Deep Reinforcement Learning for Performance-Aware Adaptive Resource Allocation in Mobile Edge Computing

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static-preview.hindawi.com/articles/wcmc/volume-2020/2765491/figures/2765491.fig.003a.svgz" name="2765491.fig.003a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>The total reward</td></tr><tr class="fig-image" id="b"><td><object data="https://static-preview.hindawi.com/articles/wcmc/volume-2020/2765491/figures/2765491.fig.003b.svgz" name="2765491.fig.003b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>The total number of processed tasks</td></tr><tr class="fig-image" id="c"><td><object data="https://static-preview.hindawi.com/articles/wcmc/volume-2020/2765491/figures/2765491.fig.003c.svgz" name="2765491.fig.003c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>The total number of timeout penalty</td></tr><tr class="fig-image" id="d"><td><object data="https://static-preview.hindawi.com/articles/wcmc/volume-2020/2765491/figures/2765491.fig.003d.svgz" name="2765491.fig.003d" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(d) </b>The total number of dropped tasks</td></tr></table>

<div>Performance impact of different arrival rates.</div>

Wireless Communications and Mobile Computing

fig3

Figure 3

Figure 3: Deep Reinforcement Learning for Performance-Aware Adaptive Resource Allocation in Mobile Edge Computing 