Digital Signal Processing Reference
In-Depth Information
Fig. 7.9
Spatial Learning is shown to outperform Spatial Backoff by 33% in throughput using the
P
r
-based states. It also reaches a better fairness index and lower power than SB
Fig. 7.10
We use the
heuristic recommendations to
speed up convergence. The
addition of heuristics to
Q-learning also allows to
converge to a better
steady-state solution. When
h
b
is equal to 1, heuristics are
not considered, as can be seen
in (
7.10
)-(
7.13
)
terminals [99]. We can see that SL performs better among legacy 802.11 terminals
as these cannot optimize their own transmissions fully, generating opportunities for
the SL terminals. However, adding more SL terminals doesn't reduce the average
throughput of the SL terminals that much. This makes for a compelling business
case, where the first adopters are rewarded the most.
