DDQN-TS: A novel bi-objective intelligent scheduling algorithm in the cloud environment

Tong, Zhao; Ye, Feng; Liu, Bilan; Cai, Jinhui; Mei, Jing

doi:10.1016/j.neucom.2021.05.070

Cited by 23 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both active and idle VMs depend on CPU utilization. The energy consumption of an active VM (𝐸 𝑎𝑐𝑡𝑖𝑣𝑒 ) is calculated as the energy consumption of task execution at a particular VM (𝐸 𝑡𝑒𝑥𝑒 ) and energy consumption of task transfer between two VMs (𝐸 𝑡𝑡 ), which is represented in (14). 𝐸 𝑡𝑒𝑥𝑒 depends on the load on VM, CPU utilization of VM and weight of the server (𝑆 𝑤𝑡 ) which is represented in (12).…”

Section: Energy Consumptionmentioning

confidence: 99%

“…To improve the exhibition, keep up load, and adjusting and incrementing the throughput, a hybrid technique is developed in [11], which combines both modified PSO and a Q-learning algorithm known as QMPSO. The Deep Qnetwork (DQN) method is broadly utilized in Deep Reinforcement Learning (DRL) to achieve the maximum reward [12,13,14]. In [12], a joint optimization is formulated of the task offloading and bandwidth allocation for multi-user mobile edge computing, with the objective of minimizing the overall cost, including the total energy consumption and the delay in finishing the task.…”

Section: Introductionmentioning

confidence: 99%

“…To solve the resource allocation issue in the Mobile Edge Computing environment, a smart resource allocation algorithm, known as the Deep Reinforcement Learning based Resource Allocation (DRLRA) algorithm, is proposed in [13] to minimize average service time and balance the resource allocation. To achieve efficient real-time task scheduling in the cloud environment, a double deep Q-network task scheduling (DDQN-TS) scheduling method is proposed in [14] to reduce the task response time while ensuring a high task completion rate. Similarly, compared to various population-based methods, Particle Swarm Optimization (PSO) is more efficient, simple, and easy to learn with fewer parameters that require adjustment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Intelligent Decision-Making of Load Balancing Using Deep Reinforcement Learning and Parallel PSO in Cloud Environment

Pradhan

Bisoy

Kautish³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Machine learning and parallel processing are extremely commonly used to enhance computing power to induce knowledge from an outsized volume of data. To deal with the problem of complexity and high dimension, machine learning algorithms like Deep Reinforcement Learning (DRL) are used, while parallel processing algorithms like Parallel Particle Swarm Optimization (PPSO) are parallelized to speed up the operation and reduce the processing time to train the neural network. Due to the arrival of a large number of incoming tasks in the cloud environment, load balancing is an important issue. To solve this problem, the datacenter controller or an agent makes an intelligent decision to handle a large number of tasks within a minimum time period or at high speed. In this work, we proposed an effective scheduling algorithm named Deep Reinforcement Learning with Parallel Particle Swarm Optimization (DRLPPSO) to solve the load balancing problem and its various parameters with greater accuracy and high speed. Our experimental results show that our proposed scheduling algorithm increases the reward by 15.7%, 12%, and 13.1% when the task set is 2000 and improves the reward by 17.5%, 12.6%, and 15.3% when the task set is 4000, as compared to the Modified Particle Swarm Optimization (MPSO), Asynchronous Advantage Actor-Critic (A3C), and Deep Q-Network (DQN) techniques.

show abstract

Section: Energy Consumptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Decision-Making of Load Balancing Using Deep Reinforcement Learning and Parallel PSO in Cloud Environment

Pradhan

Bisoy

Kautish³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In our actual arranging work, what we often want is not the best timetable, but a good enough timetable, as long as it can meet the actual work situation of the school. Usually when we solve the problem of scheduling, we use a fourtuple function to evaluate the quality of the solution [21]:…”

Section: Application Of Minimum Disturbance and Optimalmentioning

confidence: 99%

Application of Edge Computing in Physical Education Teaching Management

Nie

Yuan

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In the traditional teaching mode, teachers have limited time and energy, but the emergence of AI technology-assisted teaching has greatly facilitated students and teachers. They can study and teach anytime and anywhere and can also solve the problem of lack of professional teachers or venues. With the continuous popularization of “Internet + education” technology, the teaching mode has changed, and online courses are gradually accepted by students regardless of time and geographical constraints. This article aims to study the optimization and application of the intelligent scheduling algorithm in the physical education management system based on blockchain technology. This article proposes a combination of Edge Computing technology and intelligent algorithm software and hardware to improve the current difficulties of domestic colleges and universities. The core content of integration, system functions, course scheduling algorithm, database, and other core contents are preliminary designed, hoping to provide ideas for the specific implementation of the college course scheduling system. The experimental results in this paper show that with the support of Edge Computing in solving the CSP problem, the efficiency of various algorithms is relatively high and comparable when the filling rate is less than 90%. However, when the filling rate exceeds 90%, the execution time of the IFS CBS algorithm is relatively longer, but it is generally acceptable. The algorithm and optimization strategy are also implemented, and the performance improvement of the algorithm is compared and analyzed through experiments, which proves the feasibility of the optimization strategy.

show abstract

“…With the increase of the number of iterations, in the tth iteration, the ant k moves at the position of the path . The state transition probability [10] is as follows:…”

Section: Mathematical Model Of Ant Colony Algorithmmentioning

confidence: 99%

Research on UAV cloud control system based on ant colony algorithm

Zhang

2022

J. of Syst. Eng. Electron.

View full text Add to dashboard Cite

In the cloud era, the control objects are becoming larger and the information processing is more complex, and it is difficult for traditional control systems to process massive data in a timely manner. In view of the difficulty of data processing in the cloud era, it is extremely important to perform massive data operations through cloud servers. Unmanned aeriel vehicle (UAV) control is the representative of the intelligent field. Based on the ant colony algorithm and incorporating the potential field method, an improved potential field ant colony algorithm is designed. To deal with the path planning problem of UAVs, the potential field ant colony algorithm shortens the optimal path distance by 6.7%, increases the algorithm running time by 39.3%, and increases the maximum distance by 24.1% compared with the previous improvement. The cloud server is used to process the path problem of the UAV and feedback the calculation results in real time. Simulation experiments verify the effectiveness of the new algorithm in the cloud environment.

show abstract

DDQN-TS: A novel bi-objective intelligent scheduling algorithm in the cloud environment

Cited by 23 publications

References 36 publications

Intelligent Decision-Making of Load Balancing Using Deep Reinforcement Learning and Parallel PSO in Cloud Environment

Intelligent Decision-Making of Load Balancing Using Deep Reinforcement Learning and Parallel PSO in Cloud Environment

Application of Edge Computing in Physical Education Teaching Management

Research on UAV cloud control system based on ant colony algorithm

Contact Info

Product

Resources

About