A novel short-term load forecasting framework based on time-series clustering and early classification algorithm

Abstract With the development of data-driven models, extracting information from historical data for better energy forecasting is critically important for energy planning and optimization in buildings. Feature engineering is a key factor in improving the performance of forecasting models. Adding load pattern labels for different daily energy consumption patterns resulting from different time schedules and weather conditions can help improve forecasting accuracy. Traditionally, pattern labeling focuses mainly on finding a day similar to the forecasting day based on calendar or other information, such as weather conditions. The most intuitive approach for dividing historical time-series load into patterns is clustering; however, the pattern cannot be determined before the load is known. To address this problem, this study proposes a novel short-term load forecasting framework integrating an early classification algorithm that uses a stochastic algorithm to predetermine the load pattern of a forecasting day. In addition, a hybrid multistep method combining the strengths of single-step forecasting and recursive multistep forecasting is integrated into the framework. The proposed framework was validated through a case study using actual metered data. The results demonstrate that the early classification and proposed labeling strategy produce satisfactory forecasting accuracy and significantly improve the forecasting performance of the LightGBM model.

[1]  Duane Robinson,et al.  A data-driven strategy to forecast next-day electricity usage and peak electricity demand of a building portfolio using cluster analysis, Cubist regression models and Particle Swarm Optimization , 2020, Journal of Cleaner Production.

[2]  Ying Chen,et al.  Day-ahead high-resolution forecasting of natural gas demand and supply in Germany with a hybrid model , 2020, Applied Energy.

[3]  Antoine Cornuéjols,et al.  Early Classification of Time Series as a Non Myopic Sequential Decision Making Problem , 2015, ECML/PKDD.

[4]  Tomonobu Senjyu,et al.  A neural network based several-hour-ahead electric load forecasting using similar days approach , 2006 .

[5]  Georgios Giasemidis,et al.  Short term load forecasting and the effect of temperature at the low voltage level , 2019, International Journal of Forecasting.

[6]  Shahaboddin Shamshirband,et al.  Computational Intelligence on Short-Term Load Forecasting: A Methodological Overview , 2019, Energies.

[7]  P. Xu,et al.  Experimental investigation of demand response potential of buildings: Combined passive thermal mass and active storage , 2020 .

[8]  Tao Hong,et al.  Probabilistic electric load forecasting: A tutorial review , 2016 .

[9]  Benjamin C. M. Fung,et al.  A review of the-state-of-the-art in data-driven approaches for building energy prediction , 2020 .

[10]  Jionglong Su,et al.  Kalman filter based time series prediction of cake factory daily sale , 2017, 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[11]  Krithi Ramamritham,et al.  A deep learning framework for building energy consumption forecast , 2021 .

[12]  Fabrizio Sossan,et al.  Hierarchical Demand Forecasting Benchmark for the Distribution Grid , 2019, ArXiv.

[13]  Sahm Kim,et al.  Short term electricity load forecasting for institutional buildings , 2019, Energy Reports.

[14]  Casper Solheim Bojer,et al.  Kaggle forecasting competitions: An overlooked learning opportunity , 2020, ArXiv.

[15]  Nils Jakob Johannesen,et al.  Relative evaluation of regression tools for urban area electrical energy demand forecasting , 2019, Journal of Cleaner Production.

[16]  Yuanyuan Wang,et al.  Short-Term Load Forecasting for Industrial Customers Based on TCN-LightGBM , 2020, IEEE Transactions on Power Systems.

[17]  Dongho Lee,et al.  Low-cost and simple short-term load forecasting for energy management systems in small and middle-sized office buildings , 2020 .

[18]  Shengwei Wang,et al.  Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques , 2014 .

[19]  Mary Ann Piette,et al.  Building thermal load prediction through shallow machine learning and deep learning , 2020, Applied Energy.

[20]  Pierluigi Siano,et al.  A comparative study of clustering techniques for electrical load pattern segmentation , 2020, Renewable and Sustainable Energy Reviews.

[21]  Sudhansu Kumar Mishra,et al.  A Review of Short Term Load Forecasting using Artificial Neural Network Models , 2015 .

[22]  Hongchun Shu,et al.  State-of-the-art one-stop handbook on wind forecasting technologies: An overview of classifications, methodologies, and analysis , 2020 .

[23]  Weilin Li,et al.  Short-term electrical load forecasting using the Support Vector Regression (SVR) model to calculate the demand response baseline for office buildings , 2017 .

[24]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[25]  Youssef Fakhri,et al.  A Comparative Study of Predictive Approaches for Load Forecasting in Smart Buildings , 2019, EUSPN/ICTH.

[26]  Tianrui Li,et al.  Multivariate time series forecasting via attention-based encoder-decoder framework , 2020, Neurocomputing.

[27]  Jing Liu,et al.  Multi-step ahead forecasting of heat load in district heating systems using machine learning algorithms , 2019 .

[28]  Qiang Zhang,et al.  Model input selection for building heating load prediction: A case study for an office building in Tianjin , 2018 .

[29]  Taehoon Hong,et al.  An estimation model for determining the annual energy cost budget in educational facilities using SARIMA (seasonal autoregressive integrated moving average) and ANN (artificial neural network) , 2014 .

[30]  Yi Wang,et al.  Load probability density forecasting by transforming and combining quantile forecasts , 2020, Applied Energy.

[31]  Siem Jan Koopman,et al.  Dynamic factor models with clustered loadings: Forecasting education flows using unemployment data , 2021 .

[32]  R. L. Thorndike.  Who belongs in the family? , 1953 .

[33]  Pierre Gançarski,et al.  A global averaging method for dynamic time warping, with applications to clustering , 2011, Pattern Recognit..

[34]  Long Chen,et al.  Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation , 2017 .

[35]  Inderjit S. Dhillon,et al.  Kernel k-means: spectral clustering and normalized cuts , 2004, KDD.

[36]  Hongyu Lin,et al.  Combined electricity-heat-cooling-gas load forecasting model for integrated energy system based on multi-task learning and least square support vector machine , 2020 .

[37]  Saifur Rahman,et al.  Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques , 2019, Applied Energy.

[38]  Hongzhan Nie,et al.  Hybrid of ARIMA and SVMs for Short-Term Load Forecasting , 2012 .

[39]  Pandarasamy Arjunan,et al.  Islands of misfit buildings: Detecting uncharacteristic electricity use behavior using load shape clustering , 2021 .

[40]  G. R. Gangadharan,et al.  Trendlets: A novel probabilistic representational structures for clustering the time series data , 2020, Expert Syst. Appl..