Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm

Mohammad Abu Jami'in; Mardi Santosa; Ii Munadhif; Ryan Yudha Adhitya; Zindhu Maulana; Mohammad Fajar Adiatmoko

doi:10.1109/ITIS57155.2022.10010011

Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm

Mohammad Abu Jami'in^*
, Mardi Santosa
, Ii Munadhif
, Ryan Yudha Adhitya
, Zindhu Maulana
, Mohammad Fajar Adiatmoko

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper presents a mathematical model for the representation of wind speed modeling. This model consists of two parts: the deterministic part, the autoregressive sub-section, and the stochastic model part, which is the moving average sub-section with the time series autoregressive moving average (ARMA) model structure. The problem of the ARMA model structure that will be solved is to find the model parameters and generate the NID signal that gives the best model accuracy. The method used to find the optimal model parameters is the search for optimal solutions using genetic algorithm techniques. The fitness function used is a residual error which the mean square error can express. Simulation is done with 5000 cycles of training. The parameters obtained were tested with training data which gives an MSE value of 0.1868, while the one tested using data outside of training gives an MSE value of 0.1970. Therefore, this model is quite feasible to predict wind speed with an MSE difference of about 5.4%.

Original language	English
Title of host publication	Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	74-79
Number of pages	6
ISBN (Electronic)	9798350398199
DOIs	https://doi.org/10.1109/ITIS57155.2022.10010011
Publication status	Published - 2022
Externally published	Yes
Event	8th IEEE Information Technology International Seminar, ITIS 2022 - Surabaya, Indonesia Duration: 19 Oct 2022 → 21 Oct 2022

Publication series

Name	Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022

Conference

Conference	8th IEEE Information Technology International Seminar, ITIS 2022
Country/Territory	Indonesia
City	Surabaya
Period	19/10/22 → 21/10/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

ARMA
genetic algorithm
least square error
time series
wind speed modeling

Access to Document

10.1109/ITIS57155.2022.10010011

Cite this

Jami'in, M. A., Santosa, M., Munadhif, I., Adhitya, R. Y., Maulana, Z., & Adiatmoko, M. F. (2022). Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm. In Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022 (pp. 74-79). (Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITIS57155.2022.10010011

Jami'in, Mohammad Abu ; Santosa, Mardi ; Munadhif, Ii et al. / Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm. Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 74-79 (Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022).

@inproceedings{ebcca05573d247618224eecdcd306d3c,

title = "Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm",

abstract = "This paper presents a mathematical model for the representation of wind speed modeling. This model consists of two parts: the deterministic part, the autoregressive sub-section, and the stochastic model part, which is the moving average sub-section with the time series autoregressive moving average (ARMA) model structure. The problem of the ARMA model structure that will be solved is to find the model parameters and generate the NID signal that gives the best model accuracy. The method used to find the optimal model parameters is the search for optimal solutions using genetic algorithm techniques. The fitness function used is a residual error which the mean square error can express. Simulation is done with 5000 cycles of training. The parameters obtained were tested with training data which gives an MSE value of 0.1868, while the one tested using data outside of training gives an MSE value of 0.1970. Therefore, this model is quite feasible to predict wind speed with an MSE difference of about 5.4\%.",

keywords = "ARMA, genetic algorithm, least square error, time series, wind speed modeling",

author = "Jami'in, \{Mohammad Abu\} and Mardi Santosa and Ii Munadhif and Adhitya, \{Ryan Yudha\} and Zindhu Maulana and Adiatmoko, \{Mohammad Fajar\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 8th IEEE Information Technology International Seminar, ITIS 2022 ; Conference date: 19-10-2022 Through 21-10-2022",

year = "2022",

doi = "10.1109/ITIS57155.2022.10010011",

language = "English",

series = "Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "74--79",

booktitle = "Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022",

address = "United States",

}

Jami'in, MA, Santosa, M, Munadhif, I, Adhitya, RY, Maulana, Z & Adiatmoko, MF 2022, Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm. in Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022. Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022, Institute of Electrical and Electronics Engineers Inc., pp. 74-79, 8th IEEE Information Technology International Seminar, ITIS 2022, Surabaya, Indonesia, 19/10/22. https://doi.org/10.1109/ITIS57155.2022.10010011

Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm. / Jami'in, Mohammad Abu; Santosa, Mardi; Munadhif, Ii et al.
Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 74-79 (Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm

AU - Jami'in, Mohammad Abu

AU - Santosa, Mardi

AU - Munadhif, Ii

AU - Adhitya, Ryan Yudha

AU - Maulana, Zindhu

AU - Adiatmoko, Mohammad Fajar

PY - 2022

Y1 - 2022

N2 - This paper presents a mathematical model for the representation of wind speed modeling. This model consists of two parts: the deterministic part, the autoregressive sub-section, and the stochastic model part, which is the moving average sub-section with the time series autoregressive moving average (ARMA) model structure. The problem of the ARMA model structure that will be solved is to find the model parameters and generate the NID signal that gives the best model accuracy. The method used to find the optimal model parameters is the search for optimal solutions using genetic algorithm techniques. The fitness function used is a residual error which the mean square error can express. Simulation is done with 5000 cycles of training. The parameters obtained were tested with training data which gives an MSE value of 0.1868, while the one tested using data outside of training gives an MSE value of 0.1970. Therefore, this model is quite feasible to predict wind speed with an MSE difference of about 5.4%.

AB - This paper presents a mathematical model for the representation of wind speed modeling. This model consists of two parts: the deterministic part, the autoregressive sub-section, and the stochastic model part, which is the moving average sub-section with the time series autoregressive moving average (ARMA) model structure. The problem of the ARMA model structure that will be solved is to find the model parameters and generate the NID signal that gives the best model accuracy. The method used to find the optimal model parameters is the search for optimal solutions using genetic algorithm techniques. The fitness function used is a residual error which the mean square error can express. Simulation is done with 5000 cycles of training. The parameters obtained were tested with training data which gives an MSE value of 0.1868, while the one tested using data outside of training gives an MSE value of 0.1970. Therefore, this model is quite feasible to predict wind speed with an MSE difference of about 5.4%.

KW - ARMA

KW - genetic algorithm

KW - least square error

KW - time series

KW - wind speed modeling

UR - https://www.scopus.com/pages/publications/85147095748

U2 - 10.1109/ITIS57155.2022.10010011

DO - 10.1109/ITIS57155.2022.10010011

M3 - Conference contribution

AN - SCOPUS:85147095748

T3 - Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022

SP - 74

EP - 79

BT - Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th IEEE Information Technology International Seminar, ITIS 2022

Y2 - 19 October 2022 through 21 October 2022

ER -

Jami'in MA, Santosa M, Munadhif I, Adhitya RY, Maulana Z, Adiatmoko MF. Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm. In Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 74-79. (Proceeding - IEEE 8th Information Technology International Seminar, ITIS 2022). doi: 10.1109/ITIS57155.2022.10010011

Wind Speed Time Series Modeling under Least Square Error and Genetic Algorithm

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this