Skip to main content
Fig. 8 | EURASIP Journal on Wireless Communications and Networking

Fig. 8

From: Decentralized computation offloading for multi-user mobile edge computing: a deep reinforcement learning approach

Fig. 8

Illustration of power-delay tradeoff for a single user agent with λ1=3.0Mbps. Note that for the points on each curve from left to right, the tradeoff factor w1 varies from 0.3∼0.8, correspondingly. Notice that there is no trade-off curve for these two greedy algorithms, since they are not impacted by the tradeoff factors. The power-delay points for GD-offload and GD-local are located at (1.85,3.148) and (1.91,3.147), respectively

Back to article page