Skip to main content

Advances, Systems and Applications

Table 2 The action space of the agent in each sub-grid

From: Power flow adjustment for smart microgrid based on edge computing and multi-agent deep reinforcement learning

No.

multiples of generators’ output

Number of compensators

Transformer ratio value

agent 1

2∗(0−5)

14∗(0−10)

4∗(0−5)

agent 2

2∗(0−5)

10∗(0−10)

2∗(0−5)

agent 3

5∗(0−5)

14∗(0−10)

5∗(0−5)