[S3] Advanced Optical Technologies for Bigdata/IoT Service

[S3-3] Machine Learning Methods for Slice Admission in 5G Networks

Muhammad Rehan Raza¹, Carlos Natalino², Lena Wosinska², 〇Paolo Monti² (¹KTH Royal Institute of Technology, Sweden, ²Chalmers Univ. of Technology, Sweden)

Keywords:Data analytics for network control and management in optical core/data center networks, Optical core/metro/data-center network architecture, design, virtualization, slice, control and management

The paper discusses how the slice admission problem can be aided by machine learning strategies. Results show that both supervised and reinforcement learning might lead to profit maximization while containing losses due to performance degradation.