Advances, Systems and Applications
From: Reliability-aware failure recovery for cloud computing based automatic train supervision systems in urban rail transit using deep reinforcement learning
State
Ordinary
Alert
Critical
\(\mathcal {P}_{oo}\)
\(\mathcal {P}_{oa}\)
0
\(\mathcal {P}_{ao}\)
\(\mathcal {P}_{aa}\)
\(\mathcal {P}_{ac}\) grows overtime
recovery
No recovery