Traffic matrix is an abstract representation of the traffic volume flowing between sets of source and destination pairs.It is a key input parameter of network operations management,planning,provisioning and traffic en...Traffic matrix is an abstract representation of the traffic volume flowing between sets of source and destination pairs.It is a key input parameter of network operations management,planning,provisioning and traffic engineering.Traffic matrix is also important in the context of OpenFlow-based networks.Because even good measurement systems can suffer from errors and data collection systems can fail,missing values are common.Existing matrix completion methods do not consider traffic exhibit characteristics and only provide a finite precision.To address this problem,this paper proposes a novel approach based on compressive sensing and traffic self-similarity to reconstruct the missing traffic flow data.Firstly,we analyze the realworld traffic matrix,which all exhibit lowrank structure,temporal smoothness feature and spatial self-similarity.Then,we propose Self-Similarity and Temporal Compressive Sensing(SSTCS) algorithm to reconstruct the missing traffic data.The extensive experiments with the real-world traffic matrix show that our proposed SSTCS can significantly reduce data reconstruction errors and achieve satisfactory accuracy comparing with the existing solutions.Typically SSTCS can successfully reconstruct the traffic matrix with less than 32%errors when as much as98%of the data is missing.展开更多
In recent years, wireless communication systems have experienced tremendous growth in data traffic. Many capacity-enhancing techniques are applied to elevate the gap between the amount of traffic and network capacity,...In recent years, wireless communication systems have experienced tremendous growth in data traffic. Many capacity-enhancing techniques are applied to elevate the gap between the amount of traffic and network capacity, and more solutions are required to minimize the gap. Traffic allocation among multiple networks is regarded as one of the most effective methods to solve the problem. However, current studies are unable to derive the quantity of traffic that each network should carry. An intelligent traffic allocation algorithm for multiple networks is proposed to obtain the optimal traffic distribution. Multiple factors affecting traffic distribution are considered in the proposed algorithm, such as network coverage, network cost, user habit, service types, network capacity and terminals. Using evaluations, we proved that the proposed algorithm enables a lower network cost than load balancing schemes. A case study of strategy rmldng for a 2G system refarming is presented to further illustrate the applicability of the proposed algorithm. We demonstrated that the new algorithm could be applied in strategy rmldng for telecommunication operators.展开更多
基金This work is supported by the Prospcctive Research Project on Future Networks of Jiangsu Future Networks Innovation Institute under Grant No.BY2013095-1-05, the National Ba- sic Research Program of China （973） under Grant No. 2012CB315805 and the National Natural Science Foundation of China under Grants No. 61173167.
文摘Traffic matrix is an abstract representation of the traffic volume flowing between sets of source and destination pairs.It is a key input parameter of network operations management,planning,provisioning and traffic engineering.Traffic matrix is also important in the context of OpenFlow-based networks.Because even good measurement systems can suffer from errors and data collection systems can fail,missing values are common.Existing matrix completion methods do not consider traffic exhibit characteristics and only provide a finite precision.To address this problem,this paper proposes a novel approach based on compressive sensing and traffic self-similarity to reconstruct the missing traffic flow data.Firstly,we analyze the realworld traffic matrix,which all exhibit lowrank structure,temporal smoothness feature and spatial self-similarity.Then,we propose Self-Similarity and Temporal Compressive Sensing(SSTCS) algorithm to reconstruct the missing traffic data.The extensive experiments with the real-world traffic matrix show that our proposed SSTCS can significantly reduce data reconstruction errors and achieve satisfactory accuracy comparing with the existing solutions.Typically SSTCS can successfully reconstruct the traffic matrix with less than 32%errors when as much as98%of the data is missing.
基金supported partially by the National Science and Technology Major Projects under Grants No. 2012ZX03006003-005,No. 2012ZX03003006-002,and No. 2010ZX03002-008-01
文摘In recent years, wireless communication systems have experienced tremendous growth in data traffic. Many capacity-enhancing techniques are applied to elevate the gap between the amount of traffic and network capacity, and more solutions are required to minimize the gap. Traffic allocation among multiple networks is regarded as one of the most effective methods to solve the problem. However, current studies are unable to derive the quantity of traffic that each network should carry. An intelligent traffic allocation algorithm for multiple networks is proposed to obtain the optimal traffic distribution. Multiple factors affecting traffic distribution are considered in the proposed algorithm, such as network coverage, network cost, user habit, service types, network capacity and terminals. Using evaluations, we proved that the proposed algorithm enables a lower network cost than load balancing schemes. A case study of strategy rmldng for a 2G system refarming is presented to further illustrate the applicability of the proposed algorithm. We demonstrated that the new algorithm could be applied in strategy rmldng for telecommunication operators.
