# Impact Study of Temperature on the Time Series Electricity Demand of Urban Nepal for Short-Term Load Forecasting

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

- An impact study on the temperature is performed, which leads to increases in electricity demand during hot and cold temperatures for a tropical region like Nepal.
- The quantitative analysis among variables such as the impact of time series variables such as holidays, working days, the time of day, day of the week, and day of the month is discussed in detail.
- The development of two different forecasting models for weekends and weekdays, which leads to achieving better prediction capability among the existing literature of the Nepalese dataset.
- A comparison of developed models with conventional time series models is conducted for weekdays and weekends, which shows that the FF-ANN holds the upper hand when forecasting load for both days, with a major improvement in weekend forecasting.

## 2. Literature Review

#### 2.1. Temperature Effect

#### 2.2. Time Series Dependency

## 3. Data Analysis

#### 3.1. Temperature’s Effect on Load

#### 3.2. Time Lag Effect

## 4. Methodology

#### 4.1. Moving Average

#### 4.2. Weighted Moving Average

#### 4.3. Exponential Smoothing

#### 4.4. Holt’s Method

#### 4.5. Feedforward Artificial Neural Network

_{n}presents the weight assigned to every connection.

#### 4.6. Performance Evaluation and Validation

## 5. Results and Discussion

#### 5.1. Conventional Time Series Model Testing and Analysis

#### 5.2. Feedforward Artificial Neural Network Parameter Selection and Result Analysis

## 6. Conclusions

## Author Contributions

## Funding

## Data Availability Statement

## Acknowledgments

## Conflicts of Interest

## References

- Nepal Electricity Authority. Annual Report; Nepal Electricity Authority (NEA): Kathmandu, Nepal, 2020.
- Nepal Electricity Authority. Load Forecasting Report; July 2015. Available online: https://www.nea.org.np/admin/assets/uploads/supportive_docs/LoadForecast2014_15.pdf (accessed on 7 July 2021).
- Bhandari, B.; Shakya, S.R.; Jha, A.K. Short term electric load forecasting of kathmandu valley of nepal using artificial neural network. Kathford J. Eng. Manag.
**2018**, 1, 43–48. [Google Scholar] [CrossRef] [Green Version] - Pandey, G.P.; Shrestha, A.; Mali, B.; Singh, A.; Jha, A.K. Performance enhancement of radial distribution system via network reconfiguration: A case study of urban city in nepal. J. Renew. Energy Electr. Comput. Eng.
**2021**, 1, 1–11. [Google Scholar] [CrossRef] - Singh, A.K.; Khatoon, S.; Muazzam, M.; Chaturvedi, D.K. Load forecasting techniques and methodologies: A review. In Proceedings of the 2012 2nd International Conference on Power, Control and Embedded Systems, Allahabad, India, 17–19 December 2012; pp. 1–10. [Google Scholar]
- Shrestha, A.; Ghimire, B.; Gonzalez-Longatt, F. A Bayesian Model to Forecast the Time Series Kinetic Energy Data for a Power System. Energies
**2021**, 14, 3299. [Google Scholar] [CrossRef] - Chapagain, K.; Kittipiyakul, S.; Kulthanavit, P. Short-Term Electricity Demand Forecasting: Impact Analysis of Temperature for Thailand. Energies
**2020**, 13, 2498. [Google Scholar] [CrossRef] - Ramanathan, R.; Engle, R.; Granger, C.W.; Vahid-Araghi, F.; Brace, C. Short-run forecasts of electricity loads and peaks. Int. J. Forecast.
**1997**, 13, 161–174. [Google Scholar] [CrossRef] - Srinivasan, D.; Chang, C.; Liew, A. Demand forecasting using fuzzy neural computation, with special emphasis on weekend and public holiday forecasting. IEEE Trans. Power Syst.
**1995**, 10, 1897–1903. [Google Scholar] [CrossRef] - Kim, K.-H.; Youn, H.-S.; Kang, Y.-C. Short-term load forecasting for special days in anomalous load conditions using neural networks and fuzzy inference method. IEEE Trans. Power Syst.
**2000**, 15, 559–565. [Google Scholar] - Bessec, M.; Fouquau, J. The non-linear link between electricity consumption and temperature in Europe: A threshold panel approach. Energy Econ.
**2008**, 30, 2705–2721. [Google Scholar] [CrossRef] [Green Version] - Fung, W.; Lam, K.S.; Hung, W.; Pang, S.; Lee, Y. Impact of urban temperature on energy consumption of Hong Kong. Energy
**2006**, 31, 2623–2637. [Google Scholar] [CrossRef] - Liu, B.; Fu, C.; Bielefield, A.; Liu, Y. Forecasting of Chinese primary energy consumption in 2021 with GRU artificial neural network. Energies
**2017**, 10, 1453. [Google Scholar] [CrossRef] - Amjady, N.; Keynia, F. Mid-term load forecasting of power systems by a new prediction method. Energy Convers. Manag.
**2008**, 49, 2678–2687. [Google Scholar] [CrossRef] - Abeyrathna, K.D.; Jeenanunta, C. Hybrid particle swarm optimization with genetic algorithm to train artificial neural networks for short-term load forecasting. Int. J. Swarm Intell. Res. IJSIR
**2019**, 10, 1–14. [Google Scholar] [CrossRef] [Green Version] - Kalekar, P.S. Time series forecasting using holt-winters exponential smoothing. Kanwal Rekhi Sch. Inf. Technol.
**2004**, 4329008, 1–13. [Google Scholar] - Bouktif, S.; Fiaz, A.; Ouni, A.; Serhani, M.A. Optimal deep learning lstm model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches. Energies
**2018**, 11, 1636. [Google Scholar] [CrossRef] [Green Version] - Hu, Z.; Bao, Y.; Xiong, T. Comprehensive learning particle swarm optimization based memetic algorithm for model selection in short-term load forecasting using support vector regression. Appl. Soft Comput.
**2014**, 25, 15–25. [Google Scholar] [CrossRef] - Bashir, Z.; El-Hawary, M. Short-term load forecasting using artificial neural network based on particle swarm optimization algorithm. In Proceedings of the 2007 Canadian Conference on Electrical and Computer Engineering, Vancouver, BC, Canada, 22–26 April 2007; pp. 272–275. [Google Scholar]
- Haben, S.; Giasemidis, G.; Ziel, F.; Arora, S. Short term load forecasting and the effect of temperature at the low voltage level. Int. J. Forecast.
**2019**, 35, 1469–1484. [Google Scholar] [CrossRef] [Green Version] - Al Mamun, A.; Sohel, M.; Mohammad, N.; Sunny, M.S.H.; Dipta, D.R.; Hossain, E. A comprehensive review of the load forecasting techniques using single and hybrid predictive models. IEEE Access
**2020**, 8, 134911–134939. [Google Scholar] [CrossRef] - Bouktif, S.; Fiaz, A.; Ouni, A.; Serhani, M.A. Single and multi-sequence deep learning models for short and medium term electric load forecasting. Energies
**2019**, 12, 149. [Google Scholar] [CrossRef] [Green Version] - Fallah, S.N.; Ganjkhani, M.; Shamshirband, S.; Chau, K.-W. Computational intelligence on short-term load forecasting: A methodological overview. Energies
**2019**, 12, 393. [Google Scholar] [CrossRef] [Green Version] - Wangpattarapong, K.; Maneewan, S.; Ketjoy, N.; Rakwichian, W. The impacts of climatic and economic factors on residential electricity consumption of Bangkok Metropolis. Energy Build.
**2008**, 40, 1419–1425. [Google Scholar] [CrossRef] - Sadi, M.Z.; Deeba, S.R.; Siddique, R.H. Temperature sensitivity forecasting of electrical load. In Proceedings of the 2010 4th International Power Engineering and Optimization Conference (PEOCO), Shah Alam, Malaysia, 23–24 June 2010; pp. 244–248. [Google Scholar]
- Zhang, C.; Liao, H.; Mi, Z. Climate impacts: Temperature and electricity consumption. Nat. Hazards
**2019**, 99, 1259–1275. [Google Scholar] [CrossRef] - Chapagain, K.; Kittipiyakul, S. Performance analysis of short-term electricity demand with atmospheric variables. Energies
**2018**, 11, 818. [Google Scholar] [CrossRef] [Green Version] - Maheshwari, A.; Murari, K.K.; Jayaraman, T. Peak Electricity Demand and Global Warming in the Industrial and Residential areas of Pune: An Extreme Value Approach. arXiv
**2019**, arXiv:1908.08570. [Google Scholar] - Li, B.; Lu, M.; Zhang, Y.; Huang, J. A Weekend Load Forecasting Model Based on Semi-Parametric Regression Analysis Considering Weather and Load Interaction. Energies
**2019**, 12, 3820. [Google Scholar] [CrossRef] [Green Version] - Mirasgedis, S.; Sarafidis, Y.; Georgopoulou, E.; Kotroni, V.; Lagouvardos, K.; Lalas, D. Modeling framework for estimating impacts of climate change on electricity demand at regional level: Case of Greece. Energy Convers. Manag.
**2007**, 48, 1737–1750. [Google Scholar] [CrossRef] - Lee, K.; Baek, H.-J.; Cho, C. The estimation of base temperature for heating and cooling degree-days for South Korea. J. Appl. Meteorol. Climatol.
**2014**, 53, 300–309. [Google Scholar] [CrossRef] - Clements, A.E.; Hurn, A.; Li, Z. Forecasting day-ahead electricity load using a multiple equation time series approach. Eur. J. Oper. Res.
**2016**, 251, 522–530. [Google Scholar] [CrossRef] [Green Version] - Swamidass, P.M. (Ed.) Forecasting models, Holt’s, HOLT’S FORECASTING MODEL. In Encyclopedia of Production and Manufacturing Management; Springer: Boston, MA, USA, 2000; p. 274. [Google Scholar] [CrossRef]
- Maia, A.L.S.; de Carvalho, F.d.A. Holt’s exponential smoothing and neural network models for forecasting interval-valued time series. Int. J. Forecast.
**2011**, 27, 740–759. [Google Scholar] [CrossRef] - MathWorks. Help Center. Available online: https://www.mathworks.com/help/deeplearning/ref/trainlm.html;jsessionid=9264db9498e7877e053dc5648f1a (accessed on 2 February 2021).

**Figure 1.**(

**a**) One year of hourly load demand at a Baneshwor substation (from April 2018 to April 2019). (

**b**) Zoomed in section of electricity consumption in October (lower consumption). (

**c**) Zoomed in section of electricity consumption in January (high consumption).

**Figure 5.**(

**a**) Joint plot of the electric load vs. temperature. (

**b**) Monthly mean plot of the electric load and temperature. (

**c**) Mean plot of the temperature vs. electric load.

**Figure 10.**Actual vs. predicted forecasts achieved by conventional time series models. (

**a**) Weekday forecasting. (

**b**) Weekend forecasting.

**Figure 12.**Actual vs. predicted forecasts achieved by the ANN models with (

**a**) a double-layer 16 × 16 node structure and (

**b**) a single-layer 8 node structure.

No. | Model | Parameters (Weekdays) |
---|---|---|

1 | Moving Average | Lag load = 4 (4-day lag) |

2 | Weighted Moving Average | Lag Load = 4 (${W}_{1}=0.4,{W}_{2}=0.3,{W}_{3}=0.2,{W}_{4}=0.1$) |

3 | Exponential Smoothing | $\mathsf{\alpha}=0.15$ |

4 | Holt’s (Double Exponential) | $\mathsf{\alpha}=0.14,$ $\mathsf{\beta}=0.08$ |

No. | Model | MAPE % (Weekdays) | MAPE % (Weekends) |
---|---|---|---|

1 | Moving Average | 3.33 | 13.42 |

2 | Weighted Moving Average | 3.4 | 13.66 |

3 | Exponential Smoothing | 3.56 | 12.59 |

4 | Holt’s (Double Exponential) | 3.44 | 12.57 |

No. | Variable | Indicator |
---|---|---|

1 | Month | 1, 2, 3…, 12 |

2 | Day of the Month | 1, 2, 3, …, 30, 31 |

3 | Week | Sunday-1, Monday-2… Saturday-7 |

4 | Hour of Day | 0, 1, 2, 3…, 23 |

5 | Weekday, Weekend | 1, 0, |

6 | Previous Day’s Load | L1(t-24), L2(t-25)… L1(t-47) |

7 | Same Day of the Previous Week | L1(t-24 × 7)… L24(t-47 × 7) |

8 | Temperature | T(t) |

No. of Hidden Layers | No. of Neurons | MAPE % (Weekends) | MAPE % (Weekdays) |
---|---|---|---|

1 | 32 | 4.89 | 3.22 |

16 | 4.699 | 3.14 | |

8 | 5.08 | 2.99 | |

4 | 6.07 | 3.04 | |

2 | 7.16 | 4.77 | |

1 | 13.38 | 12.08 | |

2 | 2 × 2 | 7.06 | 3.96 |

4 × 4 | 4.76 | 3.26 | |

8 × 8 | 4.76 | 3.63 | |

16 × 16 | 4.53 | 3.04 | |

3 | 8 × 8 × 8 | 4.90 | 3.39 |

16 × 16 × 16 | 4.54 | 3.35 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 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 (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Rajbhandari, Y.; Marahatta, A.; Ghimire, B.; Shrestha, A.; Gachhadar, A.; Thapa, A.; Chapagain, K.; Korba, P.
Impact Study of Temperature on the Time Series Electricity Demand of Urban Nepal for Short-Term Load Forecasting. *Appl. Syst. Innov.* **2021**, *4*, 43.
https://doi.org/10.3390/asi4030043

**AMA Style**

Rajbhandari Y, Marahatta A, Ghimire B, Shrestha A, Gachhadar A, Thapa A, Chapagain K, Korba P.
Impact Study of Temperature on the Time Series Electricity Demand of Urban Nepal for Short-Term Load Forecasting. *Applied System Innovation*. 2021; 4(3):43.
https://doi.org/10.3390/asi4030043

**Chicago/Turabian Style**

Rajbhandari, Yaju, Anup Marahatta, Bishal Ghimire, Ashish Shrestha, Anand Gachhadar, Anup Thapa, Kamal Chapagain, and Petr Korba.
2021. "Impact Study of Temperature on the Time Series Electricity Demand of Urban Nepal for Short-Term Load Forecasting" *Applied System Innovation* 4, no. 3: 43.
https://doi.org/10.3390/asi4030043