Nebula: A Blockchain Based Decentralized Sharing Computing Platform

被引:2
作者
Yan, Bin [1 ]
Chen, Pengfei [1 ]
Li, Xiaoyun [1 ]
Wang, Yongfeng [1 ]
机构
[1] Sun Yat Sen Univ, Sch Data Sci & Comp, Guangzhou, Peoples R China
来源
BLOCKCHAIN AND TRUSTWORTHY SYSTEMS, BLOCKSYS 2019 | 2020年 / 1156卷
基金
中国国家自然科学基金;
关键词
Blockchain; Cloud computing; Smart contract; Ethereum; Resource sharing;
D O I
10.1007/978-981-15-2777-7_58
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Nowadays, there is a considerable amount of idle computers whose computing resources are partially wasted. On the other hand, the demand of resources is rapidly growing, since the explosion of data and the complexity of algorithms. To settle the contradictions, we develop Nebula, a decentralized platform based on blockchain for sharing computing resources. Nebula leverages blockchain to gather the scattered computing resources and provide a secure and vibrant computation trading market. Compared to traditional cloud platform, Nebula guarantees extra security because all transactions in this platform are validated by smart contracts. No one can tamper the transaction orders which are recorded by a widely distributed ledger. In Nebula, the resource consumer can order resources from resource providers with a very simple declarative script. When a deal is done, consumers can submit jobs to suppliers with a docker instance. Moreover, we model the order matching procedure of users' requests into a global maximum matching problem in a bipartite graph. We adopt the Hungarian algorithm to find an order matching policy, bringing an 10% increase to the matching rate in our best case. Moreover, we leverage the Proof of Authority (PoA) consensus algorithm called Clique, rather than Proof of Work (PoW) to increase the efficiency of Nebula, which provides nearly no less security but requires negligible computation on reaching consensus. To our best knowledge, we are the first to propose a general blockchain based platform for sharing computing resources, which fully utilizes the features of blockchain to achieve the scalability, the optimal order matching and a high performance.
引用
收藏
页码:715 / 731
页数:17
相关论文
共 16 条
  • [11] Nakamoto S., 2008, BITCOIN PEER TO PEER
  • [12] Online Deep Reinforcement Learning for Computation Offloading in Blockchain-Empowered Mobile Edge Computing
    Qiu, Xiaoyu
    Liu, Luobin
    Chen, Wuhui
    Hong, Zicong
    Zheng, Zibin
    [J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2019, 68 (08) : 8050 - 8062
  • [13] Wang JP, 2019, PROCEEDINGS OF THE 16TH USENIX SYMPOSIUM ON NETWORKED SYSTEMS DESIGN AND IMPLEMENTATION, P95
  • [14] Zhang Y., 2019, ABS190600245 CORR
  • [15] A Detailed and Real-time Performance Monitoring Framework for Blockchain Systems
    Zheng, Peilin
    Zheng, Zibin
    Luo, Xiapu
    Chen, Xiangping
    Liu, Xuanzhe
    [J]. 2018 IEEE/ACM 40TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING - SOFTWARE ENGINEERING IN PRACTICE TRACK (ICSE-SEIP 2018), 2018, : 134 - 143
  • [16] Blockchain challenges and opportunities: a survey
    Zheng, Zibin
    Xie, Shaoan
    Dai, Hong-Ning
    Chen, Xiangping
    Wang, Huaimin
    [J]. INTERNATIONAL JOURNAL OF WEB AND GRID SERVICES, 2018, 14 (04) : 352 - 375