SmartFog: Training the Fog for the Energy-Saving Analytics of Smart-Meter Data

In this paper, we characterize the main building blocks and numerically verify the classification accuracy and energy performance of SmartFog, a distributed and virtualized networked Fog technological platform for the support for Stacked Denoising Auto-Encoder (SDAE)-based anomaly detection in data flows generated by Smart-Meters (SMs). In SmartFog, the various layers of an SDAE are pretrained at different Fog nodes, in order to distribute the overall computational efforts and, then, save energy. For this purpose, a new Adaptive Elitist Genetic Algorithm (AEGA) is “ad hoc” designed to find the optimized allocation of the SDAE layers to the Fog nodes. Interestingly, the proposed AEGA implements a (novel) mechanism that adaptively tunes the exploration and exploitation capabilities of the AEGA, in order to quickly escape the attraction basins of local minima of the underlying energy objective function and, then, speed up the convergence towards global minima. As a matter of fact, the main distinguishing feature of the resulting SmartFog paradigm is that it accomplishes the joint integration on a distributed Fog computing platform of the anomaly detection functionality and the minimization of the resulting energy consumption. The reported numerical tests support the effectiveness of the designed technological platform and point out that the attained performance improvements over some state-of-the-art competing solutions are around 5%, 68% and 30% in terms of detection accuracy, execution time and energy consumption, respectively.

Download Full-text

Edge Computing for Data Anomaly Detection of Multi-Sensors in Underground Mining

Electronics ◽

10.3390/electronics10030302 ◽

2021 ◽

Vol 10 (3) ◽

pp. 302

Author(s):

Chunde Liu ◽

Xianli Su ◽

Chuanwen Li

Keyword(s):

Energy Consumption ◽

Anomaly Detection ◽

Underground Mining ◽

Heterogeneous Data ◽

Edge Computing ◽

Sensor Nodes ◽

Detection Methods ◽

Detection Accuracy ◽

Clustering Methods ◽

Safety Warning

There is a growing interest in safety warning of underground mining due to the huge threat being faced by those working in underground mining. Data acquisition of sensors based on Internet of Things (IoT) is currently the main method, but the data anomaly detection and analysis of multi-sensors is a challenging task: firstly, the data that are collected by different sensors of underground mining are heterogeneous; secondly, real-time is required for the data anomaly detection of safety warning. Currently, there are many anomaly detection methods, such as traditional clustering methods K-means and C-means. Meanwhile, Artificial Intelligence (AI) is widely used in data analysis and prediction. However, K-means and C-means cannot directly process heterogeneous data, and AI algorithms require equipment with high computing and storage capabilities. IoT equipment of underground mining cannot perform complex calculation due to the limitation of energy consumption. Therefore, many existing methods cannot be directly used for IoT applications in underground mining. In this paper, a multi-sensors data anomaly detection method based on edge computing is proposed. Firstly, an edge computing model is designed, and according to the computing capabilities of different types of devices, anomaly detection tasks are migrated to different edge devices, which solve the problem of insufficient computing capabilities of the devices. Secondly, according to the requirements of different anomaly detection tasks, edge anomaly detection algorithms for sensor nodes and sink nodes are designed respectively. Lastly, an experimental platform is built for performance comparison analysis, and the experimental results show that the proposed algorithm has better performance in anomaly detection accuracy, delay, and energy consumption.

Download Full-text

An Energy Model Using Sleeping Algorithms for Wireless Sensor Networks under Proactive and Reactive Protocols: A Performance Evaluation

Energies ◽

10.3390/en13113024 ◽

2020 ◽

Vol 13 (11) ◽

pp. 3024 ◽

Cited By ~ 3

Author(s):

Carolina Del-Valle-Soto ◽

Ramiro Velázquez ◽

Leonardo J. Valdivia ◽

Nicola Ivan Giannoccaro ◽

Paolo Visconti

Keyword(s):

Wireless Sensor Networks ◽

Energy Consumption ◽

Sensor Networks ◽

Ad Hoc ◽

Energy Performance ◽

Wireless Sensor ◽

University Campus ◽

Everyday Objects ◽

Adaptive Clustering ◽

Dynamic Source

The continuous evolution of the Internet of Things (IoT) makes it possible to connect everyday objects to networks in order to monitor physical and environmental conditions, which is made possible due to wireless sensor networks (WSN) that enable the transfer of data. However, it has also brought about many challenges that need to be addressed, such as excess energy consumption. Accordingly, this paper presents and analyzes wireless network energy models using five different communication protocols: Ad Hoc On-Demand Distance Vector (AODV), Multi-Parent Hierarchical (MPH), Dynamic Source Routing (DSR), Low Energy Adaptive Clustering Hierarchy (LEACH) and Zigbee Tree Routing (ZTR). First, a series of metrics are defined to establish a comparison and determine which protocol exhibits the best energy consumption performance. Then, simulations are performed and the results are compared with real scenarios. The energy analysis is conducted with three proposed sleeping algorithms: Modified Sleeping Crown (MSC), Timer Sleeping Algorithm (TSA), and Local Energy Information (LEI). Thereafter, the proposed algorithms are compared by virtue of two widely used wireless technologies, namely Zigbee and WiFi. Indeed, the results suggest that Zigbee has a better energy performance than WiFi, but less redundancy in the topology links, and this study favors the analysis with the simulation of protocols with different nature. The tested scenario is implemented into a university campus to show a real network running.

Download Full-text

Impact of roof shading on building energy performance in warm & humid climatic places of India

iCRBE Procedia ◽

10.32438/icrbe.202037 ◽

2020 ◽

pp. 50-64

Author(s):

Kuladeep Kumar Sadevi ◽

Avlokita Agrawal

Keyword(s):

Energy Consumption ◽

Energy Conservation ◽

Energy Performance ◽

General Assumption ◽

Climatic Conditions ◽

Building Envelope ◽

Passive Cooling ◽

Base Case ◽

U Value ◽

The Impact

With the rise in awareness of energy efficient buildings and adoption of mandatory energy conservation codes across the globe, significant change is being observed in the way the buildings are designed. With the launch of Energy Conservation Building Code (ECBC) in India, climate responsive designs and passive cooling techniques are being explored increasingly in building designs. Of all the building envelope components, roof surface has been identified as the most significant with respect to the heat gain due to the incident solar radiation on buildings, especially in tropical climatic conditions. Since ECBC specifies stringent U-Values for roof assembly, use of insulating materials is becoming popular. Along with insulation, the shading of the roof is also observed to be an important strategy for improving thermal performance of the building, especially in Warm and humid climatic conditions. This study intends to assess the impact of roof shading on building’s energy performance in comparison to that of exposed roof with insulation. A typical office building with specific geometry and schedules has been identified as base case model for this study. This building is simulated using energy modelling software ‘Design Builder’ with base case parameters as prescribed in ECBC. Further, the same building has been simulated parametrically adjusting the amount of roof insulation and roof shading simultaneously. The overall energy consumption and the envelope performance of the top floor are extracted for analysis. The results indicate that the roof shading is an effective passive cooling strategy for both naturally ventilated and air conditioned buildings in Warm and humid climates of India. It is also observed that a fully shaded roof outperforms the insulated roof as per ECBC prescription. Provision of shading over roof reduces the annual energy consumption of building in case of both insulated and uninsulated roofs. However, the impact is higher for uninsulated roofs (U-Value of 3.933 W/m2K), being 4.18% as compared to 0.59% for insulated roofs (U-Value of 0.33 W/m2K).While the general assumption is that roof insulation helps in reducing the energy consumption in tropical buildings, it is observed to be the other way when insulation is provided with roof shading. It is due to restricted heat loss during night.

Download Full-text

Language, procedures, and the non-perceptual origin of natural number concepts

10.31234/osf.io/3q4mf ◽

2016 ◽

Author(s):

David Barner

Keyword(s):

General Framework ◽

Ad Hoc ◽

Building Blocks ◽

Number Words ◽

Linguistic Markers ◽

Logical Foundations ◽

Large Numbers ◽

Perceptual Representations ◽

Positive Integers ◽

Perceptual Systems

Perceptual representations – e.g., of objects or approximate magnitudes –are often invoked as building blocks that children combine with linguisticsymbols when they acquire the positive integers. Systems of numericalperception are either assumed to contain the logical foundations ofarithmetic innately, or to supply the basis for their induction. Here Ipropose an alternative to this general framework, and argue that theintegers are not learned from perceptual systems, but instead arise toexplain perception as part of language acquisition. Drawing oncross-linguistic data and developmental data, I show that small numbers(1-4) and large numbers (~5+) arise both historically and in individualchildren via entirely distinct mechanisms, constituting independentlearning problems, neither of which begins with perceptual building blocks.Specifically, I propose that children begin by learning small numbers(i.e., *one, two, three*) using the same logical resources that supportother linguistic markers of number (e.g., singular, plural). Several yearslater, children discover the logic of counting by inferring the logicalrelations between larger number words from their roles in blind countingprocedures, and only incidentally associate number words with perception ofapproximate magnitudes, in an *ad hoc* and highly malleable fashion.Counting provides a form of explanation for perception but is not causallyderived from perceptual systems.

Download Full-text

Probabilistic and Fuzzy based Efficient Routing Protocol for Mobile Ad Hoc Networks

Recent Advances in Computer Science and Communications ◽

10.2174/2213275912666190101115318 ◽

2020 ◽

Vol 13 (3) ◽

pp. 422-432

Author(s):

Madan Mohan Agarwal ◽

Hemraj Saini ◽

Mahesh Chandra Govil

Keyword(s):

Fuzzy Logic ◽

Energy Consumption ◽

Routing Protocol ◽

Queue Length ◽

Ad Hoc ◽

Fuzzy Controller ◽

Second Phase ◽

Path Distance ◽

Fixed Threshold ◽

Multiple Paths

Background: The performance of the network protocol depends on number of parameters like re-broadcast probability, mobility, the distance between source and destination, hop count, queue length and residual energy, etc. Objective: In this paper, a new energy efficient routing protocol IAOMDV-PF is developed based on the fixed threshold re-broadcast probability determination and best route selection using fuzzy logic from multiple routes. Methods: In the first phase, the proposed protocol determines fixed threshold rebroadcast probability. It is used for discovering multiple paths between the source and the destination. The threshold probability at each node decides the rebroadcasting of received control packets to its neighbors thereby reducing routing overheads and energy consumption. The multiple paths list received from the first phase and supply to the second phase that is the fuzzy controller selects the best path. This fuzzy controller has been named as Fuzzy Best Route Selector (FBRS). FBRS determines the best path based on function of queue length, the distance between nodes and mobility of nodes. Results: Comparative analysis of the proposed protocol named as "Improved Ad-Hoc On-demand Multiple Path Distance Vector based on Probabilistic and Fuzzy logic" (IAOMDV-PF) shows that it is more efficient in terms of overheads and energy consumption. Conclusion: The proposed protocol reduced energy consumption by about 61%, 58% and 30% with respect to FF-AOMDV, IAOMDV-F and FPAOMDV routing protocols, respectively. The proposed protocol has been simulated and analyzed by using NS-2.

Download Full-text

OutlierNets: Highly Compact Deep Autoencoder Network Architectures for On-Device Acoustic Anomaly Detection

Sensors ◽

10.3390/s21144805 ◽

2021 ◽

Vol 21 (14) ◽

pp. 4805

Author(s):

Saad Abbasi ◽

Mahmoud Famouri ◽

Mohammad Javad Shafiee ◽

Alexander Wong

Keyword(s):

Machine Learning ◽

Anomaly Detection ◽

Detection Methods ◽

Detection Accuracy ◽

Network Architectures ◽

Design Exploration ◽

Convolutional Autoencoder ◽

Acoustic Anomaly ◽

Human Operators ◽

Computational Resources

Human operators often diagnose industrial machinery via anomalous sounds. Given the new advances in the field of machine learning, automated acoustic anomaly detection can lead to reliable maintenance of machinery. However, deep learning-driven anomaly detection methods often require an extensive amount of computational resources prohibiting their deployment in factories. Here we explore a machine-driven design exploration strategy to create OutlierNets, a family of highly compact deep convolutional autoencoder network architectures featuring as few as 686 parameters, model sizes as small as 2.7 KB, and as low as 2.8 million FLOPs, with a detection accuracy matching or exceeding published architectures with as many as 4 million parameters. The architectures are deployed on an Intel Core i5 as well as a ARM Cortex A72 to assess performance on hardware that is likely to be used in industry. Experimental results on the model’s latency show that the OutlierNet architectures can achieve as much as 30x lower latency than published networks.

Download Full-text

A Novel Anomaly Behavior Detection Scheme for Mobile Ad Hoc Networks

Electronics ◽

10.3390/electronics10141635 ◽

2021 ◽

Vol 10 (14) ◽

pp. 1635

Author(s):

Neeraj Chugh ◽

Geetam Singh Tomar ◽

Robin Singh Bhadoria ◽

Neetesh Saxena

Keyword(s):

Anomaly Detection ◽

Ad Hoc Networks ◽

Mobile Ad Hoc Networks ◽

Network Performance ◽

Ad Hoc ◽

Abnormal Behavior ◽

Energy Awareness ◽

Behavior Detection ◽

Mobile Ad Hoc ◽

Hoc Networks

To sustain the security services in a Mobile Ad Hoc Networks (MANET), applications in terms of confidentially, authentication, integrity, authorization, key management, and abnormal behavior detection/anomaly detection are significant. The implementation of a sophisticated security mechanism requires a large number of network resources that degrade network performance. In addition, routing protocols designed for MANETs should be energy efficient in order to maximize network performance. In line with this view, this work proposes a new hybrid method called the data-driven zone-based routing protocol (DD-ZRP) for resource-constrained MANETs that incorporate anomaly detection schemes for security and energy awareness using Network Simulator 3. Most of the existing schemes use constant threshold values, which leads to false positive issues in the network. DD-ZRP uses a dynamic threshold to detect anomalies in MANETs. The simulation results show an improved detection ratio and performance for DD-ZRP over existing schemes; the method is substantially better than the prevailing protocols with respect to anomaly detection for security enhancement, energy efficiency, and optimization of available resources.

Download Full-text

A Fundamental Study on the Development of New Energy Performance Index in Office Buildings

Energies ◽

10.3390/en14082064 ◽

2021 ◽

Vol 14 (8) ◽

pp. 2064

Author(s):

Jin-Hee Kim ◽

Seong-Koo Son ◽

Gyeong-Seok Choi ◽

Young-Tag Kim ◽

Sung-Bum Kim ◽

...

Keyword(s):

Energy Consumption ◽

Energy Requirement ◽

Energy Performance ◽

Office Buildings ◽

Light Transmittance ◽

Wall Structure ◽

Fundamental Study ◽

Future Studies ◽

U Value ◽

The Impact

Recently, there have been significant concerns regarding excessive energy use in office buildings with a large window-to-wall ratio (WWR) because of the curtain wall structure. However, prior research has confirmed that the impact of the window area on energy consumption varies depending on building size. A newly proposed window-to-floor ratio (WFR) correlates better with energy consumption in the building. In this paper, we derived the correlation by analyzing a simulation using EnergyPlus, and the results are as follows. In the case of small buildings, the results of this study showed that the WWR and energy requirement increase proportionally, and the smaller the size is, the higher the energy sensitivity will be. However, results also confirmed that this correlation was not established for buildings approximately 3600 m2 or larger. Nevertheless, from analyzing the correlation between the WFR and the energy requirements, it could be deduced that energy required increased proportionally when the WFR was 0.1 or higher. On the other hand, the correlation between WWR, U-value, solar heat gain coefficient (SHGC), and material property values of windows had little effect on energy when the WWR was 20%, and the highest effect was seen at a WWR of 100%. Further, with an SHGC below 0.3, the energy requirement decreased with an increasing WWR, regardless of U-value. In addition, we confirmed the need for in-depth research on the impact of the windows’ U-value, SHGC, and WWR, and this will be verified through future studies. In future studies on window performance, U-value, SHGC, visible light transmittance (VLT), wall U-value as sensitivity variables, and correlation between WFR and building size will be examined.

Download Full-text

Modelling Software Architecture for Visual Simultaneous Localization and Mapping

Automation ◽

10.3390/automation2020003 ◽

2021 ◽

Vol 2 (2) ◽

pp. 48-61

Author(s):

Bhavyansh Mishra ◽

Robert Griffin ◽

Hakki Erhan Sevil

Keyword(s):

System Integration ◽

Ad Hoc ◽

Simultaneous Localization And Mapping ◽

Software Systems ◽

Model Driven ◽

Performance Improvements ◽

Software Model ◽

Localization And Mapping ◽

Stereo Cameras ◽

Core Components

Visual simultaneous localization and mapping (VSLAM) is an essential technique used in areas such as robotics and augmented reality for pose estimation and 3D mapping. Research on VSLAM using both monocular and stereo cameras has grown significantly over the last two decades. There is, therefore, a need for emphasis on a comprehensive review of the evolving architecture of such algorithms in the literature. Although VSLAM algorithm pipelines share similar mathematical backbones, their implementations are individualized and the ad hoc nature of the interfacing between different modules of VSLAM pipelines complicates code reuseability and maintenance. This paper presents a software model for core components of VSLAM implementations and interfaces that govern data flow between them while also attempting to preserve the elements that offer performance improvements over the evolution of VSLAM architectures. The framework presented in this paper employs principles from model-driven engineering (MDE), which are used extensively in the development of large and complicated software systems. The presented VSLAM framework will assist researchers in improving the performance of individual modules of VSLAM while not having to spend time on system integration of those modules into VSLAM pipelines.

Download Full-text

Random Collective Representation-Based Detector with Multiple Features for Hyperspectral Images

Remote Sensing ◽

10.3390/rs13040721 ◽

2021 ◽

Vol 13 (4) ◽

pp. 721

Author(s):

Zhongheng Li ◽

Fang He ◽

Haojie Hu ◽

Fei Wang ◽

Weizhong Yu

Keyword(s):

Anomaly Detection ◽

Hyperspectral Image ◽

Spectral Feature ◽

Collaborative Representation ◽

Detection Accuracy ◽

Spatial Features ◽

Collective Representation ◽

Detection Approach ◽

Adaptive Weight ◽

Gabor Feature

Collaborative representation-based detector (CRD), as the most representative anomaly detection method, has been widely applied in the field of hyperspectral anomaly detection (HAD). However, the sliding dual window of the original CRD introduces high computational complexity. Moreover, most HAD models only consider a single spectral or spatial feature of the hyperspectral image (HSI), which is unhelpful for improving detection accuracy. To solve these problems, in terms of speed and accuracy, we propose a novel anomaly detection approach, named Random Collective Representation-based Detector with Multiple Feature (RCRDMF). This method includes the following steps. This method first extract the different features include spectral feature, Gabor feature, extended multiattribute profile (EMAP) feature, and extended morphological profile (EMP) feature matrix from the HSI image, which enables us to improve the accuracy of HAD by combining the multiple spectral and spatial features. The ensemble and random collaborative representation detector (ERCRD) method is then applied, which can improve the anomaly detection speed. Finally, an adaptive weight approach is proposed to calculate the weight for each feature. Experimental results on six hyperspectral datasets demonstrate that the proposed approach has the superiority over accuracy and speed.

Download Full-text