Simulation of time series wind speed at an international airport

Ronald Wesonga, Fabian Nabugoomu, Faisal Ababneh, Abraham Owino

Research output: Contribution to journalArticle

Abstract

The sporadic and unstable nature of wind speed renders it very difficult to predict accurately to serve various decisions, such as safety in the air traffic flow and reliable power generation system. In this study we assessed the autoregressive integrated moving average (ARIMA) and artificial neural network (ANN) models on the wind speed time series problem. Data on wind speed and minimum and maximum temperatures were evaluated. Wind speed was established to follow a time series that fluctuated around ARIMA (0,1,1) and ARIMA (1,1,1). The optimal ANN model was established at 10 hidden neurons. The performance indices considered all indicated that the ANN wind speed model was superior to the ARIMA model. Wind speed prediction accuracy can be improved to secure the safety of air traffic flow as well support the implementation of a reliable and secure power generation system at the airport.

Original languageEnglish
JournalSimulation
DOIs
Publication statusAccepted/In press - Jan 1 2018

Fingerprint

Wind Speed
Airports
Time series
Moving Average
Artificial Neural Network
Simulation
Neural networks
Traffic Flow
Neural Network Model
Power generation
Safety
Moving Average Model
Integrated Model
Performance Index
Air
Neurons
Neuron
Unstable
Predict
Prediction

Keywords

  • artificial neural network
  • autoregressive integrated moving average
  • model
  • statistics
  • Wind speed

ASJC Scopus subject areas

  • Software
  • Modelling and Simulation
  • Computer Graphics and Computer-Aided Design

Cite this

Simulation of time series wind speed at an international airport. / Wesonga, Ronald; Nabugoomu, Fabian; Ababneh, Faisal; Owino, Abraham.

In: Simulation, 01.01.2018.

Research output: Contribution to journalArticle

@article{9b2aef0b6a6d474394095485030cf362,
title = "Simulation of time series wind speed at an international airport",
abstract = "The sporadic and unstable nature of wind speed renders it very difficult to predict accurately to serve various decisions, such as safety in the air traffic flow and reliable power generation system. In this study we assessed the autoregressive integrated moving average (ARIMA) and artificial neural network (ANN) models on the wind speed time series problem. Data on wind speed and minimum and maximum temperatures were evaluated. Wind speed was established to follow a time series that fluctuated around ARIMA (0,1,1) and ARIMA (1,1,1). The optimal ANN model was established at 10 hidden neurons. The performance indices considered all indicated that the ANN wind speed model was superior to the ARIMA model. Wind speed prediction accuracy can be improved to secure the safety of air traffic flow as well support the implementation of a reliable and secure power generation system at the airport.",
keywords = "artificial neural network, autoregressive integrated moving average, model, statistics, Wind speed",
author = "Ronald Wesonga and Fabian Nabugoomu and Faisal Ababneh and Abraham Owino",
year = "2018",
month = "1",
day = "1",
doi = "10.1177/0037549718788955",
language = "English",
journal = "Simulation",
issn = "0037-5497",
publisher = "SAGE Publications Ltd",

}

TY - JOUR

T1 - Simulation of time series wind speed at an international airport

AU - Wesonga, Ronald

AU - Nabugoomu, Fabian

AU - Ababneh, Faisal

AU - Owino, Abraham

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The sporadic and unstable nature of wind speed renders it very difficult to predict accurately to serve various decisions, such as safety in the air traffic flow and reliable power generation system. In this study we assessed the autoregressive integrated moving average (ARIMA) and artificial neural network (ANN) models on the wind speed time series problem. Data on wind speed and minimum and maximum temperatures were evaluated. Wind speed was established to follow a time series that fluctuated around ARIMA (0,1,1) and ARIMA (1,1,1). The optimal ANN model was established at 10 hidden neurons. The performance indices considered all indicated that the ANN wind speed model was superior to the ARIMA model. Wind speed prediction accuracy can be improved to secure the safety of air traffic flow as well support the implementation of a reliable and secure power generation system at the airport.

AB - The sporadic and unstable nature of wind speed renders it very difficult to predict accurately to serve various decisions, such as safety in the air traffic flow and reliable power generation system. In this study we assessed the autoregressive integrated moving average (ARIMA) and artificial neural network (ANN) models on the wind speed time series problem. Data on wind speed and minimum and maximum temperatures were evaluated. Wind speed was established to follow a time series that fluctuated around ARIMA (0,1,1) and ARIMA (1,1,1). The optimal ANN model was established at 10 hidden neurons. The performance indices considered all indicated that the ANN wind speed model was superior to the ARIMA model. Wind speed prediction accuracy can be improved to secure the safety of air traffic flow as well support the implementation of a reliable and secure power generation system at the airport.

KW - artificial neural network

KW - autoregressive integrated moving average

KW - model

KW - statistics

KW - Wind speed

UR - http://www.scopus.com/inward/record.url?scp=85050548281&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050548281&partnerID=8YFLogxK

U2 - 10.1177/0037549718788955

DO - 10.1177/0037549718788955

M3 - Article

JO - Simulation

JF - Simulation

SN - 0037-5497

ER -