Data-driven optimizations in IoT: a new frontier of challenges and opportunities
TL;DR: IoT data driven unique communication approaches and optimization techniques to reduce the data handling footprint, leading to communication bandwidth, cloud storage, and energy saving, without compromising the service quality are presented.
Abstract: Internet of Things (IoT) has gained tremendous popularity with the recent fast-paced technological advances in embedded programmable electronic and electro-mechanical systems, miniaturization, and their networking ability. IoT is expected to change the way of human activities by extensively networked monitoring, automation, and control. However, widespread application of IoT is associated with numerous challenges on communication and storage requirements, energy sustainability, and security. Also, IoT data traffic as well as the service quality requirements are application-specific. Through a few practical example cases, this article presents IoT data driven unique communication approaches and optimization techniques to reduce the data handling footprint, leading to communication bandwidth, cloud storage, and energy saving, without compromising the service quality. Subsequently, it discusses newer challenges that are needed to be tackled, to make the IoT applications practically viable for their wide-ranging adoption.
Citations
More filters
TL;DR: Performance studies indicate that compared to the state-of-the-art, the proposed technique is able to achieve impressive bandwidth saving for transmission of data over communication network without compromising faithful reconstruction of data at the receiver.
Abstract: Recent advances in electric metering infrastructure have given rise to the generation of gigantic chunks of data. Transmission of all of these data certainly poses a significant challenge in bandwidth and storage constrained Internet of Things (IoT), where smart meters act as sensors. In this work, a novel multivariate data compression scheme is proposed for smart metering IoT. The proposed algorithm exploits the cross correlation between different variables sensed by smart meters to reduce the dimension of data. Subsequently, sparsity in each of the decorrelated streams is utilized for temporal compression. To examine the quality of compression, the multivariate data is characterized using multivariate normal–autoregressive integrated moving average modeling before compression as well as after reconstruction of the compressed data. Our performance studies indicate that compared to the state-of-the-art, the proposed technique is able to achieve impressive bandwidth saving for transmission of data over communication network without compromising faithful reconstruction of data at the receiver. The proposed algorithm is tested in a real smart metering setup and its time complexity is also analyzed.
32 citations
Cites background from "Data-driven optimizations in IoT: a..."
...Practical examples given in [2] and [3] show how a hundred million of such meters recording 5 kB of data once in 15 min can collectively generate as high as 2920 TB in 1 year....
[...]
Journal Article•
TL;DR: In this article, a Deep Learning based Locational Detection technique is proposed to continuously recognize the specific areas of FDIA, which is based on the development area solver gap happiness is a False Data Detector (FDD) that incorporates a Convolutional Neural Network (CNN).
Abstract: The smart grid replaces the traditional power structure with information inventiveness that contributes to a new physical structure. In such a field, malicious information injection can potentially lead to extreme results. Incorrect, FDI attacks will never be identified by typical residual techniques for false data identification. Most of the work on the detection of FDI attacks is based on the linearized power system model DC and does not detect attacks from the AC model. Also, the overwhelming majority of current FDIA recognition approaches focus on FDIA, whilst significant injection location data cannot be achieved. Building on the continuous developments in deep learning, we propose a Deep Learning based Locational Detection technique to continuously recognize the specific areas of FDIA. In the development area solver gap happiness is a False Data Detector (FDD) that incorporates a Convolutional Neural Network (CNN). The FDD is established enough to catch the fake information. As a multi-label classifier, the following CNN is utilized to evaluate the irregularity and cooccurrence dependency of power flow calculations due to the possible attacks. There are no earlier statistical assumptions in the architecture proposed, as they are "model-free." It is also "cost-accommodating" since it does not alter the current FDD framework and it is only several microseconds on a household computer during the identification procedure. We have shown that ANN-MLP, SVM-RBF, and CNN can conduct locational detection under different noise and attack circumstances through broad experience in IEEE 14, 30, 57, and 118 bus systems. Moreover, the multi-name classification method used successfully improves the precision of the present identification.
10 citations
TL;DR: A novel edge intelligence-based data-driven priority-aware sensing and transmission framework that saves up to 41% energy and 32% bandwidth with 68% data accuracy compared to the existing competitive frameworks for non-real-time systems.
Abstract: Owing to the limited storage capacity, battery-powered wireless sensor nodes often suffer from energy sustainability. To optimize the energy consumption of a multi-parameter sensor hub, a novel edge intelligence-based data-driven priority-aware sensing and transmission framework is proposed in this paper. The proposed framework jointly exploits the cross-correlation among the sensing parameters and temporal correlation of the individual sensing signals to find an optimal active sensor set and optimal sampling instants of the sensors in the next measurement cycle. The length of measurement cycle is dynamically decided based on the change in cross-correlation among the parameters and the system state. A discounted upper confidence bound algorithm-based optimization function is formulated to find the optimal active sensor set by solving the trade-off among cross-correlation, energy consumption, and length of measurement cycle. The proposed framework uses Gaussian process regressor-based prediction models to estimate the temporal and cross-correlated parameters of the active and inactive sensor set, respectively. The sampling interval of each active sensor is dynamically adapted based on the temporal prediction error. Extensive simulations are performed on air pollution monitoring dataset to validate the efficacy of the proposed framework in both real-time and non-real-time applications. The proposed algorithm saves up to 41% energy and 32% bandwidth with 68% data accuracy compared to the existing competitive frameworks for non-real-time systems. The proposed framework also identifies the time-critical sensing scenarios with 98% accuracy.
6 citations
TL;DR: Novel channel prediction frameworks using stochastic modeling as well as data-driven learning of channel variability are proposed, which are complemented with an adaptive channel coding scheme to increase the transmission reliability of time-critical grid monitoring data over a wireless channel.
Abstract: This article presents a new paradigm for channel dynamics adaptive transmission of intermittent data in smart grid IoT communication networks, wherein novel channel prediction frameworks using stochastic modeling as well as data-driven learning of channel variability are proposed. A probing-based transmission is also proposed as a benchmark. These prediction frameworks are complemented with an adaptive channel coding scheme to increase the transmission reliability of time-critical grid monitoring data over a wireless channel. Through analyzing the prediction and packet loss performance at varying SNR and fading conditions, it is noted that the stochastic modeling framework is efficient when the fading correlation in the channel is high while the learning-based approach is more adaptive to channel dynamics as the correlation reduces. The proposed frameworks are easily implementable on low-cost end nodes, owing to the optimal selection of parameters for low runtime complexity. When compared to probing-based data transmission for a given fading in the channel, the packet loss probability of the learning-based transmission closely matches while with stochastic model loss probability is found to be 12.3% higher. However, their respective signaling overheads are 38% and 98% lower with respect to the probing-based approach, which is a significant gain at the cost of marginally additional computation complexity.
4 citations
Cites background from "Data-driven optimizations in IoT: a..."
..., transmission energy, 67 communication bandwidth, and cloud storage space) is of 68 contemporary research interest [6]–[8]....
[...]
TL;DR: A simulation platform based on OMNeT++ to make up for the shortcomings of current WSN simulation platforms, improve the simulation capability of WSN security protocols, and provide a new technical means for designing and verifying security protocols is developed.
Abstract: In this paper, we use cognitive computing to build a WSN security threat analysis model using a data-driven approach and conduct an in-depth and systematic study. In this paper, we develop a simulation platform (OMNeT++-based WSN Security Protocol Simulation Platform (WSPSim)) based on OMNeT++ to make up for the shortcomings of current WSN simulation platforms, improve the simulation capability of WSN security protocols, and provide a new technical means for designing and verifying security protocols. The WSPSim simulation platform is used to simulate and analyze typical WSN protocols and verify the effectiveness of the platform. In this paper, we mainly analyze the node malicious behavior by listening and judging the communication behavior of the nodes, and the current trust assessment is given by the security management nodes. When the security management node is rotated, its stored trust value is used as historical trust assessment and current trust assessment together to participate in the integrated trust value calculation, which improves the reliability of node trust assessment; to increase the security and reliability of the management node, a trust value factor and residual energy factor are introduced in the security management node election in the paper. According to the time of management node election, the weights of both are changed to optimize the election. Using the WSPSim simulation platform, a typical WSN protocol is simulated and analyzed to verify the effectiveness of the platform. In this paper, the simulation results of the LEACH protocol with an MD5 hash algorithm and trust evaluation mechanism and typical LEACH protocol as simulation samples are compared; i.e., the correctness of the simulation platform is verified, and it is shown that improving the security of the protocol and enhancing the security and energy efficiency of wireless sensor networks provide an effective solution.
2 citations
References
More filters
11 Nov 2013
TL;DR: An extensive deployment in a three storey home in Delhi, spanning 73 days from May-August 2013, measuring electrical, water and ambient parameters is undertaken, which further validates the common considerations from similar residential deployments, discussed previously in the literature.
Abstract: Residential buildings contribute significantly to the overall energy usage across the world. Real deployments, and collected data thereof, play a critical role in providing insights into home energy consumption and occupant behavior. Existing datasets from real residential deployments are all from the developed countries. Developing countries, such as India, present unique opportunities to evaluate the scalability of existing research in diverse settings. Building upon more than a year of experience in sensor network deployments, we undertake an extensive deployment in a three storey home in Delhi, spanning 73 days from May-August 2013, measuring electrical, water and ambient parameters. We used 33 sensors across the home, measuring these parameters, collecting a total of approx. 400 MB of data daily. We discuss the architectural implications on the deployment systems that can be used for monitoring and control in the context of developing countries. Addressing the unreliability of electrical grid and internet in such settings, we present Sense Local-store Upload architecture for robust data collection. While providing several unique aspects, our deployment further validates the common considerations from similar residential deployments, discussed previously in the literature. We also release our collected data- Indian data for Ambient Water and Electricity Sensing (iAWE), for public use.
161 citations
TL;DR: The proposed methodology for lossy data compression in smart distribution systems using the singular value decomposition technique is capable of significantly reducing the volume of data to be transmitted through the communications network and accurately reconstructing the original data.
Abstract: Electrical distribution systems have been experiencing many changes in recent times. Advances in metering system infrastructure and the deployment of a large number of smart meters in the grid will produce a big volume of data that will be required for many different applications. Despite the significant investments taking place in the communications infrastructure, this remains a bottleneck for the implementation of some applications. This paper presents a methodology for lossy data compression in smart distribution systems using the singular value decomposition technique. The proposed method is capable of significantly reducing the volume of data to be transmitted through the communications network and accurately reconstructing the original data. These features are illustrated by results from tests carried out using real data collected from metering devices at many different substations.
140 citations
TL;DR: The K-SVD sparse representation technique, which includes two phases (dictionary learning and sparse coding), is used to decompose load profiles into linear combinations of several partial usage patterns (PUPs), which allows the smart meter data to be compressed and hidden electricity consumption patterns to be extracted.
Abstract: Smart meters play vital roles in the aspects of the management and operation of smart grids such as demand response, energy efficiency improvement, and electricity pricing. Massive amounts of data are being collected owing to the popularity of smart meters. Two main issues should be addressed in this context. One is the communication and storage of big data from smart meters at reduced cost. The other is the effective extraction of useful information from this massive dataset. In this paper, the K-SVD sparse representation technique, which includes two phases (dictionary learning and sparse coding), is used to decompose load profiles into linear combinations of several partial usage patterns (PUPs), which allows the smart meter data to be compressed and hidden electricity consumption patterns to be extracted. Then, a linear support vector machine (SVM) based method is used to classify the load profiles into two groups, residential customers and small and medium-sized enterprises (SMEs), based on the extracted patterns. Comprehensive comparisons with the results of k-means clustering, the discrete wavelet transform (DWT), principal component analysis (PCA), and piecewise aggregate approximation (PAA) are conducted on real datasets in Ireland. The results show that our proposed technique outperforms these methods in both compression ratio and classification accuracy.
101 citations
TL;DR: This work proposes a compression approach for load profile data that outperforms transmission encodings that are currently used for electricity metering by an order of magnitude and allows for resumability with very low overhead on error-prone transmission lines.
Abstract: We propose a compression approach for load profile data, which addresses practical requirements of smart metering. By providing linear time complexity with respect to the input data size, our compression approach is suitable for low-complexity encoding and decoding for storage and transmission of load profile data in smart grids. Furthermore, it allows for resumability with very low overhead on error-prone transmission lines, which is an important feature not available for standard time series compression schemes. In terms of compression efficiency, our approach outperforms transmission encodings that are currently used for electricity metering by an order of magnitude.
94 citations
TL;DR: The proposed method on data reduction, which is an “event oriented auto-adjustable sliding window method,” implements a curve fitting algorithm with a weighted exponential function-based variable sliding window accommodating different event types that works efficiently with minimal loss in data information especially around detected events.
Abstract: The aim of this paper is to present methods on real-time event detection and data archival reduction based on synchrophasor data produced by phasor measurement unit (PMU). Event detection is performed with principal component analysis and a second order difference method with a hierarchical framework for the event notification strategy on a small-scale microgrid. Compared with the existing methods, the proposed method is more practical and efficient in the combined use of event detection and data archival reduction. The proposed method on data reduction, which is an “event oriented auto-adjustable sliding window method,” implements a curve fitting algorithm with a weighted exponential function-based variable sliding window accommodating different event types. It works efficiently with minimal loss in data information especially around detected events. The performance of the proposed method is shown on actual PMU data from the Illinois Institute of Technology campus microgrid, thus successfully improving the situational awareness of the campus power system network.
81 citations