Online Service Migration in Mobile Edge with Incomplete System Information: A Deep Recurrent Actor-Critic Learning Approach

@article{Wang2020OnlineSM,
  title={Online Service Migration in Mobile Edge with Incomplete System Information: A Deep Recurrent Actor-Critic Learning Approach},
  author={Jin Wang and Jia Hu and Geyong Min and Qiang Ni and Tarek A. El-Ghazawi},
  journal={IEEE Transactions on Mobile Computing},
  year={2020}
}
—Multi-access Edge Computing (MEC) is an emerging computing paradigm that extends cloud computing to the network edge (e.g., base stations, MEC servers) to support resource- intensive applications on mobile devices. As a crucial problem in MEC, service migration needs to decide where to migrate user services for maintaining high Quality-of-Service (QoS), when users roam between MEC servers with limited coverage and capacity. However, finding an optimal migration policy is intractable due to the… 

References

SHOWING 1-10 OF 34 REFERENCES

Adaptive User-managed Service Placement for Mobile Edge Computing: An Online Learning Approach

A novel adaptive user-managed service placement mechanism, which jointly optimizes a user’s perceived-latency and service migration cost, weighted by user preferences is proposed, which helps the user to make adaptive service placement decisions.

Mobility-Aware Deep Reinforcement Learning with Glimpse Mobility Prediction in Edge Computing

Through integrating the proposed DRL and glimpse mobility prediction model, the proposed M-DRL framework is optimized to handle the service provision problem in MEC with acceptable computation complexity and near-optimal performance.

Delay-Aware Microservice Coordination in Mobile Edge Computing: A Reinforcement Learning Approach

This article reformulates the microservice coordination problem using Markov decision process framework and then proposes a reinforcement learning-based online micro service coordination algorithm to learn the optimal strategy, which proves that the offline algorithm can find the optimal solution while the online algorithm can achieve near-optimal performance.

Follow Me at the Edge: Mobility-Aware Dynamic Service Placement for Mobile Edge Computing

This paper applies Lyapunov optimization to decompose the long-term optimization problem into a series of real-time optimization problems which do not require a priori knowledge such as user mobility, and designs an approximation algorithm based on Markov approximation to seek a near-optimal solution.

Dynamic Service Migration in Mobile Edge Computing Based on Markov Decision Process

This paper forms the service migration problem as a Markov decision process (MDP), which captures general cost models and provides a mathematical framework to design optimal service migration policies and approximate the underlying state space by the distance between the user and service locations.

Path Selection for Seamless Service Migration in Vehicular Edge Computing

A path-selection algorithm is proposed to jointly optimize both interests of the network plane and service plane to ensure seamless service migration during the migration of vehicles and it is proved theoretically that the proposed algorithm can give a weakly Pareto-optimal solution.

Efficient Live Migration of Edge Services Leveraging Container Layered Storage

An edge computing platform architecture which supports seamless migration of offloading services while also keeping the moving mobile user “in service” with its nearest edge server is proposed.

A Survey on Mobility-Induced Service Migration in the Fog, Edge, and Related Computing Paradigms

The diversity characterizing the landscape of migration scenarios at the edge is examined, an objective-driven taxonomy of the literature is presented, and contributions that rather focused on architectural design and implementation are highlighted.

EMM: Energy-Aware Mobility Management for Mobile Edge Computing in Ultra Dense Networks

A novel user-centric energy-aware mobility management scheme, based on Lyapunov optimization and multi-armed bandit theories, that can achieve close-to-optimal delay performance while satisfying the user energy consumption constraint.

A Joint Service Migration and Mobility Optimization Approach for Vehicular Edge Computing

A multi-agent deep reinforcement learning (MADRL) algorithm is proposed to maximize the composite utility of communication, computing, and route planning in a distributed way and substantially reduces service delay, migration cost and travel time as compared with the existing baselines.