Majalah Ilmiah UNIKOM

Vol.8, No. 2

208

H a l a m a n

Muhammad Aria

Defuzzification

Since the resultant type-reduced output is

an interval type-1 fuzzy set, the output of

fuzzy can be calculate using the average of

its lower and upper bounds

FUZZY LOGIC TRAFFIC SIGNAL CONTROL-

LERS FOR COMPLEX INTERSECTIONS

A fuzzy logic controlled traffic lights uses

sensors that count cars. This provides the

controller with traffic densities in the lanes

and allows a better assessment of changing

traffic patterns. As the traffic distributions

fluctuate, the fuzzy controller can change

the signal light accordingly. The fuzzy logic

controller determines whether to extend or

terminate the current green phase based on

a set of fuzzy rules. The flow diagram of a

controller is shown if Figure 4.

The objective of the Fuzzy traffic light con-

trollers is to reduce the total delay time of

waiting vehicles as well as to avoid heavy

traffic congestion and to synchronize the

local traffic controller with its neighbors,

such as controlling the outgoing vehicles

into neighboring traffic controllers. The fuzzy

traffic lights controller is designed with a

number of useful features so for example is

that if a large volume of vehicles are con-

gested at a neighboring intersection, the

number of vehicles coming into that inter-

section will be reduced.

Fuzzy logic traffic signal controllers con-

tains three modules and this is as shown in

Figure 5. It consist of a Next Phase Module,

a Green Phase Module and a Decision Mod-

ule. The Next Phase Module observes the

condition all the other phases except the

green phase. The Select Max Urgency Phase

selects the most urgent phase. The Green

Phase Module observes the condition of

traffic flow of the green phase only. The De-

cision Module decides the urgency degree

between the Next Phase and the Green

Phase Modules. It also decides by how long

to extend the green phase signal or whether

to change to other phases. For example, if

the Green Phase Module is more urgent

than the Next Phase Module, the green sig-

nal will be extended. On the other hand, if

the Next Phase Module is more urgent than

the Green Phase Module, the Decision Mod-

ule will change the green phase signal to

another phase.

Fuzzy Logic Next Phase Module

NextPhase Module

QueueNum

FrontNumRedTimeQueueNum

(zero, short, medium, large, very large) re-

fers to the number of vehicles remain in a

FrontNum

(short, medium, large, very large) quantifies

the number of vehicles in the link between

the affected intersection and the down-

stream intersections. Information regarding

the quantity of vehicles in the front link, left

link and the right link are all sent to the

fuzzy controller. This input is important in

order to avoid congested links. Another in-

put which is considered in our design is re-

RedTime

very large). It calculates the number of vehi-

cles waiting at a red light. This input is con-

sidered as to avoid the drivers waiting too

long for the green signal. Figure 6 - Figure 8

shows the membership functions of

QueueNum, FrontNum and RedTime.

Ur-

gencyUrgency

traffic condition of the selected phase. If the

Figure 6. Membership functions

for QueueNum