随着万物互联和5G时代的到来,移动用户需要处理的数据量与其处理数据能力不匹配。将大量任务卸载到有限的边缘服务器上执行势必会产生竞争,拍卖模型的引入可以解决用户之间对资源的竞争问题。目前大多基于拍卖的任务卸载工作忽略了任务...随着万物互联和5G时代的到来,移动用户需要处理的数据量与其处理数据能力不匹配。将大量任务卸载到有限的边缘服务器上执行势必会产生竞争,拍卖模型的引入可以解决用户之间对资源的竞争问题。目前大多基于拍卖的任务卸载工作忽略了任务的期限感知,普遍的任务卸载工作只单一考虑延迟敏感任务,并且未考虑到保证卸载过程的安全性。基于此,提出了一种基于拍卖的期限感知任务卸载(Auction Based Deadline-aware Task Offloading,ABDTO)策略,利用基于智能合约的拍卖机制实现期限感知任务(延迟敏感型任务和非延迟敏感型任务)到边缘服务器的最优分配,以总效用(即总利润)作为评价标准,实现移动用户和边缘服务器的共赢。利用启发式遗传算法进行仿真实验,相比TACD,UPPER和RND算法,ABDTO策略的整体效用更高,最后利用Remix和Ganache等建立以太坊私有区块链网络进行仿真,证明了所提策略的正确性和可行性。展开更多
Fog computing is a new computing paradigm for meeting ubiquitous massive access and latency-critical applications by moving the processing capability closer to end users.The geographical distribution/floating features...Fog computing is a new computing paradigm for meeting ubiquitous massive access and latency-critical applications by moving the processing capability closer to end users.The geographical distribution/floating features with potential autonomy requirements introduce new challenges to the traditional methodology of network access control.In this paper,a blockchain-enabled fog resource access and granting solution is proposed to tackle the unique requirements brought by fog computing.The smart contract concept is introduced to enable dynamic,and automatic credential generation and delivery for an independent offer of fog resources.A per-transaction negotiation mechanism supports the fog resource provider to dynamically publish an offer and facilitates the choice of the preferred resource by the end user.Decentralized authentication and authorization relieve the processing pressure brought by massive access and single-point failure.Our solution can be extended and used in multi-access and especially multi-carrier scenarios in which centralized authorities are absent.展开更多
文摘随着万物互联和5G时代的到来,移动用户需要处理的数据量与其处理数据能力不匹配。将大量任务卸载到有限的边缘服务器上执行势必会产生竞争,拍卖模型的引入可以解决用户之间对资源的竞争问题。目前大多基于拍卖的任务卸载工作忽略了任务的期限感知,普遍的任务卸载工作只单一考虑延迟敏感任务,并且未考虑到保证卸载过程的安全性。基于此,提出了一种基于拍卖的期限感知任务卸载(Auction Based Deadline-aware Task Offloading,ABDTO)策略,利用基于智能合约的拍卖机制实现期限感知任务(延迟敏感型任务和非延迟敏感型任务)到边缘服务器的最优分配,以总效用(即总利润)作为评价标准,实现移动用户和边缘服务器的共赢。利用启发式遗传算法进行仿真实验,相比TACD,UPPER和RND算法,ABDTO策略的整体效用更高,最后利用Remix和Ganache等建立以太坊私有区块链网络进行仿真,证明了所提策略的正确性和可行性。
文摘Fog computing is a new computing paradigm for meeting ubiquitous massive access and latency-critical applications by moving the processing capability closer to end users.The geographical distribution/floating features with potential autonomy requirements introduce new challenges to the traditional methodology of network access control.In this paper,a blockchain-enabled fog resource access and granting solution is proposed to tackle the unique requirements brought by fog computing.The smart contract concept is introduced to enable dynamic,and automatic credential generation and delivery for an independent offer of fog resources.A per-transaction negotiation mechanism supports the fog resource provider to dynamically publish an offer and facilitates the choice of the preferred resource by the end user.Decentralized authentication and authorization relieve the processing pressure brought by massive access and single-point failure.Our solution can be extended and used in multi-access and especially multi-carrier scenarios in which centralized authorities are absent.
