# Deep Learning with Loss Ensembles for Solar Power Prediction in Smart Cities

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Related Works

## 3. Supervised Learning

## 4. The Proposed Method

## 5. Experimental Results

## 6. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Liu, J.; Fang, W.; Zhang, X.; Yang, C. An improved photovoltaic power forecasting model with the assistance of aerosol index data. IEEE Trans. Sustain. Energy
**2015**, 6, 434–442. [Google Scholar] [CrossRef] - Yang, D.; Kleissl, J.; Gueymard, C.A.; Pedro, H.T.; Coimbra, C.F. History and trends in solar irradiance and PV power forecasting: A preliminary assessment and review using text mining. Sol. Energy
**2018**, 168, 60–101. [Google Scholar] [CrossRef] - Estebsari, A.; Pons, E.; Patti, E.; Mengistu, M.; Bompard, E.; Bahmanyar, A.; Jamali, S. An IoT realization in an interdepartmental real time simulation lab for distribution system control and management studies. In Proceedings of the 2016 IEEE 16th International Conference on Environment and Electrical Engineering (EEEIC), Florence, Italy, 7–10 June 2016; pp. 1–6. [Google Scholar]
- Estebsari, A.; Pons, E.; Huang, T.; Bompard, E. Techno-economic impacts of automatic undervoltage load shedding under emergency. Electr. Power Syst. Res.
**2016**, 131, 168–177. [Google Scholar] [CrossRef] [Green Version] - Wolff, B.; Kuhnert, J.; Lorenz, E.; Kramer, O.; Heinemann, D. Comparing support vector regression for PV power forecasting to a physical modeling approach using measurement, numerical weather prediction, and cloud motion data. Sol. Energy
**2016**, 135, 197–208. [Google Scholar] [CrossRef] - Zhang, W.; Quan, H.; Gandhi, O.; Rodríguez-Gallegos, C.D.; Sharma, A.; Srinivasan, D. An ensemble machine learning based approach for constructing probabilistic pv generation forecasting. In Proceedings of the 2017 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), Bangalore, India, 8–10 November 2017; IEEE: Piscataway, NJ, USA, 2017; pp. 1–6. [Google Scholar]
- Wang, K.; Qi, X.; Liu, H. A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network. Appl. Energy
**2019**, 251, 113315. [Google Scholar] [CrossRef] - Estebsari, A.; Rajabi, R. Single Residential Load Forecasting Using Deep Learning and Image Encoding Techniques. Electronics
**2020**, 9, 68. [Google Scholar] [CrossRef] [Green Version] - Behera, M.K.; Nayak, N. A comparative study on short-term PV power forecasting using decomposition based optimized extreme learning machine algorithm. Eng. Sci. Technol. Int. J.
**2020**, 23, 156–167. [Google Scholar] [CrossRef] - Ogliari, E.; Dolara, A.; Manzolini, G.; Leva, S. Physical and hybrid methods comparison for the day ahead PV output power forecast. Renew. Energy
**2017**, 113, 11–21. [Google Scholar] [CrossRef] - Wolff, B.; Lorenz, E.; Kramer, O. Statistical learning for short-term photovoltaic power predictions. In Computational Sustainability; Springer: Cham, Switzerland, 2016; pp. 31–45. [Google Scholar]
- Almeida, M.P.; Perpinan, O.; Narvarte, L. PV power forecast using a nonparametric PV model. Sol. Energy
**2015**, 115, 354–368. [Google Scholar] [CrossRef] [Green Version] - Wang, F.; Zhen, Z.; Wang, B.; Mi, Z. Comparative study on KNN and SVM based weather classification models for day ahead short term solar pv power forecasting. Appl. Sci.
**2018**, 8, 28. [Google Scholar] [CrossRef] [Green Version] - Dolara, A.; Grimaccia, F.; Leva, S.; Mussetta, M.; Ogliari, E. A physical hybrid artificial neural network for short term forecasting of PV plant power output. Energies
**2015**, 8, 1138–1153. [Google Scholar] [CrossRef] [Green Version] - Li, Z.; Rahman, S.; Vega, R.; Dong, B. A hierarchical approach using machine learning methods in solar photovoltaic energy production forecasting. Energies
**2016**, 9, 55. [Google Scholar] [CrossRef] [Green Version] - Li, Z.; Zang, C.; Zeng, P.; Yu, H.; Li, H. Day-ahead hourly photovoltaic generation forecasting using extreme learning machine. In Proceedings of the 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), Shenyang, China, 8–12 June 2015; IEEE: Piscataway, NJ, USA, 2015; pp. 779–783. [Google Scholar]
- Teo, T.T.; Logenthiran, T.; Woo, W.L. Forecasting of photovoltaic power using extreme learning machine. In Proceedings of the 2015 IEEE Innovative Smart Grid Technologies-Asia (ISGT ASIA), Bangkok, Thailand, 3–6 November 2015; IEEE: Piscataway, NJ, USA, 2015; pp. 1–6. [Google Scholar]
- Su, D.; Batzelis, E.; Pal, B. Machine Learning Algorithms in Forecasting of Photovoltaic Power Generation. In Proceedings of the 2019 International Conference on Smart Energy Systems and Technologies (SEST), Porto, Portugal, 9–11 September 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 1–6. [Google Scholar]
- Reddy, S.S. Bat algorithm-based back propagation approach for short-term load forecasting considering weather factors. Electr. Eng.
**2018**, 100, 1297–1303. [Google Scholar] [CrossRef] - Rego, L.; Sumaili, J.; Miranda, V.; Francês, C.; Silva, M.; Santana, A. Mean shift densification of scarce data sets in short-term electric power load forecasting for special days. Electr. Eng.
**2017**, 99, 881–898. [Google Scholar] [CrossRef] - Holland, M.J.; Ikeda, K. Minimum proper loss estimators for parametric models. IEEE Trans. Signal Process.
**2016**, 64, 704–713. [Google Scholar] [CrossRef] - Hajiabadi, H.; Molla-Aliod, D.; Monsefi, R. On Extending Neural Networks with Loss Ensembles for Text Classification. In Proceedings of the Australasian Language Technology Association Workshop 2017, Brisbane, Australia, 6–8 December 2017; pp. 98–102. [Google Scholar]
- Liu, W.; Pokharel, P.P.; Principe, J.C. Correntropy: A localized similarity measure. In Proceedings of the 2006 IEEE International Joint Conference on Neural Network Proceedings, Vancouver, BC, Canada, 16–21 July 2006; IEEE: Piscataway, NJ, USA, 2006; pp. 4919–4924. [Google Scholar]
- Peng, J.; Du, Q. Robust joint sparse representation based on maximum correntropy criterion for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens.
**2017**, 55, 7152–7164. [Google Scholar] [CrossRef] - Shi, Q.; Reid, M.; Caetano, T.; Van Den Hengel, A.; Wang, Z. A Hybrid Loss for Multiclass and Structured Prediction. IEEE Trans. Pattern Anal. Mach. Intell.
**2015**, 37, 2–12. [Google Scholar] [CrossRef] [PubMed] - BenTaieb, A.; Kawahara, J.; Hamarneh, G. Multi-Loss Convolutional Networks for Gland Analysis in Microscopy. In Proceedings of the Biomedical Imaging (ISBI 2016), Prague, Czech Republic, 13–16 April 2016; pp. 642–645. [Google Scholar]
- Rajabi, R.; Estebsari, A. Deep Learning Based Forecasting of Individual Residential Loads Using Recurrence Plots. In Proceedings of the 2019 IEEE Milan PowerTech, Milan, Italy, 23–27 June 2019; pp. 1–5. [Google Scholar]

**Figure 2.**The Absolute loss (red), the Square loss (blue) and the Correntropy loss function (green).

**Figure 4.**(

**Left**) The predicted labels compared with the true labels. (

**Right**) Zoomed curve of the predicted and real labels.

Method | Training Error | Test Error |
---|---|---|

Ridge Regression | 0.000488 | 0.005673 |

kNN Regression | 0.000242 | 0.003482 |

Bayesian Regression | 0.000488 | 0.005672 |

Decision Tree | 0.001040 | 0.012720 |

SVR | 0.000842 | 0.009866 |

The Proposed Method | 0.000335 | 0.002785 |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Hajiabadi, M.; Farhadi, M.; Babaiyan, V.; Estebsari, A.
Deep Learning with Loss Ensembles for Solar Power Prediction in Smart Cities. *Smart Cities* **2020**, *3*, 842-852.
https://doi.org/10.3390/smartcities3030043

**AMA Style**

Hajiabadi M, Farhadi M, Babaiyan V, Estebsari A.
Deep Learning with Loss Ensembles for Solar Power Prediction in Smart Cities. *Smart Cities*. 2020; 3(3):842-852.
https://doi.org/10.3390/smartcities3030043

**Chicago/Turabian Style**

Hajiabadi, Moein, Mahdi Farhadi, Vahide Babaiyan, and Abouzar Estebsari.
2020. "Deep Learning with Loss Ensembles for Solar Power Prediction in Smart Cities" *Smart Cities* 3, no. 3: 842-852.
https://doi.org/10.3390/smartcities3030043