Differential Evolution Optimized Fuzzy Controller for Wireless Sensor Network Energy Management

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F16%3A86100120" target="_blank" >RIV/61989100:27240/16:86100120 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/FUZZ-IEEE.2016.7737708" target="_blank" >http://dx.doi.org/10.1109/FUZZ-IEEE.2016.7737708</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/FUZZ-IEEE.2016.7737708" target="_blank" >10.1109/FUZZ-IEEE.2016.7737708</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Differential Evolution Optimized Fuzzy Controller for Wireless Sensor Network Energy Management

Popis výsledku v původním jazyce

Differential evolution was used to optimize a fuzzy energy controller for a wireless sensor node. The evolved controller was validated by simulating a small wireless sensor network. The optimization goal was to best utilize the solar energy available for harvest while preserving a backup energy reserve. Performing the highest number of operations possible while leaving the energy reserve untouched increases deployment time and reliability. The controller being optimized was a Takagi-Sugeno fuzzy controller with inputs for the state of the energy buffer and a forecast of current day solar energy available for harvest. Two types of forecasts were used: one ideal and another based on atmospheric pressure measurements. Compared to a human-created reference controller, the evolved controller collected 124.96% of the measurements across the network, while only consuming 1.07% of the energy reserve capacity using a perfect forecast with similar results using the pressure-based forecast, representing an improvement in possible network deployment duration.

Název v anglickém jazyce

Differential Evolution Optimized Fuzzy Controller for Wireless Sensor Network Energy Management

Popis výsledku anglicky

Differential evolution was used to optimize a fuzzy energy controller for a wireless sensor node. The evolved controller was validated by simulating a small wireless sensor network. The optimization goal was to best utilize the solar energy available for harvest while preserving a backup energy reserve. Performing the highest number of operations possible while leaving the energy reserve untouched increases deployment time and reliability. The controller being optimized was a Takagi-Sugeno fuzzy controller with inputs for the state of the energy buffer and a forecast of current day solar energy available for harvest. Two types of forecasts were used: one ideal and another based on atmospheric pressure measurements. Compared to a human-created reference controller, the evolved controller collected 124.96% of the measurements across the network, while only consuming 1.07% of the energy reserve capacity using a perfect forecast with similar results using the pressure-based forecast, representing an improvement in possible network deployment duration.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2016 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2016; Vancouver; Canada; 24 July 2016 through 29 July 2016

ISBN

978-1-5090-0625-0

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

352-358

Název nakladatele

Institute of Electrical and Electronics Engineers

Místo vydání

New York

Místo konání akce

Vancouver

Datum konání akce

24. 7. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000392150700049