Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

UWSN communication scenario with concurrent communication.

More »

Fig 1 Expand

Fig 2.

Mobility model of underwater sensor nodes.

More »

Fig 2 Expand

Fig 3.

Workflow diagram of MARL.

More »

Fig 3 Expand

Fig 4.

Training and distributed execution architecture.

More »

Fig 4 Expand

Fig 5.

UWSN communication scenarios including node failures.

More »

Fig 5 Expand

Fig 6.

Process of semi-cooperative power allocation mechanism.

More »

Fig 6 Expand

Table 1.

Parameter settings.

More »

Table 1 Expand

Fig 7.

Network performance during the training phase.

More »

Fig 7 Expand

Table 2.

Performance of the MARL model and other comparison methods.

More »

Table 2 Expand

Fig 8.

Training curves under different network densities in the HomNet scenario.

More »

Fig 8 Expand

Fig 9.

Training curves under different network densities in the HetNet scenario.

More »

Fig 9 Expand

Table 3.

Average latency of MARL model and baseline methods under different network densities.

More »

Table 3 Expand

Table 4.

Simulation results under different synchronization error levels (Shallow sea complex channel, D = 4).

More »

Table 4 Expand

Fig 10.

The influence of SINR thresholds on network performance in various scenarios.

More »

Fig 10 Expand

Fig 11.

The influence of water flow velocity on network performance in different scenarios.

More »

Fig 11 Expand

Fig 12.

The impact of mobile node interference on network performance.

More »

Fig 12 Expand

Table 5.

Comparison of inference overhead among different micro-controller platforms.

More »

Table 5 Expand

Table 6.

Performance comparison statistics results with modern MARL baselines (HetNet scenario, n = 10).

More »

Table 6 Expand

Table 7.

Results of ablation experiment.

More »

Table 7 Expand