They describe a distributed independent reinforcement learning (DIRL) approach for resource management, which forms an important component of any application including initial sensor selection and task allocation as well as run-time adaptation of allocated resources to tasks.
We initially define both zones in terms of the physical area and the amount of allocated resources and we investigate the impact of illumination requirements on defining both zones.
A container is characterized by a triplet of allocated resources (CPU, RAM, and network bandwidth).
If a handoff connection is established, thad will be decreased with the amount of allocated resources as Equation (7) shows; if a new connection is granted, thad will be increased with the amount of allocated resources as Equation (8) shows.
It is seen that for lower values of, the amount of allocated resources (Set ) and the achieved throughput (Set ) are approximately equal.
Equation (3) allows minimizing the number of allocated resources n (θ = 1) or maximizing the average number of served users U n) (θ = 0).
For 0 < θ < 1, the resources are allocated as a function of the performance increment in relation to the amount of allocated resources.
(3) If a handoff connection is established, thad will be decreased with the amount of allocated resources as Equation (7) shows; if a new connection is granted, thad will be increased with the amount of allocated resources as Equation (8) shows. .
The update used can be linear in its simplest form and is based on the number of allocated resources as follows: mathrm{T} (u,t) = frac{mathrm{T} (u,t)}{K u,t)+1}.
When the condition shown in Equation (4) is met and a handoff connection is accepted, the adaptive threshold thad will be decreased with the amount of allocated resources for the handoff connection without going below thmin.
Alternatively, when the condition shown in Equation (5) is met and a new connection is accepted, thad will be increased with the amount of allocated resources for the new connection without exceeding thmax.
