Kea: A Computation Offloading System for Smartphone Sensor Data

Roshan Bharath Das, Nicolae Vladimir Bozdog, Marc X. Makkes, Henri Bal

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Nowadays smartphones are equipped with many sensors which applications can continuously invoke to acquire real-time sensor information, such as GPS tracking. Due to the resource-constrained nature of the smartphones, it is often beneficial if the processing of the sensor data is offloaded to a remote resource. However, the decision to offload the computation depends on a multitude of factors such as the hardware capabilities of the phone, the communication energy and latency and the characteristics of the stream computations, e.g., window size, sensor frequency and operational complexity.In this paper we introduce Kea, a profiling-based computation offloading system that automatically decides whether offloading is beneficial for smartphones. The decision making is based on two criteria: the power consumption of the application and the elapsed time for processing the sensor data. Our evaluation results show that unexpected factors such as CPU frequency scaling and the network state also influence the decision-making process. In addition, we show that Kea's profiling overhead is negligible.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE 9th International Conference on Cloud Computing Technology and Science, CloudCom 2017
PublisherIEEE Computer Society
Pages9-16
Number of pages8
ISBN (Electronic)9781538606926
DOIs
Publication statusPublished - 27 Dec 2017
Event9th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2017 - Hong Kong, Hong Kong
Duration: 11 Dec 201714 Dec 2017

Publication series

NameProceedings of the International Conference on Cloud Computing Technology and Science, CloudCom
Volume2017-December
ISSN (Print)2330-2194
ISSN (Electronic)2330-2186

Conference

Conference9th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2017
CountryHong Kong
CityHong Kong
Period11/12/1714/12/17

Fingerprint

Smartphones
Sensor
Sensors
Profiling
Decision making
Decision Making
Resources
Processing
Power Consumption
Program processors
Latency
Global positioning system
Electric power utilization
Hardware
Scaling
Real-time
Communication
Evaluation
Energy

Keywords

  • Context-aware computing
  • Mobile cloud computing
  • Mobile phone sensing
  • Models computation offloading

Cite this

Das, R. B., Bozdog, N. V., Makkes, M. X., & Bal, H. (2017). Kea: A Computation Offloading System for Smartphone Sensor Data. In Proceedings - 2017 IEEE 9th International Conference on Cloud Computing Technology and Science, CloudCom 2017 (pp. 9-16). (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom; Vol. 2017-December). IEEE Computer Society. https://doi.org/10.1109/CloudCom.2017.33
Das, Roshan Bharath ; Bozdog, Nicolae Vladimir ; Makkes, Marc X. ; Bal, Henri. / Kea : A Computation Offloading System for Smartphone Sensor Data. Proceedings - 2017 IEEE 9th International Conference on Cloud Computing Technology and Science, CloudCom 2017. IEEE Computer Society, 2017. pp. 9-16 (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom).
@inproceedings{0b549c8c9a1d4dfeaa9712a665c7e7fb,
title = "Kea: A Computation Offloading System for Smartphone Sensor Data",
abstract = "Nowadays smartphones are equipped with many sensors which applications can continuously invoke to acquire real-time sensor information, such as GPS tracking. Due to the resource-constrained nature of the smartphones, it is often beneficial if the processing of the sensor data is offloaded to a remote resource. However, the decision to offload the computation depends on a multitude of factors such as the hardware capabilities of the phone, the communication energy and latency and the characteristics of the stream computations, e.g., window size, sensor frequency and operational complexity.In this paper we introduce Kea, a profiling-based computation offloading system that automatically decides whether offloading is beneficial for smartphones. The decision making is based on two criteria: the power consumption of the application and the elapsed time for processing the sensor data. Our evaluation results show that unexpected factors such as CPU frequency scaling and the network state also influence the decision-making process. In addition, we show that Kea's profiling overhead is negligible.",
keywords = "Context-aware computing, Mobile cloud computing, Mobile phone sensing, Models computation offloading",
author = "Das, {Roshan Bharath} and Bozdog, {Nicolae Vladimir} and Makkes, {Marc X.} and Henri Bal",
year = "2017",
month = "12",
day = "27",
doi = "10.1109/CloudCom.2017.33",
language = "English",
series = "Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom",
publisher = "IEEE Computer Society",
pages = "9--16",
booktitle = "Proceedings - 2017 IEEE 9th International Conference on Cloud Computing Technology and Science, CloudCom 2017",
address = "United States",

}

Das, RB, Bozdog, NV, Makkes, MX & Bal, H 2017, Kea: A Computation Offloading System for Smartphone Sensor Data. in Proceedings - 2017 IEEE 9th International Conference on Cloud Computing Technology and Science, CloudCom 2017. Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom, vol. 2017-December, IEEE Computer Society, pp. 9-16, 9th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2017, Hong Kong, Hong Kong, 11/12/17. https://doi.org/10.1109/CloudCom.2017.33

Kea : A Computation Offloading System for Smartphone Sensor Data. / Das, Roshan Bharath; Bozdog, Nicolae Vladimir; Makkes, Marc X.; Bal, Henri.

Proceedings - 2017 IEEE 9th International Conference on Cloud Computing Technology and Science, CloudCom 2017. IEEE Computer Society, 2017. p. 9-16 (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom; Vol. 2017-December).

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Kea

T2 - A Computation Offloading System for Smartphone Sensor Data

AU - Das, Roshan Bharath

AU - Bozdog, Nicolae Vladimir

AU - Makkes, Marc X.

AU - Bal, Henri

PY - 2017/12/27

Y1 - 2017/12/27

N2 - Nowadays smartphones are equipped with many sensors which applications can continuously invoke to acquire real-time sensor information, such as GPS tracking. Due to the resource-constrained nature of the smartphones, it is often beneficial if the processing of the sensor data is offloaded to a remote resource. However, the decision to offload the computation depends on a multitude of factors such as the hardware capabilities of the phone, the communication energy and latency and the characteristics of the stream computations, e.g., window size, sensor frequency and operational complexity.In this paper we introduce Kea, a profiling-based computation offloading system that automatically decides whether offloading is beneficial for smartphones. The decision making is based on two criteria: the power consumption of the application and the elapsed time for processing the sensor data. Our evaluation results show that unexpected factors such as CPU frequency scaling and the network state also influence the decision-making process. In addition, we show that Kea's profiling overhead is negligible.

AB - Nowadays smartphones are equipped with many sensors which applications can continuously invoke to acquire real-time sensor information, such as GPS tracking. Due to the resource-constrained nature of the smartphones, it is often beneficial if the processing of the sensor data is offloaded to a remote resource. However, the decision to offload the computation depends on a multitude of factors such as the hardware capabilities of the phone, the communication energy and latency and the characteristics of the stream computations, e.g., window size, sensor frequency and operational complexity.In this paper we introduce Kea, a profiling-based computation offloading system that automatically decides whether offloading is beneficial for smartphones. The decision making is based on two criteria: the power consumption of the application and the elapsed time for processing the sensor data. Our evaluation results show that unexpected factors such as CPU frequency scaling and the network state also influence the decision-making process. In addition, we show that Kea's profiling overhead is negligible.

KW - Context-aware computing

KW - Mobile cloud computing

KW - Mobile phone sensing

KW - Models computation offloading

UR - http://www.scopus.com/inward/record.url?scp=85044251630&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044251630&partnerID=8YFLogxK

U2 - 10.1109/CloudCom.2017.33

DO - 10.1109/CloudCom.2017.33

M3 - Conference contribution

T3 - Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom

SP - 9

EP - 16

BT - Proceedings - 2017 IEEE 9th International Conference on Cloud Computing Technology and Science, CloudCom 2017

PB - IEEE Computer Society

ER -

Das RB, Bozdog NV, Makkes MX, Bal H. Kea: A Computation Offloading System for Smartphone Sensor Data. In Proceedings - 2017 IEEE 9th International Conference on Cloud Computing Technology and Science, CloudCom 2017. IEEE Computer Society. 2017. p. 9-16. (Proceedings of the International Conference on Cloud Computing Technology and Science, CloudCom). https://doi.org/10.1109/CloudCom.2017.33