Table 5.

Summary of ML studies for network slicing in O-RAN.

Year	Ref	Contribution
2022	[37]	Introduced the application of ML to network slicing; discussed some open challenges and potential solutions.
2022	[38]	Provided an intelligent closed-loop SLA assurance scheme for O-RAN slicing. A real-world dataset of a large operator is used to train a learning solution for optimizing resource utilization in the proposed closed-loop service automation process.
2022	[39]	Developed a novel O-RAN slicing framework over an evolutionary-based DRL approach to manage network slices dynamically in the rapid changing environment.
2022	[40]	Addressed the elastic O-RAN slicing problem for industrial monitoring and control in IIoT and introduced a matching game for solving the IIoT association problem, and then applied an actor-critic-based deep reinforcement learning model for O-RAN slicing-based resource allocation.