Intelligent Cloud Resource Management using Deep Reinforcement Learning

使用深度强化学习的智能云资源管理

• 批准号: 20K19931
• 负责人: Ahmed Moustafa
• 金额: $ 2.25万
• 依托单位: Nagoya Institute of Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Early-Career Scientists
• 财政年份: 2020
• 资助国家: 日本
• 起止时间: 2020-04-01 至 2022-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-20K19931/
• 关键词: Resource Management; Cloud Services; Service Composition; Federated Learning; Reinforcement Learning

We were able to achieve sufficient results on the following subjects.・ how to utilize the collectec data in offline mode in order to provide more efficient approaches for clud service compositions.・ how to improve the security and privacy of the clud data using novel federated learning techniques.Due to the outbreak of CIVID-19, travel and movement became restricted. This has greatly affected our ability to move especially attending international conferences and society meeting.Based on these, we plan to investigate the application of federated learning in order to secure the privacy of cloud data during exchange among multiple coud ventors and provide autonomous management for coud services.

我们能够在以下主题上取得足够的成果。·如何在离线模式下利用collectec数据，以便为clud服务组合提供更有效的方法。 如何使用新的联邦学习技术来提高clud数据的安全性和隐私性。由于CIVID-19的爆发，旅行和移动受到限制。 这极大地影响了我们的移动能力，特别是参加国际会议和社会会议。基于此，我们计划研究联邦学习的应用，以确保云数据在多个Coud供应商之间交换时的隐私，并提供Coud服务的自主管理。

项目成果

CEEP-FL: A comprehensive approach for communication efficiency and enhanced privacy in federated learning

• DOI: 10.1016/j.asoc.2021.107235
• 发表时间: 2021-03-06
• 期刊: APPLIED SOFT COMPUTING
• 影响因子: 8.7
• 作者: Asad, Muhammad;Moustafa, Ahmed;Aslam, Muhammad
• 通讯作者: Aslam, Muhammad

On Learning Adaptive Service Compositions

• DOI: 10.1007/s11518-021-5498-0
• 发表时间: 2021-08
• 期刊: Journal of Systems Science and Systems Engineering
• 影响因子: 1.2
• 作者: Ahmed Moustafa

Federated Learning Versus Classical Machine Learning: A Convergence Comparison

• DOI: 10.22541/au.162074596.66890690/v1
• 发表时间: 2021-07
• 期刊: ArXiv
• 作者: Muhammad Asad;Ahmed Moustafa;Takayuki Ito

PPCSA: Partial Participation-based Compressed and Secure Aggregation in Federated Learning

PPCSA：联邦学习中基于部分参与的压缩和安全聚合

• 发表时间: 2021
• 期刊: Proceedings of the The International Conference on Advanced Information Networking and Applications (AINA-2021)
• 作者: Ahmed Moustafa;Muhammad Asad;Saima Shaukat and Alexander Norta
• 通讯作者: Saima Shaukat and Alexander Norta