scholarly journals Multi-Parametric Analysis of Reliability and Energy Consumption in IoT: A Deep Learning Approach

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 309 ◽  
Author(s):  
Muhammad Ateeq ◽  
Farruh Ishmanov ◽  
Muhammad Afzal ◽  
Muhammad Naeem
Keyword(s):  
Deep Learning ◽  
Energy Consumption ◽  
Ieee 802.15.4 ◽  
Performance Metrics ◽  
Optimization Problems ◽  
Gradient Boosting ◽  
Delivery Ratio ◽  
Primary Concern ◽  
Design Error ◽  
Smart Control

Small-to-medium scale smart buildings are an important part of the Internet of Things (IoT). Wireless Sensor Networks (WSNs) are the major enabler for smart control in such environments. Reliability is among the key performance requirements for many loss-sensitive IoT and WSN applications, while Energy Consumption (EC) remains a primary concern in WSN design. Error-prone links, traffic intense applications, and limited physical resources make it challenging to meet these service goals—not only that these performance metrics often conflict with one another, but also require solving optimization problems, which are intrinsically NP-hard. Correctly forecasting Packet Delivery Ratio (PDR) and EC can play a significant role in different loss-sensitive application environments. With the ever-increasing availability of performance data, data-driven techniques are becoming popular in such settings. It is observed that a number of communication parameters like transmission power, packet size, etc., influence metrics like PDR and EC in diverse ways. In this work, different regression models including linear, gradient boosting, random forest, and deep learning are used for the purpose of predicting both PDR and EC based on such communication parameters. To evaluate the performance, a public dataset of the IEEE 802.15.4 network, containing measurements against more than 48,000 combinations of parameter configurations, is used. Results are evaluated using root mean square error and it turns out that deep learning achieves up to 98% accuracy for both PDR and EC predictions. These prediction results can help configure communication parameters taking into account the performance goals.

scholarly journals Efficient Data Collection using Mobile Sink Scheme in IoT

2019 ◽  
Vol 9 (1) ◽  
pp. 1360-1371
Keyword(s):  
Big Data ◽  
Energy Consumption ◽  
Data Collection ◽  
Large Scale ◽  
Performance Metrics ◽  
Route Planning ◽  
Mobile Sink ◽  
Sensor Nodes ◽  
Delivery Ratio ◽  
Energy Hole

Wireless sensor networks (WSNs) have become increasingly important in the informative development of communication technology. The growth of Internet of Things (IoT) has increased the use of WSNs in association with large scale industrial applications. The integration of WSNs with IoT is the pillar for the creation of an inescapable smart environment. A huge volume of data is being generated every day by the deployment of WSNs in smart infrastructure. The collaboration is applicable to environmental surveillance, health surveillance, transportation surveillance and many more other fields. A huge quantity of data which is obtained in various formats from varied applications is called big data. The Energy efficient big data collection requires new techniques to gather sensor-based data which is widely and densely distributed in WSNs and spread over wider geographical areas. In view of the limited range of communication and low powered sensor nodes, data gathering in WSN is a tedious task. The energy hole is another considerable issue that requires attention for efficient handling in WSN. The concept of mobile sink has been widely accepted and exploited, since it is able to effectively alleviate the energy hole problem. Scheduling a mobile sink with energy efficiency is still a challenge in WSNs time constraint implementation due to the slow speed of the mobile sink. The paper addresses the above issues and the proposal contains four-phase data collection model; the first phase is the identification of network subgroups, which are formed due to a restricted range of communication in sensor nodes in a wide network, second is clustering which is addressed on each identified subgroup for reducing energy consumption, third is efficient route planning and fourth is based on data collection. The two time-sensitive route planning schemes are presented to build a set of trajectories which satisfy the deadline constraint and minimize the overall delay. We have evaluated the performance of our schemes through simulation and compared them with the generic enhanced expectation-maximization (EEM) mobility based scenario of data collection. Simulation results reveal that our proposed schemes give much better results as compared to the generic EEM mobility approach in terms of selected performance metrics such as energy consumption, delay, network lifetime and packet delivery ratio.

scholarly journals Genetic Optimized Location Aided Routing Protocol for VANET Based on Rectangular Estimation of Position

2020 ◽  
Vol 10 (17) ◽  
pp. 5759 ◽  
Author(s):  
Ravie Chandren Muniyandi ◽  
Faizan Qamar ◽  
Ahmed Naeem Jasim
Keyword(s):  
Energy Consumption ◽  
Routing Protocol ◽  
Network Performance ◽  
Performance Metrics ◽  
Average Energy ◽  
Search Space ◽  
Location Information ◽  
Destination Node ◽  
Delivery Ratio ◽  
Routing Overhead

Vehicle Ad-Hoc Network (VANET) is a dynamic decentralized network that consists of various wireless mobile vehicles with no individual user management. Several routing protocols can be used for VANETs, for example, the Location-Aided Routing (LAR) protocol that utilizes location information provided by the Global Positioning System (GPS) sensors. It can help to reduce the search space for the desired route—limiting the search space results in fewer route discovery messages. However, two essential aspects are ignored while applying the LAR protocol in the VANET-based environment. Firstly, the LAR does not exploit the fact that nodes in VANET do not have pure random movement. In other words, nodes in LAR predict the position of destination node by ignoring the fact that the pre-defined constraint on the destination node navigation is met. Secondly, the nodes in the conventional LAR (or simply stated as LAR) protocol use the location information of the destination node before selecting the route location, which is most likely to expire because of the fast movement of the nodes in the VANET environment. This study presents an estimation based on a heuristic approach that was developed to reject weak GPS location data and accept accurate ones. The proposed routing protocol stated as Rectangle-Aided LAR (RALAR) is based on a moving rectangular zone according to the node′s mobility model. Additionally, the proposed RALAR protocol was optimized by using the Genetic Algorithm (GA) by selecting the most suitable time-out variable. The results were compared with LAR and Kalman-Filter Aided-LAR (KALAR), the most commonly utilized protocols in VANET for performance metrics using Packet Delivery Ratio (PDR), average End-to-End Delay (E2E Delay), routing overhead and average energy consumption. The results showed that the proposed RALAR protocol achieved an improvement over the KALAR in terms of PDR of 4.7%, average E2E delay of 60%, routing overhead of 15.5%, and 10.7% of energy consumption. The results proved that the performance of the RALAR protocol had outperformed the KALAR and LAR protocol in terms of regular network performance measures in the VANET environment.

Transport Protocol Performance for Multi-Hop Transmission in Wireless Sensor Network (WSN)

2016 ◽  
pp. 587-607
Author(s):  
Farizah Yunus ◽  
Sharifah H. S. Ariffin ◽  
S. K. Syed-Yusof ◽  
Nor-Syahidatul N. Ismail ◽  
Norsheila Fisal
Keyword(s):  
Ieee 802.15.4 ◽  
Performance Metrics ◽  
Multimedia Data ◽  
Transport Layer ◽  
Wireless Sensor ◽  
Delivery Ratio ◽  
Transport Protocol ◽  
Transport Protocols ◽  
Stream Control Transmission Protocol ◽  
Transport Control

The need for reliable data delivery at the transport layer for video transmission over IEEE 802.15.4 Wireless Sensor Networks (WSNs) has attracted great attention from the research community due to the applicability of multimedia transmission for many applications. The IEEE 802.15.4 standard is designed to transmit data within a network at a low rate and a short distance. However, the characteristics of WSNs such as dense deployment, limited processing ability, memory, and power supply provide unique challenges to transport protocol designers. Additionally, multimedia applications add further challenges such as requiring large bandwidth, large memory, and high data rate. This chapter discusses the challenges and evaluates the feasibility of transmitting data over an IEEE 802.15.4 network for different transport protocols. The analysis result highlights the comparison of standard transport protocols, namely User Datagram Protocol (UDP), Transport Control Protocol (TCP), and Stream Control Transmission Protocol (SCTP). The performance metrics are analyzed in terms of the packet delivery ratio, energy consumption, and end-to-end delay. Based on the study and analysis that has been done, the standard transport protocol can be modified and improved for multimedia data transmission in WSN. As a conclusion, SCTP shows significant improvement up to 18.635% and 40.19% for delivery ratio compared to TCP and UDP, respectively.

scholarly journals Traffic Class Prioritization-Based Slotted-CSMA/CA for IEEE 802.15.4 MAC in Intra-WBANs

Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 466 ◽  
Author(s):  
Farhan Masud ◽  
Abdul Abdullah ◽  
Ayman Altameem ◽  
Gaddafi Abdul-Salaam ◽  
Farkhana Muchtar
Keyword(s):  
Energy Consumption ◽  
Packet Loss ◽  
Ieee 802.15.4 ◽  
Sensor Nodes ◽  
Delivery Ratio ◽  
Channel Access ◽  
Period Range ◽  
Packet Delivery ◽  
Delivery Delay ◽  
Traffic Class

This paper proposes an improved Traffic Class Prioritization based Carrier Sense Multiple Access/Collision Avoidance (TCP-CSMA/CA) scheme for prioritized channel access to heterogenous-natured Bio-Medical Sensor Nodes (BMSNs) for IEEE 802.15.4 Medium Access Control (MAC) in intra-Wireless Body Area Networks (WBANs). The main advantage of the scheme is to provide prioritized channel access to heterogeneous-natured BMSNs of different traffic classes with reduced packet delivery delay, packet loss, and energy consumption, and improved throughput and packet delivery ratio (PDR). The prioritized channel access is achieved by assigning a distinct, minimized and prioritized backoff period range to each traffic class in every backoff during contention. In TCP-CSMA/CA, the BMSNs are distributed among four traffic classes based on the existing patient’s data classification. The Backoff Exponent (BE) starts from 1 to remove the repetition of the backoff period range in the third, fourth, and fifth backoffs. Five moderately designed backoff period ranges are proposed to assign a distinct, minimized, and prioritized backoff period range to each traffic class in every backoff during contention. A comprehensive verification using NS-2 was carried out to determine the performance of the TCP-CSMA/CA in terms of packet delivery delay, throughput, PDR, packet loss ratio (PLR) and energy consumption. The results prove that the proposed TCP-CSMA/CA scheme performs better than the IEEE 802.15.4 based PLA-MAC, eMC-MAC, and PG-MAC as it achieves a 47% decrease in the packet delivery delay and a 63% increase in the PDR.

scholarly journals Evaluación de las topologías físicas de redes WSN para la medición de variables ambientales

2015 ◽  
Vol 3 (1) ◽  
pp. 159-165
Author(s):  
S. Saigua Carvajal ◽  
M. Villafuerte Haro ◽  
D. Ávila Pesantez ◽  
A. Arellano
Keyword(s):  
Energy Consumption ◽  
Performance Metrics ◽  
Inductive Method ◽  
Delivery Ratio ◽  
Network Simulator ◽  
Environmental Sensors ◽  
Coverage Area ◽  
Packet Delivery ◽  
Low Energy Consumption ◽  
Para Determinar

En este trabajo se presenta un estudio comparativo entre las topologías físicas que apoyan WSN con el fin de determinar la más eficaz aplicado a una red inalámbrica de sensores ambientales. La investigación se realizó mediante el apoyo del Network Simulator 2 (NS-2), que permite crear un entorno similar al real y simulado su funcionamiento, para determinar la mejor topología de un método inductivo se aplicó para evaluar los datos de NS-2 que se basaron en las métricas de rendimiento, tales como: el envío de paquetes, el consumo de energía y la cobertura. Como resultado se obtuvo que la topología física estrella es la mejor manera de aplicar una red WSN para las mediciones ambientales, que tiene una relación de Entrega de paquetes del 97,9%, el rendimiento de 0,7542 Kbps, un retraso de 0,0162 ms, un consumo de energía bajo y una mayor área de cobertura del sensor. AbstractThis paper presents a comparative study between physical topologies that support WSN in order to determine the most efficient applied to a wireless network of environmental sensors. The research was performed by the support of Network Simulator 2 (NS-2), it allows to create an environment similar to real and simulated its operation, to determine the best topology an inductive method was applied to evaluate the data from NS-2 that were based on the performance metrics such as: sending packages, energy consumption and coverage. As a result it was obtained that the star physical topology is the best to implement a WSN network for environmental measurements, that has Packet Delivery Ratio of 97,9 %, Throughput of 0,7542 Kbps, a delay of 0,0162 ms, a low energy consumption and a greater sensor coverage area.

scholarly journals Energy Consumption Analysis in WSN Based on Node Placement Strategies

2018 ◽  
Vol 7 (3.12) ◽  
pp. 531
Author(s):  
R Shanmugavalli ◽  
P Subashini
Keyword(s):  
Energy Consumption ◽  
Power Distribution ◽  
Ad Hoc ◽  
Performance Metrics ◽  
Finite Energy ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Delivery Ratio ◽  
Node Placement ◽  
Comparison Results

Wireless Sensor Networks (WSNs) is a collection of devices and sensor nodes connected with wireless network and communicate with one another via radio signals. Sensor in WSN is an autonomous (self-configuring) device used to sense the light, heat, motion, moisture and pressure etc that communicate with their neighbor nodes. Node placement is a technique that places the nodes effectively in the specified network environment. In WSN basically, wireless sensor network includes different topologies namely star, point-to-point, ring, bus, mesh and hybrid. In recent years, research has been carried out on different node placement strategies and produced different results based on its performance that includes power distribution and energy consumption of sensors. Energy consumption and network lifetime are considered to be the critical issues as the nodes are powered by the batteries which have finite energy reservoirs. In this paper, three different node placements namely Random, Uniform and Grid with respect to AODV (Ad hoc On-Demand Distance Vector) protocol is evaluated in order to analyze the energy factor during wireless communication. The performance metrics used to measure the analysis are Energy Consumption Average Jitter, Average End-to-End Delay, Average Throughput and Average Packet Delivery Ratio. The comparison results suggests that Grid node placement performs well in grid scenarios and shows best for specific performance metrics.  

Transport Protocol Performance for Multi-Hop Transmission in Wireless Sensor Network (WSN)

2014 ◽  
pp. 389-409 ◽  
Author(s):  
Farizah Yunus ◽  
Sharifah H. S. Ariffin ◽  
S. K. Syed-Yusof ◽  
Nor-Syahidatul N. Ismail ◽  
Norsheila Fisal
Keyword(s):  
Ieee 802.15.4 ◽  
Performance Metrics ◽  
Multimedia Data ◽  
Transport Layer ◽  
Wireless Sensor ◽  
Delivery Ratio ◽  
Transport Protocol ◽  
Transport Protocols ◽  
Stream Control Transmission Protocol ◽  
Transport Control

The need for reliable data delivery at the transport layer for video transmission over IEEE 802.15.4 Wireless Sensor Networks (WSNs) has attracted great attention from the research community due to the applicability of multimedia transmission for many applications. The IEEE 802.15.4 standard is designed to transmit data within a network at a low rate and a short distance. However, the characteristics of WSNs such as dense deployment, limited processing ability, memory, and power supply provide unique challenges to transport protocol designers. Additionally, multimedia applications add further challenges such as requiring large bandwidth, large memory, and high data rate. This chapter discusses the challenges and evaluates the feasibility of transmitting data over an IEEE 802.15.4 network for different transport protocols. The analysis result highlights the comparison of standard transport protocols, namely User Datagram Protocol (UDP), Transport Control Protocol (TCP), and Stream Control Transmission Protocol (SCTP). The performance metrics are analyzed in terms of the packet delivery ratio, energy consumption, and end-to-end delay. Based on the study and analysis that has been done, the standard transport protocol can be modified and improved for multimedia data transmission in WSN. As a conclusion, SCTP shows significant improvement up to 18.635% and 40.19% for delivery ratio compared to TCP and UDP, respectively.

scholarly journals MAC protocol with grouping awareness GMAC for large scale Internet-of-Things network

2021 ◽  
Vol 7 ◽  
pp. e733
Author(s):  
Abdulrahman Sameer Sadeq ◽  
Rosilah Hassan ◽  
Azana Hafizah Mohd Aman ◽  
Hasimi Sallehudin ◽  
Khalid Allehaibi ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Internet Of Things ◽  
Large Scale ◽  
Ieee 802.15.4 ◽  
Mac Protocol ◽  
Cluster Head ◽  
Delivery Ratio ◽  
Energy Aware ◽  
Medium Access ◽  
Two Stages

The development of Medium Access Control (MAC) protocols for Internet of Things should consider various aspects such as energy saving, scalability for a wide number of nodes, and grouping awareness. Although numerous protocols consider these aspects in the limited view of handling the medium access, the proposed Grouping MAC (GMAC) exploits prior knowledge of geographic node distribution in the environment and their priority levels. Such awareness enables GMAC to significantly reduce the number of collisions and prolong the network lifetime. GMAC is developed on the basis of five cycles that manage data transmission between sensors and cluster head and between cluster head and sink. These two stages of communication increase the efficiency of energy consumption for transmitting packets. In addition, GMAC contains slot decomposition and assignment based on node priority, and, therefore, is a grouping-aware protocol. Compared with standard benchmarks IEEE 802.15.4 and industrial automation standard 100.11a and user-defined grouping, GMAC protocols generate a Packet Delivery Ratio (PDR) higher than 90%, whereas the PDR of benchmark is as low as 75% in some scenarios and 30% in others. In addition, the GMAC accomplishes lower end-to-end (e2e) delay than the least e2e delay of IEEE with a difference of 3 s. Regarding energy consumption, the consumed energy is 28.1 W/h for GMAC-IEEE Energy Aware (EA) and GMAC-IEEE, which is less than that for IEEE 802.15.4 (578 W/h) in certain scenarios.

scholarly journals Development of Hierarchical Clustering Protocols for Wireless Sensor Networks

2020 ◽  
Vol 8 (5) ◽  
pp. 758-761
Keyword(s):  
Wireless Sensor Networks ◽  
Energy Consumption ◽  
Sensor Networks ◽  
Routing Protocols ◽  
Performance Metrics ◽  
Primary Objective ◽  
Wireless Sensor ◽  
Delivery Ratio ◽  
Network Simulator ◽  
The Everyday

Wireless Sensor Networks (WSN) has turned out to be raising field in research and significant part in the everyday universe of data computing. WSN are initially conveyed in military, overwhelming mechanical applications and, later reached out to the lighter applications, for example, shopper WSN applications. The primary objective of this paper is to diminish energy consumption in wireless sensor networks utilizing energy productive routing protocols (i.e., Modified HEED). To test the presentation of proposed routing protocols through simulations utilizing Network Simulator 2 (NS2.35) and to contrast and existing routing protocols dependent on performance metrics, for example, packet delivery ratio, throughput, energy consumption, overhead and start to finish delay

scholarly journals Short and Very Short Term Firm-level Load Forecasting for Warehouses: A Comparison of Machine Learning and Deep Learning Models

2022 ◽  
Author(s):  
Andrea Maria N. C. Ribeiro ◽  
Pedro Rafael X. do Carmo ◽  
Patricia Takako Endo ◽  
Pierangelo Rosati ◽  
Theo Lynn
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Energy Consumption ◽  
Load Forecasting ◽  
Energy Performance ◽  
Gradient Boosting ◽  
Support Vector ◽  
Learning Models ◽  
Short Term ◽  
Extreme Gradient Boosting

Commercial buildings are a significant consumer of energy worldwide. Logistics facilities, and specifically warehouses, are a common building type yet under-researched in the demand-side energy forecasting literature. Warehouses have an idiosyncratic profile when compared to other commercial and industrial buildings with a significant reliance on a small number of energy systems. As such, warehouse owners and operators are increasingly entering in to energy performance contracts with energy service companies (ESCOs) to minimise environmental impact, reduce costs, and improve competitiveness. ESCOs and warehouse owners and operators require accurate forecasts of their energy consumption so that precautionary and mitigation measures can be taken. This paper explores the performance of three machine learning models (Support Vector Regression (SVR), Random Forest, and Extreme Gradient Boosting (XGBoost)), three deep learning models (Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)), and a classical time series model, Autoregressive Integrated Moving Average (ARIMA) for predicting daily energy consumption. The dataset comprises 8,040 records generated over an 11-month period from January to November 2020 from a non-refrigerated logistics facility located in Ireland. The grid search method was used to identify the best configurations for each model. The proposed XGBoost models outperform other models for both very short load forecasting (VSTLF) and short term load forecasting (STLF); the ARIMA model performed the worst.

Sign in / Sign up

Export Citation Format

Share Document