Electrical Charge of Niamey City Modelisation by Neural Network

Mamane Moumouni Hamidou; Noma Talibi Soumaïla; Boureima Seibou; Adekunlé Akim Salami; Attoumane Kosso Moustapha; Madougou Saïdou

doi:doi:10.11648/j.sjee.20190701.12

Electrical Charge of Niamey City Modelisation by Neural Network

Mamane Moumouni Hamidou, Noma Talibi Soumaïla, Boureima Seibou, Adekunlé Akim Salami, Attoumane Kosso Moustapha, Madougou Saïdou

Published in Science Journal of Energy Engineering (Volume 7, Issue 1)

Received: 11 July 2019 Accepted: 9 August 2019 Published: 23 August 2019

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

In order to forecast consumption, electric power generation, transmission and distribution companies need model to predict short-term demand for electric power load so that they can use their electricity infrastructure efficiently, safely and economically. The short-term forecast of electrical energy demand is the forecast of consumption over time interval ranging from one hour to few days. For optimal use of electricity grid, energy production must keep pace with demand. To this end, prediction errors can lead to risks and shortcomings in the generation and distribution of electrical load to users. This paper is part of electrical charge prediction of Niamey city. Several are being carried out in this field, but prediction techniques based on artificial neural networks have recently been developed. This work focused on two (2) neural approaches such as the multilayer Perceptron (MLP) and the non-linear autoregressive network with exogenous inputs (NARX). Several configurations of these two models have been developed and tested on actual electrical load data. We carried out the short-term forecast (hourly basis) of electrical load of Niamey city. All configurations have been implemented in MATLAB software. The statistical indicators MAPE (Mean Absolute Average Error in Percent), R² (the correlation coefficient) and RMSE (Square Root of Mean Square Error) were used to evaluate the performance of the models. Thus, with MAPE of 5.1765%, R² of 95.3013% and RMSE of 5.6014%, the [ABCD] configuration of NARX model converges better compared to the MLP model with MAPE of 7.1874%, R² of 92.0622% and RMSE of 7.2199%. Where A is the data charge of the same time of the previous day, B is the charge data of the same time of the previous week, C is the charge data of same time of previous year and D is the average of last 24 charge values. So the NARX model is the most efficient and can be used for future predictions on Niamey city network.

Published in	Science Journal of Energy Engineering (Volume 7, Issue 1)
DOI	10.11648/j.sjee.20190701.12
Page(s)	13-19
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2019. Published by Science Publishing Group

Keywords

Short-term Forecast, Artificial Neural Networks, MLP, NARX, MAPE, R², RMSE

References

[1]	Binod Bhandari, Shree Raj Shakya, Ajay Kumar Jha, “Short Term Electric Load Forecasting of Kathmandu Valley of Nepal using Artificial Neural Network”, Kathford Journal of Engineering and Management, Volume 1, Issue 1, ISSN: 2661-6106, pp. 43-48, 2018.
[2]	Rahul SG, Monah Pradeep I, Kavitha P, Dhivyasri G, “Prediction of Electricity Load Using Artificial Neural Network for Technology Tower Block of VIT University”, International Journal of Applied Engineering Research ISSN 0973-4562 Volume 12, Number 18, pp. 7717-7723, 2017.
[3]	TCHONDA Malanguièhèwa, neural approach for the prediction of electrical charge on the grid of the Communauté Electrique du Benin (CEB), December 2016; 142p.
[4]	Isaac Samuel, Tolulope Ojewola, Ayokunle Awelewa, and Peter Amaize, “Short-Term Load Forecasting Using The Time Series And Artificial Neural Network Methods”, IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE), e-ISSN: 2278-1676, p-ISSN: 2320-3331, Vol. 11, Issue. 1, pp. 72-81, 2016.
[5]	Anil Patel, Albert John Varghese, “Evaluate Hourly based Load Forecasting using NARX Neural Network in MATLAB Environment”, IJAREEIE, Vol. 6, Issue 3, March 2017.
[6]	S. TATSA, "Modeling and Forecasting of Hourly Electricity Consumption in Québec: Comparison of Time Series Methods," Master's Thesis in Econ. Laval University, Quebec, Canada, pp. 1-10, 2013. Control, Signals, and Systems, Vol. 2, 1989, pp. 303-314.
[7]	M. A. Arbib, The Hand Book of Brain Theory and Neural Networks, 2nd edition, 2002.
[8]	L. P. J. Veelenturf, Analysis and Applications of Artificial Neural Networks, Book Prntice Hall Edition, 1995.
[9]	Anamika Singh, Vinay Kumar Tripathi, “Load Forecasting Using Multilayer Perceptron Neural Network”, IJESC, Volume 6 Issue No. 5, pp. 4548-4551, May 2016.
[10]	Mohsen Hayati, and Yazdan Shirvany, “Artificial Neural Network Approach for Short Term Load Forecasting for Illam Region”, IJECSE VOLUME 1 NUMBER 2, ISSN 1307-5179, pp. 121-125, 2007.
[11]	Leo Dencelin X, Ramkumar T, “Analysis of multilayer perceptron machine learning approach in classifying protein secondary structures”, Biomedical Research; Special Issue: S166-S173, 2016.
[12]	E. L. TAYLOR, “Short-term Electrical Load Forecasting for an Institutional/Industrial Power System Using an Artificial Neural Network,” Tennessee Res. Creat. Exch., pp. 1–97, 2013.
[13]	Haykin S., "Neural Networks-A Comprehensive Foundation", Prentice-Hall, New York, 1999.
[14]	Cybenko G. "Approximation by Superpositions of a Sigmoidal Function", Mathematics of Control, Signals, and Systems, Vol. 2, 1989, pp. 303-314.
[15]	Esra Eri¸ sen Cem Iyigun Fehmi Tanrısever, “Short-term electricity load forecasting with special days: an analysis on parametric and non-parametric methods”, Springer Science+Business Media, LLC, part of Springer Nature 2017.
[16]	Abdullateef Ayodele Isqeel, Tijani Bayo Ismaeel, and Salami Momoh-Jimoh Eyiomika, “Consumer Load Prediction Based on NARX for Electricity Theft Detection”, IEEE-2016 International Conference on Computer & Communication Engineering, DOI 10.1109/ICCCE.2016.70, pp. 294-299, 2016.

Cite This Article

Plain Text BibTeX RIS

APA Style

Mamane Moumouni Hamidou, Noma Talibi Soumaïla, Boureima Seibou, Adekunlé Akim Salami, Attoumane Kosso Moustapha, et al. (2019). Electrical Charge of Niamey City Modelisation by Neural Network. Science Journal of Energy Engineering, 7(1), 13-19. https://doi.org/10.11648/j.sjee.20190701.12

Copy | Download

ACS Style

Mamane Moumouni Hamidou; Noma Talibi Soumaïla; Boureima Seibou; Adekunlé Akim Salami; Attoumane Kosso Moustapha, et al. Electrical Charge of Niamey City Modelisation by Neural Network. Sci. J. Energy Eng. 2019, 7(1), 13-19. doi: 10.11648/j.sjee.20190701.12

Copy | Download

AMA Style

Mamane Moumouni Hamidou, Noma Talibi Soumaïla, Boureima Seibou, Adekunlé Akim Salami, Attoumane Kosso Moustapha, et al. Electrical Charge of Niamey City Modelisation by Neural Network. Sci J Energy Eng. 2019;7(1):13-19. doi: 10.11648/j.sjee.20190701.12

Copy | Download

@article{10.11648/j.sjee.20190701.12,
  author = {Mamane Moumouni Hamidou and Noma Talibi Soumaïla and Boureima Seibou and Adekunlé Akim Salami and Attoumane Kosso Moustapha and Madougou Saïdou},
  title = {Electrical Charge of Niamey City Modelisation by Neural Network},
  journal = {Science Journal of Energy Engineering},
  volume = {7},
  number = {1},
  pages = {13-19},
  doi = {10.11648/j.sjee.20190701.12},
  url = {https://doi.org/10.11648/j.sjee.20190701.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sjee.20190701.12},
  abstract = {In order to forecast consumption, electric power generation, transmission and distribution companies need model to predict short-term demand for electric power load so that they can use their electricity infrastructure efficiently, safely and economically. The short-term forecast of electrical energy demand is the forecast of consumption over time interval ranging from one hour to few days. For optimal use of electricity grid, energy production must keep pace with demand. To this end, prediction errors can lead to risks and shortcomings in the generation and distribution of electrical load to users. This paper is part of electrical charge prediction of Niamey city. Several are being carried out in this field, but prediction techniques based on artificial neural networks have recently been developed. This work focused on two (2) neural approaches such as the multilayer Perceptron (MLP) and the non-linear autoregressive network with exogenous inputs (NARX). Several configurations of these two models have been developed and tested on actual electrical load data. We carried out the short-term forecast (hourly basis) of electrical load of Niamey city. All configurations have been implemented in MATLAB software. The statistical indicators MAPE (Mean Absolute Average Error in Percent), R2 (the correlation coefficient) and RMSE (Square Root of Mean Square Error) were used to evaluate the performance of the models. Thus, with MAPE of 5.1765%, R2 of 95.3013% and RMSE of 5.6014%, the [ABCD] configuration of NARX model converges better compared to the MLP model with MAPE of 7.1874%, R2 of 92.0622% and RMSE of 7.2199%. Where A is the data charge of the same time of the previous day, B is the charge data of the same time of the previous week, C is the charge data of same time of previous year and D is the average of last 24 charge values. So the NARX model is the most efficient and can be used for future predictions on Niamey city network.},
 year = {2019}
}

Copy | Download

TY - JOUR
T1 - Electrical Charge of Niamey City Modelisation by Neural Network
AU - Mamane Moumouni Hamidou
AU - Noma Talibi Soumaïla
AU - Boureima Seibou
AU - Adekunlé Akim Salami
AU - Attoumane Kosso Moustapha
AU - Madougou Saïdou
Y1 - 2019/08/23
PY - 2019
N1 - https://doi.org/10.11648/j.sjee.20190701.12
DO - 10.11648/j.sjee.20190701.12
T2 - Science Journal of Energy Engineering
JF - Science Journal of Energy Engineering
JO - Science Journal of Energy Engineering
SP - 13
EP - 19
PB - Science Publishing Group
SN - 2376-8126
UR - https://doi.org/10.11648/j.sjee.20190701.12
AB - In order to forecast consumption, electric power generation, transmission and distribution companies need model to predict short-term demand for electric power load so that they can use their electricity infrastructure efficiently, safely and economically. The short-term forecast of electrical energy demand is the forecast of consumption over time interval ranging from one hour to few days. For optimal use of electricity grid, energy production must keep pace with demand. To this end, prediction errors can lead to risks and shortcomings in the generation and distribution of electrical load to users. This paper is part of electrical charge prediction of Niamey city. Several are being carried out in this field, but prediction techniques based on artificial neural networks have recently been developed. This work focused on two (2) neural approaches such as the multilayer Perceptron (MLP) and the non-linear autoregressive network with exogenous inputs (NARX). Several configurations of these two models have been developed and tested on actual electrical load data. We carried out the short-term forecast (hourly basis) of electrical load of Niamey city. All configurations have been implemented in MATLAB software. The statistical indicators MAPE (Mean Absolute Average Error in Percent), R2 (the correlation coefficient) and RMSE (Square Root of Mean Square Error) were used to evaluate the performance of the models. Thus, with MAPE of 5.1765%, R2 of 95.3013% and RMSE of 5.6014%, the [ABCD] configuration of NARX model converges better compared to the MLP model with MAPE of 7.1874%, R2 of 92.0622% and RMSE of 7.2199%. Where A is the data charge of the same time of the previous day, B is the charge data of the same time of the previous week, C is the charge data of same time of previous year and D is the average of last 24 charge values. So the NARX model is the most efficient and can be used for future predictions on Niamey city network.
VL - 7
IS - 1
ER -

Copy | Download

Author Information

Mamane Moumouni Hamidou

Electrical Engineering Department, Mines, Industry and Geology School, Niamey, Niger
Noma Talibi Soumaïla
Boureima Seibou

Electrical Engineering Department, Mines, Industry and Geology School, Niamey, Niger
Adekunlé Akim Salami

Electrical Engineering Department, National Engineering School, University of Lome, Lome, Togo
Attoumane Kosso Moustapha

Electrical Engineering Department, Mines, Industry and Geology School, Niamey, Niger
Madougou Saïdou

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Mamane Moumouni Hamidou, Noma Talibi Soumaïla, Boureima Seibou, Adekunlé Akim Salami, Attoumane Kosso Moustapha, et al. (2019). Electrical Charge of Niamey City Modelisation by Neural Network. Science Journal of Energy Engineering, 7(1), 13-19. https://doi.org/10.11648/j.sjee.20190701.12

Copy | Download

ACS Style

Mamane Moumouni Hamidou; Noma Talibi Soumaïla; Boureima Seibou; Adekunlé Akim Salami; Attoumane Kosso Moustapha, et al. Electrical Charge of Niamey City Modelisation by Neural Network. Sci. J. Energy Eng. 2019, 7(1), 13-19. doi: 10.11648/j.sjee.20190701.12

Copy | Download

AMA Style

Mamane Moumouni Hamidou, Noma Talibi Soumaïla, Boureima Seibou, Adekunlé Akim Salami, Attoumane Kosso Moustapha, et al. Electrical Charge of Niamey City Modelisation by Neural Network. Sci J Energy Eng. 2019;7(1):13-19. doi: 10.11648/j.sjee.20190701.12

Copy | Download

@article{10.11648/j.sjee.20190701.12,
  author = {Mamane Moumouni Hamidou and Noma Talibi Soumaïla and Boureima Seibou and Adekunlé Akim Salami and Attoumane Kosso Moustapha and Madougou Saïdou},
  title = {Electrical Charge of Niamey City Modelisation by Neural Network},
  journal = {Science Journal of Energy Engineering},
  volume = {7},
  number = {1},
  pages = {13-19},
  doi = {10.11648/j.sjee.20190701.12},
  url = {https://doi.org/10.11648/j.sjee.20190701.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sjee.20190701.12},
  abstract = {In order to forecast consumption, electric power generation, transmission and distribution companies need model to predict short-term demand for electric power load so that they can use their electricity infrastructure efficiently, safely and economically. The short-term forecast of electrical energy demand is the forecast of consumption over time interval ranging from one hour to few days. For optimal use of electricity grid, energy production must keep pace with demand. To this end, prediction errors can lead to risks and shortcomings in the generation and distribution of electrical load to users. This paper is part of electrical charge prediction of Niamey city. Several are being carried out in this field, but prediction techniques based on artificial neural networks have recently been developed. This work focused on two (2) neural approaches such as the multilayer Perceptron (MLP) and the non-linear autoregressive network with exogenous inputs (NARX). Several configurations of these two models have been developed and tested on actual electrical load data. We carried out the short-term forecast (hourly basis) of electrical load of Niamey city. All configurations have been implemented in MATLAB software. The statistical indicators MAPE (Mean Absolute Average Error in Percent), R2 (the correlation coefficient) and RMSE (Square Root of Mean Square Error) were used to evaluate the performance of the models. Thus, with MAPE of 5.1765%, R2 of 95.3013% and RMSE of 5.6014%, the [ABCD] configuration of NARX model converges better compared to the MLP model with MAPE of 7.1874%, R2 of 92.0622% and RMSE of 7.2199%. Where A is the data charge of the same time of the previous day, B is the charge data of the same time of the previous week, C is the charge data of same time of previous year and D is the average of last 24 charge values. So the NARX model is the most efficient and can be used for future predictions on Niamey city network.},
 year = {2019}
}

Copy | Download