Search

Predicting the future network traffic through big data analysis technologies has been one of the important preoccupations of network design and management. Combining Markov chains with tensors to implement predictions has received considerable attention in the era of big data. However, when dealing with multi-order Markov models, the existing approaches including the combination of states and Z-eigen decomposition still face some shortcomings. Therefore, this paper focuses on proposing a novel multivariate multi-order Markov transition to realize multi-modal accurate predictions. First, we put forward two new tensor operations including tensor join and unified product (UP). Then a general multivariate multi-order (2M) Markov model with its UP-based state transition is proposed. Afterwards, we develop a multi-step transition tensor for 2M Markov models to implement the multi-step state transition. Furthermore, an UP-based power method is proposed to calculate the stationary joint probability distribution tensor (i.e., stationary joint eigentensor, SJE) and realize SJE based multi-modal accurate predictions. Finally, a series of experiments under various Markov models on real-world network traffic datasets are conducted. Experimental results demonstrate that the proposed SJE based approach can improve the prediction accuracy for network traffic by highest up to 38.47 percentage points compared with the Z-eigen based approach. [ABSTRACT FROM AUTHOR]

The exponential growth of big data places a great burden on current computing environment. However, there exists a vast gap in the approaches that can securely and efficiently process the large scale heterogeneous data. This paper, on the basis of transparent computing paradigm, presents a unified approach that coordinates the transparent servers and transparent clients to decompose tensor, a mathematical model widely used in data intensive applications, to a core tensor multiplied with a number of truncated orthogonal bases. The structured, semi-structured as well as structured data are transformed to low-order sub-tensors, which are then encrypted using the Paillier homomorphic encryption scheme on the transparent clients. The cipher sub-tensors are transported to the transparent servers for carrying out the integration and decomposition operations. Three secure decomposition algorithms, namely secure bidiagonalization algorithm, secure singular value decomposition algorithm, and secure mode product algorithm, are presented to generate the bidiagonal matrices, truncated orthogonal bases, and core tensor respectively. The homomorphic operations of the three algorithms are carried out on the transparent servers, while the non-homomorphic operations, namely division and square root, are performed on the transparent clients. Experimental results indicate that the proposed method is promising for secure tensor decomposition for big data. [ABSTRACT FROM AUTHOR]

Telecommunication networks are evolving toward a data-center-based architecture, which includes physical network functions, virtual network functions, as well as various types of management and orchestration systems. The primary purpose of this type of heterogeneous network is to provide efficient and convenient communication services for users. However, the diverse factors of a heterogeneous network such as bandwidth, delay, and communication protocol, bring great challenges for routing recommendations. In addition, the growing volume of big data and the explosive deployment of heterogeneous networks have started a new era of applying big data technologies to implement routing recommendations. In this article, a tensor-based big-data-driven routing recommendation framework, including the edge plane, fog plane, cloud plane, and application plane, is proposed. In this framework, a tensor-based, holistic, hierarchical approach is introduced to generate efficient routing paths using tensor decomposition methods. Also, a tensor matching method including the controlling tensor, seed tensor, and orchestration tensor is employed to realize routing recommendation. Finally, a case study is used to demonstrate the key processing procedures of the proposed framework. [ABSTRACT FROM AUTHOR]

Telecommunication networks are evolving toward a data-center-based architecture, which includes physical network functions, virtual network functions, as well as various types of management and orchestration systems. The primary purpose of this type of heterogeneous network is to provide efficient and convenient communication services for users. However, the diverse factors of a heterogeneous network such as bandwidth, delay, and communication protocol, bring great challenges for routing recommendations. In addition, the growing volume of big data and the explosive deployment of heterogeneous networks have started a new era of applying big data technologies to implement routing recommendations. In this article, a tensor-based big-data-driven routing recommendation framework, including the edge plane, fog plane, cloud plane, and application plane, is proposed. In this framework, a tensor-based, holistic, hierarchical approach is introduced to generate efficient routing paths using tensor decomposition methods. Also, a tensor matching method including the controlling tensor, seed tensor, and orchestration tensor is employed to realize routing recommendation. Finally, a case study is used to demonstrate the key processing procedures of the proposed framework. [ABSTRACT FROM AUTHOR]

IoT exhibits characteristics of the presence of diverse physical sensing and actuating devices, complex wireless communication and networking technologies, as well as large-scale heterogeneous data generated in the physical and cyber worlds. The exponentially increasing volume of data places an unprecedent burden on the network infrastructure of IoT systems, where there are two key challenges: how to represent the heterogeneous IoT data as a concise and unified model, and extract the essential core data that are smaller for transmission but consist of the most valuable information; and how to globally and flexibly control the network devices, and dynamically reallocate the bandwidth to improve the communication link utilization ratio. To address the mentioned challenges, this article first transforms structured, semi-structured, and unstructured IoT data to a unified tensor model, and employs the HO-SVD approach for extraction of the high-quality core data. Then this article applies SDN technology to IoT for device management, and develops a transition tensor model for routing path recommendation. Finally, a smart home case study is investigated, which reveals that the proposed tensor-based software defined model is feasible and promising. It is strongly suggested that further study on combination of IoT with SDN technology and tensor algebra should be performed. [ABSTRACT FROM PUBLISHER]

The growing volume of network traffic and gradual deployment of SDN devices initiate a new era in which one distinguished feature is the application of big data technology to SDNs for construction of flexible, scalable, and self-managing networks. The primary purpose of this article is to develop a novel tensor-based model for efficient provisioning of QoS in software defined networks. First, a forwarding tensor model is proposed to formalize the networking functions in the data plane; then a controlling tensor model is presented for routing path recommendation in the control plane. Finally, the article introduces a transition tensor model for network traffic prediction and QoS provisioning. The three models can automatically monitor the network state, recommend routing paths and predict network traffic, respectively. A case study to recommend routing paths is investigated in the article. [ABSTRACT FROM PUBLISHER]