T R A C K       P A P E R
Close

Login Panel

Close tab

Password Meter

Volume 11 Issue 06 (June 2024)

S.No. Title & Authors Page No View
1

Title : Deep Reinforcement Learning-based DAG Task Scheduling Algorithm for Cloud Computing

Authors : Jiaxin Su

Click Here For Abstract

Download Certificate
Abstract :

As the paradigm of cloud computing burgeons, task scheduling emerges as a critical mechanism in enhancing resource utilization and quality of service. However, scheduling tasks modeled by Directed Acyclic Graphs (DAGs) poses significant challenges due to their inherent parallelism and dependency constraints. Deep reinforcement learning (DRL) offers a promising approach to address these challenges, yet existing approaches such as the Deep Deterministic Policy Gradient (DDPG) algorithm are hindered by issues including unstable Actor network training. This study introduces an advanced DDPG-based scheduling algorithm tailored for the unique complexities of DAG cloud computing task scheduling. We fortified the Actor network by incorporating a supervised learning approach to adjust its loss function, thereby stabilizing training outcomes. Empirical analyses across several critical metrics—task completion time, server energy consumption, and standard deviation of resource utilization—demonstrate that our refined model substantially outperforms traditional scheduling methods and unmodified DRL algorithms. The findings affirm that the enhanced DDPG algorithm not only expedites scheduling effectiveness but also reduces energy consumption while maintaining service quality, showcasing the extensive potential and pragmatic value of applying DRL in cloud computing task scheduling. Our improved approach is poised to contribute a fresh perspective to future research and application in DAG task scheduling.

1-7
2

Title : Observer-Based Event-Triggered Sliding Mode Control for Attitude of Quadrotor with Mismatched Disturbances

Authors : Shanshan Zhang, Ming Zhao

Click Here For Abstract

Download Certificate
Abstract :

This paper presents an observer-based event-triggered adaptive super-twisting controller for attitude tracking of a quadrotor unmanned aerial vehicles (UAVs) in the presence of matched and mismatched disturbances. Firstly, an observer-based adaptive super-twisting controller is designed to mitigate overestimation of gains and reduce chattering effects, thereby effectively addressing both matched and mismatched disturbances, and enhancing the control performance and robustness of quadrotor UAV. Furthermore, a dynamic event-triggered control strategy is employed, which flexibly determines the timing of controller updates based on the actual state variations of the system. This approach reduces unnecessary controller updates, saving communication and computational resources, and enhances system performance and efficiency. Finally, the superiority of the proposed method is validated through simulation and experimental results.

8-12
3

Title : Quadrotor UAV attitude control of super-twisting sliding mode based on disturbance observer

Authors : Ming Zhao, Shanshan Zhang

Click Here For Abstract

Download Certificate
Abstract :

In this paper, we introduce a novel approach combine the high-gain disturbance observer and super-twisting sliding mode control strategy. In this method, the disturbance observer is cleverly used to generate accurate estimates of the disturbance in real time, and then these estimates are incorporated into the control law to achieve effective compensation for the disturbance effect. By using a single parameter, the observer can be stabilized while the parameter tuning effort is reduced. In addition, interference estimation is combined with a super-twisting sliding mode controller to reduce the chattering effect caused by discontinuity. In order to ensure the stability of the system, Lyapunov stability analysis is further carried out to ensure that the tracking error is kept within the bounded range. To comprehensively evaluate the efficacy of the proposed control methods, this paper adopts a combined approach, encompassing both simulation and experimental methods. The research data show that the tracking accuracy and stability of the quadrotor UAV controller are significantly improved when the disturbance observer is introduced into the controller.

13-17
4

Title : Design and Case Study of Long Short Term Modeling for Next POI Recommendation

Authors : Qi An, Minhong Dong

Click Here For Abstract

Download Certificate
Abstract :

In recent years, research on the next POI recommendation has received widespread attention. Its goal is to recommend the next POI to users at a specific time based on their historical check-in data. Therefore, modeling the long-term behavior habits and recent continuous behavior of users is crucial. However, existing methods for modeling user short-term preferences either ignore their long-term preferences or the semantic distribution between recently visited POIs, resulting in unreliable recommendation results. To address these issues, we conducted research and analysis on existing relevant literature, planned potential further research ideas and technical routes, and summarized the methods for such research tasks. Described the model framework of the research case, introduced the commonly used datasets and evaluation indicators in POI recommendation methods, and analyzed the experimental results of existing research cases.

18-21
5

Title : Barrier Function Based On Terminal Sliding Mode Control for Robotic Manipulators

Authors : Jixun Li

Click Here For Abstract

Download Certificate
Abstract :

This paper studies the optimal trajectory tracking control strategy of robotic manipulators in the presence of external disturbances. Super-twisting algorithm (STA) is used as switching controller to effectively weaken chattering.  The choice of the barrier function as the gain of STA avoids the estimation of the disturbance upper bound and does not require the design of the low-pass filter. The stability of the closed-loop system is proved by Lyapunov theory. Finally, the effectiveness of the proposed method is verified by simulation experiments.

22-27
6

Title : Research on Column Generation Algorithm for Solving Three-Dimensional Packing Problem

Authors : Meng Wang, Chengxia Liu, Minling Zhu,Yaokun Shi

Click Here For Abstract

Download Certificate
Abstract :

Three-dimensional packing problem refers to how to put a series of items of known size into a given container in three-dimensional space, so that the space utilization of the container is the highest. This problem has a wide range of applications in logistics, warehousing, manufacturing and other fields. We first solve the relevant mathematical model through a column-generation heuristic algorithm to obtain a layer containing a set of items. These layers are then stacked together into a container using a simple heuristic algorithm. After experiments, our method has a good loading rate and can complete the loading of items in a very short time.

28-32