# Ensemble Prediction Approach Based on Learning to Statistical Model for Efficient Building Energy Consumption Management

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

- Provide different time-series analysis of energy consumption data of multifamily residential buildings, South Korea, to highlight hidden insights and characteristics for stakeholders to devise effective policies.
- Integration of deep learning and statistical models to forecast short-term energy consumption using time-series data collected from multifamily residential buildings, South Korea.
- Experimental results demonstrate that the proposed ensemble prediction approach produces better generalization and outperforms standalone models, such as LSTM and KF.
- Comparative analysis is also given to highlight the significance of the proposed model compared to standalone models.

## 2. Related Work

## 3. Proposed Ensemble Prediction Approach Based on Learning to Statistical Model

#### Proposed Ensemble Prediction Model Architecture

## 4. Time Series Analysis of Building Energy Consumption Data

#### 4.1. Residential Building Energy Consumption Data

#### 4.2. Data Preprocessing/Cleaning

#### 4.3. Time Series Analysis

#### 4.4. Correlation Analysis

## 5. Ensemble Prediction Approach for Efficient Building Energy Management

#### 5.1. LSTM Model

#### 5.2. Kalman Filter

#### 5.3. Proposed Ensemble Prediction Model

## 6. Experimentation Environment, Results, and Performance Analysis

#### 6.1. Experimentation Environment

#### 6.2. Short-Term Energy Consumption Demands’ Prediction Results

#### 6.3. Feature Importance

#### 6.4. Performance Evaluation

## 7. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Ahmad, M.W.; Mourshed, M.; Rezgui, Y. Trees vs. Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption. Energy Build.
**2017**, 147, 77–89. [Google Scholar] [CrossRef] - Connolly, R.; Connolly, M.; Carter, R.M.; Soon, W. How Much Human-Caused Global Warming Should We Expect with Business-As-Usual (BAU) Climate Policies? A Semi-Empirical Assessment. Energies
**2020**, 13, 1365. [Google Scholar] [CrossRef] [Green Version] - Penya, Y.K.; Borges, C.E.; Fernández, I. Short-term load forecasting in non-residential buildings. In Proceedings of the IEEE Africon’11, Victoria Falls, Zambia, 13–15 September 2011; pp. 1–6. [Google Scholar]
- Deb, C.; Zhang, F.; Yang, J.; Lee, S.E.; Shah, K.W. A review on time series forecasting techniques for building energy consumption. Renew. Sustain. Energy Rev.
**2017**, 74, 902–924. [Google Scholar] [CrossRef] - Khan, P.W.; Byun, Y.C.; Lee, S.J.; Park, N. Machine Learning Based Hybrid System for Imputation and Efficient Energy Demand Forecasting. Energies
**2020**, 13, 2681. [Google Scholar] [CrossRef] - Alvarez, F.M.; Troncoso, A.; Riquelme, J.C.; Ruiz, J.S.A. Energy time series forecasting based on pattern sequence similarity. IEEE Trans. Knowl. Data Eng.
**2010**, 23, 1230–1243. [Google Scholar] [CrossRef] - Iqbal, N.; Jamil, F.; Ahmad, S.; Kim, D. Toward Effective Planning and Management Using Predictive Analytics Based on Rental Book Data of Academic Libraries. IEEE Access
**2020**, 8, 81978–81996. [Google Scholar] [CrossRef] - Singh, S.; Yassine, A. Big data mining of energy time series for behavioral analytics and energy consumption forecasting. Energies
**2018**, 11, 452. [Google Scholar] [CrossRef] [Green Version] - Gridach, M. Character-level neural network for biomedical named entity recognition. J. Biomed. Inform.
**2017**, 70, 85–91. [Google Scholar] [CrossRef] - Ahmad, N.; Han, L.; Iqbal, K.; Ahmad, R.; Abid, M.A.; Iqbal, N. SARM: Salah activities recognition model based on smartphone. Electronics
**2019**, 8, 881. [Google Scholar] [CrossRef] [Green Version] - Jamil, F.; Iqbal, N.; Ahmad, S.; Kim, D.H. Toward accurate position estimation using learning to prediction algorithm in indoor navigation. Sensors
**2020**, 20, 4410. [Google Scholar] [CrossRef] [PubMed] - Ahmad, S.; Iqbal, N.; Jamil, F.; Kim, D. Optimal Policy-Making for Municipal Waste Management Based on Predictive Model Optimization. IEEE Access
**2020**, 8, 218458–218469. [Google Scholar] [CrossRef] - Sutskever, I.; Vinyals, O.; Le, Q.V. Sequence to sequence learning with neural networks. Adv. Neural Inf. Process. Syst.
**2014**, 27, 3104–3112. [Google Scholar] - Bengio, Y.; Courville, A.; Vincent, P. Representation learning: A review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell.
**2013**, 35, 1798–1828. [Google Scholar] [CrossRef] - Rahman, A.; Srikumar, V.; Smith, A.D. Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks. Appl. Energy
**2018**, 212, 372–385. [Google Scholar] [CrossRef] - Kong, W.; Dong, Z.Y.; Jia, Y.; Hill, D.J.; Xu, Y.; Zhang, Y. Short-term residential load forecasting based on LSTM recurrent neural network. IEEE Trans. Smart Grid
**2017**, 10, 841–851. [Google Scholar] [CrossRef] - Ullah, I.; Fayaz, M.; Kim, D. Improving accuracy of the kalman filter algorithm in dynamic conditions using ANN-based learning module. Symmetry
**2019**, 11, 94. [Google Scholar] [CrossRef] [Green Version] - Ecotect. Available online: https://web.archive.org/web/20080724093511/http://squ1.com/products/ecotect/ (accessed on 20 December 2020).
- Energy Plus. Available online: https://energyplus.net/ (accessed on 20 December 2020).
- DOE2. Available online: https://www.doe2.com/ (accessed on 20 December 2020).
- Integrated Environmental Solutions (IES). Available online: https://www.iesve.com/ (accessed on 20 December 2020).
- Esen, H.; Esen, M.; Ozsolak, O. Modelling and experimental performance analysis of solar-assisted ground source heat pump system. J. Exp. Theor. Artif. Intell.
**2017**, 29, 1–17. [Google Scholar] [CrossRef] - Bourdeau, M.; Zhai, X.Q.; Nefzaoui, E.; Guo, X.; Chatellier, P. Modeling and forecasting building energy consumption: A review of data-driven techniques. Sustain. Cities Soc.
**2019**, 48, 101533. [Google Scholar] [CrossRef] - Christiaanse, W. Short-term load forecasting using general exponential smoothing. IEEE Trans. Power Appar. Syst.
**1971**, 2, 900–911. [Google Scholar] [CrossRef] - Pappas, S.S.; Ekonomou, L.; Karamousantas, D.C.; Chatzarakis, G.; Katsikas, S.; Liatsis, P. Electricity demand loads modeling using AutoRegressive Moving Average (ARMA) models. Energy
**2008**, 33, 1353–1360. [Google Scholar] [CrossRef] - Papalexopoulos, A.D.; Hesterberg, T.C. A regression-based approach to short-term system load forecasting. IEEE Trans. Power Syst.
**1990**, 5, 1535–1547. [Google Scholar] [CrossRef] - Amjady, N. Short-term hourly load forecasting using time-series modeling with peak load estimation capability. IEEE Trans. Power Syst.
**2001**, 16, 498–505. [Google Scholar] [CrossRef] - Chae, Y.T.; Horesh, R.; Hwang, Y.; Lee, Y.M. Artificial neural network model for forecasting sub-hourly electricity usage in commercial buildings. Energy Build.
**2016**, 111, 184–194. [Google Scholar] [CrossRef] - Quilumba, F.L.; Lee, W.J.; Huang, H.; Wang, D.Y.; Szabados, R.L. Using smart meter data to improve the accuracy of intraday load forecasting considering customer behavior similarities. IEEE Trans. Smart Grid
**2014**, 6, 911–918. [Google Scholar] [CrossRef] - Dong, B.; Li, Z.; Rahman, S.M.; Vega, R. A hybrid model approach for forecasting future residential electricity consumption. Energy Build.
**2016**, 117, 341–351. [Google Scholar] [CrossRef] - Paudel, S.; Elmitri, M.; Couturier, S.; Nguyen, P.H.; Kamphuis, R.; Lacarrière, B.; Le Corre, O. A relevant data selection method for energy consumption prediction of low energy building based on support vector machine. Energy Build.
**2017**, 138, 240–256. [Google Scholar] [CrossRef] - Jozi, A.; Pinto, T.; Praça, I.; Ramos, S.; Vale, Z.; Goujon, B.; Petrisor, T. Energy consumption forecasting using neuro-fuzzy inference systems: Thales TRT building case study. In Proceedings of the 2017 IEEE Symposium Series on Computational Intelligence (SSCI), Honolulu, HI, USA, 27 November–1 December 2017; pp. 1–5. [Google Scholar]
- Bagis, A. Fuzzy rule base design using tabu search algorithm for nonlinear system modeling. ISA Trans.
**2008**, 47, 32–44. [Google Scholar] [CrossRef] - Hinton, G.E.; Osindero, S.; Teh, Y.W. A fast learning algorithm for deep belief nets. Neural Comput.
**2006**, 18, 1527–1554. [Google Scholar] [CrossRef] - Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput.
**1997**, 9, 1735–1780. [Google Scholar] [CrossRef] [PubMed] - Urban, G.; Geras, K.J.; Kahou, S.E.; Aslan, O.; Wang, S.; Caruana, R.; Mohamed, A.; Philipose, M.; Richardson, M. Do deep convolutional nets really need to be deep and convolutional? arXiv
**2016**, arXiv:1603.05691. [Google Scholar] - Dedinec, A.; Filiposka, S.; Dedinec, A.; Kocarev, L. Deep belief network based electricity load forecasting: An analysis of Macedonian case. Energy
**2016**, 115, 1688–1700. [Google Scholar] [CrossRef] - Mocanu, E.; Nguyen, P.H.; Gibescu, M.; Kling, W.L. Deep learning for estimating building energy consumption. Sustain. Energy Grids Netw.
**2016**, 6, 91–99. [Google Scholar] [CrossRef] - El-Sharkh, M.Y.; Rahman, M.A. Forecasting electricity demand using dynamic artificial neural network model. In Proceedings of the 2012 International Conference on Industrial Engineering and Operations Management, Istanbul, Turkey, 3–6 July 2012; pp. 3–6. [Google Scholar]
- Qiu, X.; Zhang, L.; Ren, Y.; Suganthan, P.N.; Amaratunga, G. Ensemble deep learning for regression and time series forecasting. In Proceedings of the 2014 IEEE Symposium on Computational Intelligence in Ensemble Learning (CIEL), Singapore, 9–12 December 2014; pp. 1–6. [Google Scholar]
- Li, P.; Li, Y.; Xiong, Q.; Chai, Y.; Zhang, Y. Application of a hybrid quantized Elman neural network in short-term load forecasting. Int. J. Electr. Power Energy Syst.
**2014**, 55, 749–759. [Google Scholar] [CrossRef] - Ertugrul, Ö.F. Forecasting electricity load by a novel recurrent extreme learning machines approach. Int. J. Electr. Power Energy Syst.
**2016**, 78, 429–435. [Google Scholar] [CrossRef] - Mandal, P.; Senjyu, T.; Urasaki, N.; Funabashi, T. A neural network based several-hour-ahead electric load forecasting using similar days approach. Int. J. Electr. Power Energy Syst.
**2006**, 28, 367–373. [Google Scholar] [CrossRef] - Marino, D.L.; Amarasinghe, K.; Manic, M. Building energy load forecasting using deep neural networks. In Proceedings of the IECON 2016-42nd Annual Conference of the IEEE Industrial Electronics Society, Florence, Italy, 24–27 October 2016; pp. 7046–7051. [Google Scholar]
- Tian, C.; Ma, J.; Zhang, C.; Zhan, P. A deep neural network model for short-term load forecast based on long short-term memory network and convolutional neural network. Energies
**2018**, 11, 3493. [Google Scholar] [CrossRef] [Green Version] - Singh, P.; Dwivedi, P. Integration of new evolutionary approach with artificial neural network for solving short term load forecast problem. Appl. Energy
**2018**, 217, 537–549. [Google Scholar] [CrossRef] - Nowotarski, J.; Liu, B.; Weron, R.; Hong, T. Improving short term load forecast accuracy via combining sister forecasts. Energy
**2016**, 98, 40–49. [Google Scholar] [CrossRef] - Jamil, F.; Iqbal, N.; Imran; Ahmad, S.; Kim, D. Peer-to-Peer Energy Trading Mechanism based on Blockchain and Machine Learning for Sustainable Electrical Power Supply in Smart Grid. IEEE Access
**2021**. [Google Scholar] [CrossRef] - Al-Hamadi, H.; Soliman, S. Fuzzy short-term electric load forecasting using Kalman filter. IEE Proc. Gener. Transm. Distrib.
**2006**, 153, 217–227. [Google Scholar] [CrossRef] - Stavrakakis, S.A.M.G.S.; Nikolaou, T.G. Short-term load forecasting based on the Kalman filter and the neural-fuzzy network (ANFIS). In Proceedings of the 2006 IASME/WSEAS International Conference on Energy & Environmental Systems, GREECE, Canary Islands, Spain, 16–18 December 2006; Volume 1, pp. 189–193. [Google Scholar]
- Jung, H.W.; Song, K.B.; Park, J.D.; Park, R.J. Very short-term electric load forecasting for real-time power system operation. J. Electr. Eng. Technol.
**2018**, 13, 1419–1424. [Google Scholar] - Takeda, H.; Tamura, Y.; Sato, S. Using the ensemble Kalman filter for electricity load forecasting and analysis. Energy
**2016**, 104, 184–198. [Google Scholar] [CrossRef] - Hu, Z.; Ma, J.; Yang, L.; Yao, L.; Pang, M. Monthly electricity demand forecasting using empirical mode decomposition-based state space model. Energy Environ.
**2019**, 30, 1236–1254. [Google Scholar] [CrossRef] - Chujai, P.; Kerdprasop, N.; Kerdprasop, K. Time series analysis of household electric consumption with ARIMA and ARMA models. In Proceedings of the International MultiConference of Engineers and Computer Scientists, Hong Kong, China, 13–15 March 2013; Volume 1, pp. 295–300. [Google Scholar]
- Steyerberg, E.W.; Harrell, F.E., Jr.; Borsboom, G.J.; Eijkemans, M.; Vergouwe, Y.; Habbema, J.D.F. Internal validation of predictive models: Efficiency of some procedures for logistic regression analysis. J. Clin. Epidemiol.
**2001**, 54, 774–781. [Google Scholar] [CrossRef] - Iqbal, N.; Jamil, F.; Ahmad, S.; Kim, D. A Novel Blockchain-based Integrity and Reliable Veterinary Clinic Information Management System using Predictive Analytics for Provisioning of Quality Health Services. IEEE Access
**2021**, 9, 8069–8098. [Google Scholar] [CrossRef]

**Figure 8.**Seasonal-based percentage analysis of electric energy consumption (January 2010–January 2011).

**Figure 13.**Comparative analysis of actual and predicted hourly energy consumption requirements using KF.

**Figure 14.**Comparative analysis of actual and predicted hourly energy consumption requirements using LSTM.

**Figure 15.**Comparative analysis of actual and predicted hourly energy consumption requirements using the proposed ensemble prediction model.

**Figure 19.**MAPE-based comparison of the proposed ensemble approach and traditional ML energy prediction models.

Model | Dataset | Types of Prediciton | MAPE (%) | Objective |
---|---|---|---|---|

Ensemble [1] | Weather and Time-Series Data | Heating and cooling energy consumption (Non-Residential) | 4.97 | Ensemble model to deal with multi-dimensional complex data |

AR [3] | Weather and Time-Series Data | Overall energy consumption (Non-Residential) | 6.10 | Forecast energy hourly load of non-residential buildings using ARIMA and NN |

Hybrid [30] | Energy consumption and building details | Overall energy consumption (Residential Single Family) | 5.30 | Integrated data-driven method with a physical model to forecast hourly and daily energy consumption |

ANN [28] | Weather, Time-Series, and Operational | Commercial buildings energy prediction | 9.09 | Developed ANN-based energy forecasting model to predict short-term energy consumption |

DBN [37] | Time-Series | Electric power systems of Macedonian | 8.6 | Developed DBN model to predict short-term electricity load and analyzed electricity consumptions of Macedonia city to extract hidden insights |

FCRMB [38] | Time-Series | Energy Demand Consumption (Multifamily Residential) | 8.60 | Stochastic models were developed to analyze time-series data of energy consumption to forecast short-term energy load |

HQENN [41] | Weather and Time-Series | Predict electricity load | – | Evolutionary technique is used to develop robust ANN model to forecast short-term energy load |

RELM [42] | Time Series electric consumption data | Electric load forecasting | Developed RLEM model to forecast energy consumption load to facilitate energy providers | |

S2S LSTM architecture [44] | Historical electric consumption data | Short term load forecasting | – | Deep learning based approach was proposed to predict power load to facilitate policymakers. |

ANN-FTL [46] | Historical load and weather data | Short term load forecasting for load commercial market | 3.30 | Evolutionary algorithm was used to predict power load to help power distribution organizations |

Season | Percentage (%) |
---|---|

Winter | 27.20 |

Spring | 24.50 |

Summer | 25.70 |

Autumn | 22.60 |

System Components | Description |
---|---|

Operating System | Microsoft Windows 10 (64-bits) |

CPU | Intel^{®} Core™ i5-4300 CPU at 3.40 GHz |

RAM | 16 GB |

Programming Language | Python |

Storage | MySQL and MS Excel |

IDE | PyCharm Professional |

Model | MAE | RMSE | MAPE | R2 Score |
---|---|---|---|---|

Kalman Filter | 740.790 | 928.770 | 5.000 | 0.922 |

LSTM | 557.960 | 695.552 | 3.925 | 0.956 |

Proposed Model | 373.580 | 487 | 3.264 | 0.966 |

**Table 5.**Performance evaluation and comparison of proposed ensemble approach with conventional ensemble prediction models.

Model | MAE | RMSE | MAPE | R2 Score |
---|---|---|---|---|

RF | 2095.669 | 2624.76 | 15.54 | 0.089 |

XGBoost | 2083.946 | 2623.99 | 15.48 | 0.090 |

AdaBoost | 2038.337 | 2683.314 | 15.80 | 0.048 |

GB | 2039.429 | 2640.467 | 15.50 | 0.079 |

Proposed Model | 373.580 | 487 | 3.264 | 0.966 |

**Table 6.**Performance evaluation and comparison of proposed ensemble approach with conventional ML-based energy prediction models.

Model | MAE | RMSE | MAPE | R2 Score |
---|---|---|---|---|

SVR | 2495.188 | 3197.90 | 20.14 | −0.352 |

L1 Regularization | 2118.817 | 2701.68 | 15.68 | 0.035 |

L2 Regularization | 2103.325 | 2788.46 | 16.46 | −0.028 |

Elastic Net | 2159.134 | 2751.16 | 15.87 | −0.0 |

Proposed Model | 373.580 | 487 | 3.264 | 0.966 |

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 (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Khan, A.N.; Iqbal, N.; Ahmad, R.; Kim, D.-H.
Ensemble Prediction Approach Based on Learning to Statistical Model for Efficient Building Energy Consumption Management. *Symmetry* **2021**, *13*, 405.
https://doi.org/10.3390/sym13030405

**AMA Style**

Khan AN, Iqbal N, Ahmad R, Kim D-H.
Ensemble Prediction Approach Based on Learning to Statistical Model for Efficient Building Energy Consumption Management. *Symmetry*. 2021; 13(3):405.
https://doi.org/10.3390/sym13030405

**Chicago/Turabian Style**

Khan, Anam Nawaz, Naeem Iqbal, Rashid Ahmad, and Do-Hyeun Kim.
2021. "Ensemble Prediction Approach Based on Learning to Statistical Model for Efficient Building Energy Consumption Management" *Symmetry* 13, no. 3: 405.
https://doi.org/10.3390/sym13030405