Evaluation showed that the proposed utility based solution outperformed the existing heuristic based approach in terms of energy savings and minimizing SLAVs in both lightly loaded and more heavily loaded cloud data centers.
For example, let us assume asymmetric traffic, where the highly loaded link (DL) offers k times more load than the lightly loaded link (UL).
Thus, NCJT is considered more suitable for deployment in lightly loaded scenario [17].
In principle, this can facilitate more efficient use of servers by shifting VMs from lightly loaded servers onto higher-laden servers until the lightly-loaded server is unutilised and can be switched into a sleep or off state.
Results conclude that the proposed utility-based solution saves more energy and reduces SLA violations more effectively than the heuristics-based one both in heavily and lightly loaded data center settings.
The goal of the first experiment is to test the effectiveness of the solution on lightly loaded data centers while the second experiment tests the solution in more loaded cloud data centers.
We confirmed that (i) the first cases in Propositions 1 and 2 are generally observed, (ii) FFR and macro-diversity (MD) increase cell-edge throughput by up to 15% when without a loss in system throughput, and (iii) more users switch to the cell-edge type when the neighboring cell is lightly loaded.
These scenarios are considered relevant because we need to be confident that: (i) the opportunities that exist to save energy are exploited in lightly loaded settings, and (ii) adaptation costs and attempts at energy saving do not lead to more SLAs being missed in a heavily loaded setting.
As in the analysis above, MIL can identify heavy load and heavy interference areas in the network; packets are routed through low interference and lightly loaded path, which can lead to less packet loss, shorter end-to-end delay, that is, more packets can reach destinations more quickly and more accurately, and thus, the network performance is improved.
We derive simple non-smooth models for the lightly damped, lightly loaded dynamics of the pump.
A large lightly loaded balloon will be very "fat".
