Joint Optimization Across Timescales: Resource Placement and Task Dispatching in Edge Clouds

Wei, Xinliang; Rahman, Arrasy; Cheng, Dazhao; Wang, Yu

doi:10.1109/tcc.2021.3113605

Cited by 9 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[20], a deep deterministic policy gradient (DDPG)-based scheduling in Ref. [23], and graph coloring (GRAPH) with a genetic algorithm fitness function for scheduling [21].…”

Section: Simulation Environment Results Analysis and Evaluationsmentioning

confidence: 99%

“…Since task scheduling is an NP-hard problem, reinforcement learning based solutions are also provided. Reference [23] uses deep deterministic policy gradient-based scheduling. A set of tasks and resources are considered as the state of the system, and policy is learned to find optimal action of mapping edge server to the given task set.…”

Section: Load Balancing For Resource Managementmentioning

confidence: 99%

“…These general dynamic algorithms provide cost and time efficient results. Nowadays, machine learning based load balancing solutions are getting a lot of attention such as an energy efficient scheduling on federated edge cloud based on reinforcement learning (ESFEC-RL) [20], deep deterministic policy gradient (DDPG) [23], and graph coloring (GRAPH) [21]. Although algorithms such as ESFEC-RL [20] find optimal costs, execution time to converge to minimal cost is high.…”

Section: How Load Balancing Is Used To Optimize Latency and Energymentioning

confidence: 99%

“…1, we tested them on our proposed system. ESFEC-EF [20] is a heuristic-based algorithm, DDPG is a reinforcement-based algorithm in [23], and GRAPH is a graph coloring-based algorithm using a genetic algorithm fitness function in [21]. Both Refs.…”

Section: Graph Coloring (Graph) [21]mentioning

confidence: 99%

“…[21] and [23] are machine learning based algorithms with differences in learning approaches. Reference [23] uses reinforcement learning based algorithm which leverages the learning capability of DDPG technique to tackle network variation and find load balancing solution. Whereas Ref.…”

Section: Graph Coloring (Graph) [21]mentioning

confidence: 99%

See 4 more Smart Citations

Hybrid Mobile Cloud Computing Architecture with Load Balancing for Healthcare Systems

Lee¹,

Mhatre²,

Das³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Healthcare is a fundamental part of every individual's life. The healthcare industry is developing very rapidly with the help of advanced technologies. Many researchers are trying to build cloud-based healthcare applications that can be accessed by healthcare professionals from their premises, as well as by patients from their mobile devices through communication interfaces. These systems promote reliable and remote interactions between patients and healthcare professionals. However, there are several limitations to these innovative cloud computing-based systems, namely network availability, latency, battery life and resource availability. We propose a hybrid mobile cloud computing (HMCC) architecture to address these challenges. Furthermore, we also evaluate the performance of heuristic and dynamic machine learning based task scheduling and load balancing algorithms on our proposed architecture. We compare them, to identify the strengths and weaknesses of each algorithm; and provide their comparative results, to show latency and energy consumption performance. Challenging issues for cloudbased healthcare systems are discussed in detail.

show abstract

“…[20], a deep deterministic policy gradient (DDPG)-based scheduling in Ref. [23], and graph coloring (GRAPH) with a genetic algorithm fitness function for scheduling [21].…”

Section: Simulation Environment Results Analysis and Evaluationsmentioning

confidence: 99%

Section: Load Balancing For Resource Managementmentioning

confidence: 99%