Information Technology Reference
In-Depth Information
Ta b l e 2 .
Adaptation of the offer prices
•
update
receivedT otalCycles
;
•
calculate
receivedCycles
;
• expectedCycles
=
min{
2000
,offeredCycles × μ}
;
•
if
receivedCycles < expectedCycles
then
r
=
r − δ
;
•
else if
receivedCycles > expectedCycles
then
r
=
r
+
δ
.
more than this figure, it means that the agent has set its offer price too low. In contrast,
if the number is too small, it means the agent is not winning enough customer orders
(which implies that its offer price is too high). However, we cannot just base our deci-
sion on 2000 cycles because some of that day's production cycles might be reserved by
the orders of previous days (because more than 2000 cycles were needed previously).
In this case, the number of expected cycles for the day's order is only part of the offered
cycles of the previous day (because all agents compete for customer orders and only the
lowest price can be accepted). With this information, the agent can adapt its offer prices
in order to try and keep the factory working at high capacity, but still be responsive to
the prices other agents offer (based on the highest and lowest transaction prices of the
previous day). Specifically, the adaptation rule is if the orders the agent receives need
more cycles than it expected, it will increase its price, otherwise it will decrease it.
Table 2 shows how the price adaptation works. Here,
receivedT otalCycles
repre-
sents the total number of cycles needed to produce the PCs for the orders just received;
receivedCycles
represents the cycles needed for the orders that the agent offers from
the component inventory rather than the finished PCs (finished PCs do not count since
they do not require more cycles to produce them);
offeredCycles
is the actual total
number of cycles offered on the previous day (as per Table 1) and
expectedCycles
is
offeredCycles
multiplied by the expected acceptance rate (
μ
=0
.
75),
i.e.
,how
many cycles are expected to win customer orders among all the cycles offered. Now
if
receivedCycles
is much less than the expected number of cycles, the agent will
decrease the adjustment factor (thus the price is decreased, see Equation (1)) by
δ
(here
δ
=0
.
02), otherwise it will increase the adjustment factor (thus the price is in-
creased). However sometimes if the expected number of cycles is only slightly smaller
than the actual number of received cycles, we do not decrease the offer prices (since
this is a close enough approximation in a noisy environment). To realise this, we view
expectedCycles
as a fuzzy number [11].
3.3
The Factory Agent
One of the main challenges for the factory agent is scheduling what to produce and
when to produce it (
i.e.
, how to allocate supply resources and factory time). The strat-
egy we use includes: manufacturing PCs according to customer orders and satisfying
orders with an earlier delivery date (see Table 3 for more detail). Now, since the com-
puters stored in the factory will be charged storage cost, each order will be delivered
as soon as it is filled. The agent builds the PCs according to the customers' orders it
has obtained (which has the advantage of ensuring that the factory always produces the
