 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| n |
But recent
instances are more likely to reflect
|
|
|
future
behavior
|
|
|
| n |
A common
technique for that is to use
|
|
|
exponential
averaging
|
|
|
|
u |
S[n+1] = a T[n] + (1-a) S[n] ;
0 < a < 1
|
|
|
|
u |
more weight is
put on recent instances whenever
|
|
a > 1/n
|
|
|
| n |
By expanding
this eqn, we see that weights of
|
|
|
past
instances are decreasing exponentially
|
|
|
u |
S[n+1] = aT[n] + (1-a)aT[n-1] + ... (1-a)^{i}aT[n-i] +
|
|
|
|
|
... + (1-a)^{n}S[1]
|
|
|
|
u |
predicted value
of 1st instance S[1] is not calculated;
|
|
|
usually set to 0
to give priority to to new processes
|
|
