Tensor-Based Big Data Management Scheme for Dimensionality Reduction Problem in Smart Grid Systems: SDN Perspective

Abstract

Smart grid (SG) is an integration of traditional power grid with advanced information and communication infrastructure for bidirectional energy flow between grid and end users. A huge amount of data is being generated by various smart devices deployed in SG systems. Such a massive data generation from various smart devices in SG systems may generate issues such as-congestion, and available bandwidth on the networking infrastructure deployed between users and the grid. Hence, an efficient data transmission technique is required for providing desired QoS to the end users in this environment. Generally, the data generated by smart devices in SG has high dimensions in the form of multiple heterogeneous attributes, values of which are changed with time. The high dimensions of data may affect the performance of most of the designed solutions in this environment. Most of the existing schemes reported in the literature have complex operations for data dimensionality reduction problem which may deteriorate the performance of any implemented solution for this problem. To address these challenges, in this paper, a tensor-based big data management scheme is proposed for dimensionality reduction problem of big data generated from various smart devices. In the proposed scheme, firstly the Frobenius norm is applied on high-order tensors (used for data representation) to minimize the reconstruction error of the reduced tensors. Then, an empirical probability-based control algorithm is designed to estimate an optimal path to forward the reduced data using software-defined networks (SDN) for minimization of the load and effective bandwidth utilization on the network infrastructure. The proposed scheme minimizes the transmission delay occurred during the movement of the dimensionally reduced data between different nodes. The efficacy of the proposed scheme has been evaluated using extensive simulations carried out on the data traces using 'R' programming and Matlab. The big data traces considered for evaluation consist of more than 2 million entries (2075259) colecetd at 1 minute sampling rate having hetrogenous features such as-voltage, energy, frequency, electric signals, etc. Moreover, a comparative study for different data traces and a real SG testbed is also presented to prove the efficacy of the proposed scheme. The results obtained depict the effectiveness of the proposed scheme with respect to the parameters such as-network delay, accuracy, and throughput.

Software Defined Networks-Based Smart Grid Communication: A Comprehensive Survey

“…Thus, in order to avoid these issues, efficient data transmission schemes have been proposed in the literature. One such a scheme to forward reduced data named as empirical probability-based routing algorithm (EPCS) for SDN controller is proposed in [146]. In the proposed EPCS routing scheme, first the generated big data is reduced by applying Tensor-based data reduction method to reduce its dimensionality.…”

A Spatial-Temporal Correlation Approach for Data Reduction in Cluster-Based Sensor Networks

“…Compression [12]- [15] and aggregation [16]- [18] are two techniques aiming to reduce the amount of data routed through the network [19]. The former focus on compressing the data before transmission to the upper node in the network hierarchy and the latter filters and clean the data by removing redundant information before routing these data to the Sink station.…”

“…For instance, in the "M " matrix, x 51 1 is Nan it will be set equal to the same value as x 50 1 , and x 50 2 and x 51 2 are set equal to the same value as x 49 2 , and so on. Algorithm 1 -line (17)(18)(19)(20)(21)(22) : Afterward, the linear dependency of each pair of vectors (v i ,v j ) ∈ M is calculated using the Pearson correlation coefficient. The latter is known as the best method of measuring the association between variables of interest because it is based on the method of covariance.…”

“…Figure 12 shows the maximum memory size needed by the CH in function of the number of nodes belonging to the cluster. The maximum memory size required by the CH is 8 × M ax(N (SR max + 1 2 N + 4) + 1, 6N + 1) bytes, since the values stored in the first part of the Algorithm (1-17), could be cleared once the sensors have been matched (Algorithm 1, line [17][18][19][20][21][22][23][24][25][26][27][28].…”

Parameters and fractional factors in different settings

“…In order to overcome this problem, network experts have proposed the concept of software defined networking (SDN) in recent years (see Sahoo et al [26], Ikarashi et al [15], Salman et al [27], Satchou et al [28] and Kaur et al [16]). The most attractive feature of SDN is that it can calculate the data flow in the whole network in real time and select the path that can reach the destination as soon as possible, and thus avoid the congestion channels.…”