden and output
  layer
• context neuron for time-dependency learning

30
Factors which have impact on the speed

• Factors
• Time
• Day of the week
• Month
• Weather
• Special events

31
Impact on speed

• Time

32
Impact on speed

• Day of the week

33
Impact on speed

• Day of the week

34
Impact on speed

• Month

35
Impact on speed

• Month

36
Impact on speed

• Weather

37
Impact on speed

• Special events

38
Model 1

• Is it possible to predict average speed on a
  special location and time?

39
Model 1
40
Model 2

• Is it possible to predict average time 25
  minutes ahead on a special location with an error
  of less then 10 ?

41
Model 2
42
Model 3
43
Test results Model 1

• 6 networks tested
• Tuesday
• A12 in the direction of Gouda
• Best results with 5 neurons in hidden layer

44
Test results Model 1
45
Test results Model 2

• 9 networks tested
• Tuesday
• A12 in the direction of Gouda
• Best results with 9 neurons in the hidden layer

46
Test results Model 2
47
Test results
48
Test results

• Results of the best performing network
• 76 of the values with difference of 10 or less
• Average error is more than 20
• Deleting outliers average error less than 9

49
Conclusions

• Existing research
• Formula of Fletcher and Goss
• Impact
• Results

50
Current system

• Model (based on historical data)
• Accidents and work on the road
• Travel time (based on Recurrent neural networks)
• Data collection (average speed per segment, per
  road)

51
(No Transcript)
52
Ant Based Control Algorithm (ABC)

• Is inspired from the behavior of the real ants
• Was designed for routing the data in packet
  switch networks
• Can be applied to any routing problem which
  assumes dynamic data like
• Routing in mobile Ad-Hoc networks
• Dynamic routing of traffic in a city
• Evacuation from a dangerous area ( the routing
  is done to multiple destinations )

53
Natural ants find the shortest route
54
Choosing randomly
55
Laying pheromone
56
Biased choosing
57
3 reasons for choosing the shortest path

• Earlier pheromone (trail completed earlier)
• More pheromone (higher ant density)
• Younger pheromone (less diffusion)

58
Application of ant behaviour in network management

• Mobile agents
• Probability tables
• Different pheromone for every destination

59
Traffic model in one node
i j k
1 pi1 pj1 pk1
2 pi2 pj2 pk2
.. ..
N piN pjN PkN
1 2 .... N
µ1s1 W1 µ2 s2 W2 µN sN WN
60
Routing table

• To forward the packets, each node has a routing
  table

Neighbours
6 8 10
1 0.4 0.5 0.1
2 0.7 0.2 0.1

11 0.4 0.1 0.5
7
All possible destinations
61
Generating virtual ants (agents)

• ants are launched on regular intervals
• - it goes from source to a randomly chosen
  destination

62
Chosing the next node

• 2. Ant chooses its next node according to a
  probabilistic rule
• -probabilities in routing table
• -traffic level in the node

neighbours
2 5
11 0.4 0.6
destination
63
Sniffing the network

• Ant moves towards its destination
• and it memories its path

11 t5
10 t4
9 t3
3 t2
2 t1
1 t0
1
64
The backward ant

• Ant goes back using the same path

11 t5
10 t4
9 t3
3 t2
2 t1
1 t0
65
Updating the probability tables

• On its way to the source, ant updates
• routing tables in all nodes
• table in 1 before update
• table after update

2 5
11 0.4 0.6
2 5
11 0.8 0.2
66
Simple formulae

• Calculate reinforcement
• Update probabilities

67
Complex formulae
PjdPjd r(1-Pjd)
PndPnd - rPnd , nltgtj
68
Simulation environment

• Map representation for
• simulation

69
Results
Average trip time for the cars using the routing
system
Average trip time for the cars that not use the
routing system
70
Simulation environment

• Architecture

71
Communication flow
72
Routing system
73
Routing system (2)

• Timetable

1 2 4 5
1 - 12 15 -
2 11 - - 18
4 14 - - 13
5 - 18 14 -

74
Experiment
75
Personal intelligent travel assistant

• PITA is multimodal, speech, touch, text,
  picture,GPS,GPRS
• PITA is able to find shortest route in time using
  dynamic traffic data
• PITA is able to launch robust agents finding
  information on different sites (imitating HCI)
• PITA computes shortest route using AI techniques
  (expertsystems, case based reasoning, ant based
  routing alg, adaptive Dijkstra alg.)

76
(No Transcript)
77
(No Transcript)
78
PDA
79
Digital Assistant

• Digital assistant has characteristics of a human
  operator
• Ambient Intelligent
• Context awareness
• Adaptive to personal characteristics
• Independent, problem solver
• Computational, transparent solutions
• Multimodal input/output

80
Schematic overview of the PITA components
81
(No Transcript)
82
Overview of communication

• Wireless network layers
• human communication layer
• virtual communication
• virtual coordinating agent

83
Actors, Agents and Services

• Layers of communication
• overlapping clouds of actors ( human sensors,
  perception devices)
• corresponding clouds of representative agents
• clouds of services

84
Mobile Ad-Hoc Network
85
PITA system in a train

• Travelers in train have device able to set up a
  wireless network in the train or to communicate
  via e-mail, connected to GPS
• Position of traveler corresponds to position of
  trains
• (de-)Centralized systems knows the position of
  train at every time and is able to reroute and
  inform travelers in dynamically changing
  environments

86
A technical view of the PITA system
87
(No Transcript)
88
The personal agent
89
The handheld interface model
90
The handheld application model
91
A handheld can be connected to the rest of the
system by only an ad-hoc wireless connection
92
Sequence diagram of the addition of a new delay
93
The distributed agent platform architecture
94
(No Transcript)
95
(No Transcript)
96
(No Transcript)
97
(No Transcript)
98
THE MAPPING BETWEEN THE USER PROFILES AND THE
SEARCH PARAMETERS
User profiles
99
Search times
The route plan to Groningen Noord