Latency and Energy-Awareness in Data Stream Processing for Edge Based IoT Systems

Oliveira, Egberto A. R. de; Rocha, Atslands Rego da; Mattoso, Marta; Delicato, Flávia Coimbra

doi:10.1007/s10723-022-09611-4

Cited by 7 publications

(4 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the economy continues to develop, the era of Internet of Everything has arrived, which can provide some help to change the human lifestyle [1]. What is the Internet of Things?…”

Section: Introductionmentioning

confidence: 99%

Edge Node Aware Adaptive Data Processing Method for Ubiquitous NB-IoT

Sun

Diao

2022

Journal of Sensors

View full text Add to dashboard Cite

Nowadays, we have entered the golden age of economic development, and the Internet of Things (IoT) has also ushered in the opportunity of development, and the rapid development of IoT is also beneficial to drive the economy forward continuously. Therefore, the research on IoT is very meaningful and meets the contemporary development needs and greatly facilitates people’s daily life through the interconnection of all things. In today’s era of massive data, all kinds of data are complicated and messy, and if the large amount of data obtained is not properly classified and processed, the major problem will be that a pile of disordered and messy data is generated, and it is impossible to find the corresponding useful, engineering value, and regular data among them, and then, such data can only be discarded. Such a simple and brutal way of data processing is not only a waste of data resources but also may inadvertently throw away important, confidential, and private data information. If such data is carelessly discarded, the consequences will be incalculable, because such data information is likely to be used, processed, and disseminated by unscrupulous elements, which will eventually result in the following consequences: for individuals, it is equivalent to making their privacy public, which will seriously affect all aspects of life; for enterprises, if confidential data information is disseminated, then it will bring unpredictable losses to the enterprise. The adaptive data processing method for edge node sensing in ubiquitous NB-IoT can make the data generated from NB-IoT modules in ubiquitous IoT have practical engineering application value after processing, so the data source of this paper is the IoT data generated from NB-IoT communication modules in ubiquitous network (called NB-IoT dataset in this paper). The experimental results show that the accuracy of the adaptive data classification achieved by these two algorithms reaches about 75%, which provides some help to improve the efficiency of data utilization.

show abstract

“…As the economy continues to develop, the era of Internet of Everything has arrived, which can provide some help to change the human lifestyle [1]. What is the Internet of Things?…”

Section: Introductionmentioning

confidence: 99%

Edge Node Aware Adaptive Data Processing Method for Ubiquitous NB-IoT

Sun

Diao

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…In Fog/Edge, stream processing can exploit adaptive sampling to reduce the network and hence the energy consumption of battery-based edge devices [35], [12]. More generally, approximation is exploited in Fog/Edge environments to optimize edge tasks execution [36], [16].…”

Section: Uc1mentioning

confidence: 99%

“…The variability and heterogeneity in Fog Computing and different QoS necessities require combining the two techniques to optimize resource utilization and application performance. There are various examples of the usage of elastic approximation computing for stream processing [3] and fog computing [12]. However, most works focus on a single one of the two techniques [13].…”

Section: Introductionmentioning

confidence: 99%

TransScale: Combined-Approach Elasticity for Stream Processing in Fog Environments

Pagliari,

Pierre

2023

2023 11th IEEE International Conference on Mobile Cloud Computing, Services, and Engineering (MobileCloud)

View full text Add to dashboard Cite

Real-time data processing is a standard requirement in Fog Computing. Dynamically adapting data stream processing frameworks is an essential functionality to handle time-varying workloads efficiently and to optimize resource consumption. However, horizontal scaling alone, by adapting the parallelism and number of provisioned nodes, faces limits when available compute resources are scarce. We propose TransScale, a combined-approach auto-scaler that combines horizontal scaling to approximation computing, controlling it through transprecision computing. We design TransScale to make the approximation method transparent to the system and support context-specific requirements through QoS-driven re-configuration decisions. Based on the policy's objective, we show that it can reduce re-configuration occurrences, optimize resource utilization and sustain high workloads in resource-constrained environments.

show abstract

“…It also discussed a LE-STREAM framework for processing IoT data streams that uses edge computing to bring data processing closer to the data sources, reducing latency. Adaptive sampling in combination with a data prediction model reduces device energy consumption without compromising data accuracy (8) . A System-on-Chip (SoC)-based three-level edge computing architecture for low power consumption https://www.indjst.org/ and extensible on-board computation had offered based on the results of studies performed on the simulation hardware of the Luojia3 satellite using simulation data and frame array sensor data (9) .…”

Section: Introductionmentioning

confidence: 99%

Analysis of Latency and Bandwidth for Edge-Based Short Length in Edge Computing Devices for Short Ranges and Long Ranges

Bharadwaj¹,

Barman²,

Saha³

2023

IJST

View full text Add to dashboard Cite

Objectives:To propose an IoT-based design in an edge computing environment for short ranges and long ranges of real-time data streaming to the client. Methods: Multimedia data is used in this work. Here we have used Opnet for creating a physical architecture and to analyze the quality-of-service parameters like delay, throughput, and jitter for different Ad-hoc routing protocols like Ad-hoc on-Demand Distance vector routing, Dynamic source routing, Optimized Link State Routing, Temporally ordered routing algorithm and Geographic Routing Protocol for edge-based short length in edge computing devices for short ranges and long ranges. Riverbed academic modeler (formerly known as OPNET) has been used as a simulation tool to analyze the latency and bandwidth for edge computing under the pre-configured set-up. The simulation is accomplished using MATLAB to find the fluctuation of the delay, throughput, and jitter for edge-based short length in edge computing devices for short ranges and long ranges by applying the datasets in the edge computing environment. Findings: The results we got through simulations from different routing protocols like AODV, DSR, OLSR, TORA, and GRP of delay, throughput, and jitter shows that the proposed system strengthens the existing cloud-based system, leading to greater QoS.AODV surpasses all other protocols with a minimal delay of 0.24 msec and OLSR achieves the best performance with an average delay of 0.3 msec, better throughput of 180 bits/sec, and a load of 1410 bits/sec for the three key parameters of latency, throughput, and jitter. Novelty: The study compares the performance of different routing protocols and shows a reduction in the delay of 0.24 msec with respect to time as compared to other existing works. The proposed research is designed for a media streaming application based on the mobile nodes regarded as an edge devices for https://www.indjst.org/ different QoS parameters like throughput, delay, and load, and by comparing the existing work we found that AODV outperforms all other routing protocols with a minimum delay.

show abstract

Latency and Energy-Awareness in Data Stream Processing for Edge Based IoT Systems

Cited by 7 publications

References 53 publications

Edge Node Aware Adaptive Data Processing Method for Ubiquitous NB-IoT

Edge Node Aware Adaptive Data Processing Method for Ubiquitous NB-IoT

TransScale: Combined-Approach Elasticity for Stream Processing in Fog Environments

Analysis of Latency and Bandwidth for Edge-Based Short Length in Edge Computing Devices for Short Ranges and Long Ranges

Contact Info

Product

Resources

About