A Deep-Q Learning Approach to Mobile Operator Collaboration

• Next-generation mobile connectivity services include a large number of devices distributed across vast geographical areas. Mobile network operators will need to collaborate to fulfill service requirements at scale. Existing approaches to multioperator services assume already-established collaborations to fulfill customer service demand with specific quality of service (QoS). In this paper, we propose an agent-based architecture, where establishment of collaboration for a given connectivity service is done proactively, given predictions about future service demand. We build a simulation environment and evaluate our approach with a number of scenarios and in context of a real-world use case, and compare it with existing collaboration approaches. Results show that by learning how to adapt their collaboration strategy, operators can fulfill a greater part of the service requirements than by providing the service independently, or through pre-established, intangible service level agreements.

Subject headings

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Telekommunikation (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Telecommunications (hsv//eng)

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Kommunikationssystem (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Communication Systems (hsv//eng)

Keyword

agent-based architectures

deep reinforcement learning

mobile networks

5G

6G

Publication and Content Type

ref (subject category)

art (subject category)