The wide use of sensor and information technologies in buildings resulted in the massive generation of data related to its operation. Thus, there is a need for identifying patterns in data that they may use for the optimal operation of the buildings. The case of non-residential building characteristically provides a big volume of data whose analysis requires computational efficient methods. In this paper, we introduce a new big data analytic method that is applicable to forecasting energy demand in non-residential buildings. The goal is to make energy forecasts in a two-dimensional (2D) space defined by i) the electricity load and ii) gas demand. The proposed method combines the matrix profile (MP) method with a Long-Short Term Memory (LSTM) neural network. The combination of the above tools provides an efficient method in 2D hour ahead forecasting with the big data environment of smart buildings. In specific, with respect to mean average percentage error (MAPE) the combined MP-LSTM method provides a concurrent forecast of electricity and gas around 3% and 4%, respectively.
TsoukalasLHGaoR. From smart grids to an energy internet: Assumptions, architectures and requirements. In: 2008 Third international conference on electric utility deregulation and restructuring and power technologies. 2008 Apr 6. IEEE; pp. 94-98. doi: 10.1109/DRPT.2008.4523385.
2.
DimitroulisPAlamaniotisM. Residential energy management system utilizing fuzzy based decision-making. In: 2020 IEEE Texas Power and Energy Conference (TPEC). 2020 Feb 6. IEEE; pp. 1-6. doi: 10.1109/TPEC48276.2020.9042571.
3.
Al-AliARZualkernanIARashidMGuptaRAliKararM. A smart home energy management system using IoT and big data analytics approach. IEEE Transactions on Consumer Electronics. 2017 Nov; 63(4): 426-34. doi: 10.1109/TCE.2017.015014.
4.
SuHZioEZhangJXuMLiXZhangZ. A hybrid hourly natural gas demand forecasting method based on the integration of wavelet transform and enhanced Deep-RNN model. Energy. 2019 Jul 1; 178: 585-97. doi: 10.1016/j.energy.2019.04.167.
5.
AlamaniotisM. Synergism of deep neural network and elm for smart very-short-term load forecasting. In: 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe). 2019 Sep 29. IEEE; pp. 1-5. doi: 10.1109/ISGTEurope.2019.8905686.
6.
PrakashVFontenotHKhanAADongBAlamaniotisM. Ensemble Method for Short-Term Load Forecasting Using LSTM, SVR, and FFNN Taking into Account Seasonal Dependency. ASHRAE Transactions. 2020 Jan 1; 126(1).
7.
AlamaniotisMIkonomopoulosATsoukalasLH. Evolutionary multiobjective optimization of kernel-based very-short-term load forecasting. IEEE Transactions on Power Systems. 2012 Feb 17; 27(3): 1477-84. doi: 10.1109/TPWRS.2012.2184308.
8.
AlamaniotisMIkonomopoulosATsoukalasLH. A Pareto optimization approach of a Gaussian process ensemble for short-term load forecasting. In: 2011 16th International Conference on Intelligent System Applications to Power Systems. 2011 Sep 25. IEEE; pp. 1-6. doi: 10.1109/ISAP.2011.6082231.
9.
NichiforovCStamatescuGStamatescuICalofirVFagarasanIIliescuSS. Deep learning techniques for load forecasting in large commercial buildings. In: 2018 22nd international conference on system theory, control and computing (ICSTCC). 2018 Oct 10. IEEE; pp. 492-497. doi: 10.1109/ICSTCC.2018.8540768.
10.
NichiforovCStamatescuGStamatescuIFăgărăşanI. Evaluation of sequence-learning models for large-commercial-building load forecasting. Information. 2019 Jun 1; 10(6): 189. doi: 10.1109/ICSTCC.2018.8540768.
11.
NichiforovCStancuIStamatescuIStamatescuG. Information extraction approach for energy time series modelling. In: 2020 24th International Conference on System Theory, Control and Computing (ICSTCC). 2020 Oct 8. IEEE; pp. 886-891. doi: 10.1109/ICSTCC50638.2020.9259635.
12.
JiaoRZhangTJiangYHeH. Short-term non-residential load forecasting based on multiple sequences LSTM recurrent neural network. IEEE Access. 2018 Oct 4; 6: 59438-48. doi: 10.1109/ACCESS.2018.2873712.
13.
CiullaGD’AmicoA. Building energy performance forecasting: A multiple linear regression approach. Applied Energy. 2019 Nov 1; 253: 113500. doi: 10.1016/j.apenergy.2019.
14.
MassanaJPousCBurgasLMelendezJColomerJ. Short-term load forecasting for non-residential buildings contrasting artificial occupancy attributes. Energy and Buildings. 2016 Oct 15; 130: 519-31. doi: 10.1016/j.enbuild.2016.08.081.
15.
SeyedzadehSRahimianFPGleskIRoperM. Machine learning for estimation of building energy consumption and performance: a review. Visualization in Engineering. 2018 Dec; 6(1): 1-20. doi: 10.1186/s40327-018-0064-7.
16.
FathiSSrinivasanRFennerAFathiS. Machine learning applications in urban building energy performance forecasting: A systematic review. Renewable and Sustainable Energy Reviews. 2020 Nov 1; 133: 110287. doi: 10.1016/j.rser.2020.
17.
MocanuENguyenPHGibescuMKlingWL. Deep learning for estimating building energy consumption. Sustainable Energy, Grids and Networks2016 Jun 1; 6: 91-9.
18.
LeTVoMTKieuTHwangERhoSBaikSW. Multiple electric energy consumption forecasting using a cluster-based strategy for transfer learning in smart building. Sensors. 2020 Jan; 20(9): 2668. doi: 10.3390/s20092668.
19.
YehCCZhuYUlanovaLBegumNDingYDauHASilvaDFMueenAKeoghE. Matrix profile I: all pairs similarity joins for time series: a unifying view that includes motifs, discords and shapelets. In: 2016 IEEE 16th international conference on data mining (ICDM). 2016 Dec 12. IEEE; pp. 1317-1322. doi: 10.1109/ICDM.2016.0179.
20.
MarinoDLAmarasingheKManicM. Building energy load forecasting using deep neural networks. In: IECON 2016-42nd Annual Conference of the IEEE Industrial Electronics Society. 2016 Oct 23. IEEE; pp. 7046-7051. doi: 10.1109/IECON.2016.7793413.
21.
HochreiterSSchmidhuberJ. Long short-term memory. Neural computation. 1997 Nov 15; 9(8): 1735-80. doi: 10.1162/neco..
22.
YangSYuXZhouY. Lstm and gru neural network performance comparison study: Taking yelp review dataset as an example. In: 2020 International workshop on electronic communication and artificial intelligence (IWECAI). 2020 Jun 12. IEEE; pp. 98-101. doi: 10.1109/IWECAI50956.2020.00027.
23.
MillerCMeggersF. The Building Data Genome Project: An open, public data set from non-residential building electrical meters. Energy Procedia. 2017 Sep 1; 122: 439-44.
24.
Van BenschotenAHOuyangABischoffFMarrsTW. MPA: a novel cross-language API for time series analysis. Journal of Open Source Software. 2020 May 10; 5(49): 2179. doi: 10.21105/joss.02179.
25.
KingmaDPBaJ. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. 2014 Dec 22.
