Assessment of aggregation strategies for machine-learning based short-term load forecasting

Abstract Effective short-term load forecasting (STLF) plays an important role in power system operations. It is challenging to identify an ML model that has the outperformance in all scenarios. Therefore, there are a number of aggregation strategies developed to improve STLF. However, the superiority of these aggregation strategies has not been assessed. In this paper, STLF with three aggregation strategies are developed, which are information aggregation (IA), model aggregation (MA), and hierarchy aggregation (HA). The IA, MA, and HA strategies aggregate inputs, models, and forecasts at the pre-forecasting, model-building, or post-forecasting stage, respectively. To verify the effectiveness of the three aggregation strategies, a set of 10 models based on 4 machine-learning algorithms are developed in each aggregation category to predict 1-hour-ahead load. Case studies show that: (i) STLF-IA presents superior performance than STLF with weather data and STLF with individual load data consistently, and the performance can be further enhanced by the recursive feature elemination (RFE) feature selection method; (ii) MA improves the STLF robustness by reducing the risk of unsatisfactory single-algorithm STLF models; and (iii) STLF-HA produces the most accurate forecasts with a 0.83% normalized mean absolute error and a 1.35% mean absolute percentage error, while keeping hierarchical aggregate consistency.

[1]  Lachlan L. H. Andrew,et al.  Short-term residential load forecasting: Impact of calendar effects and forecast granularity , 2017 .

[2]  Nadeem Javaid,et al.  An Accurate and Fast Converging Short-Term Load Forecasting Model for Industrial Applications in a Smart Grid , 2017, IEEE Transactions on Industrial Informatics.

[3]  Jie Zhang,et al.  Characterizing Time Series Data Diversity for Wind Forecasting , 2017, BDCAT.

[4]  Oliver Kramer,et al.  Wind Power Ramp Event Prediction with Support Vector Machines , 2014, HAIS.

[5]  Chun Zhang,et al.  Feature selection of power system transient stability assessment based on random forest and recursive feature elimination , 2016, 2016 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC).

[6]  José Manuel Benítez,et al.  Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS , 2012 .

[7]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[8]  Jie Zhang,et al.  Short-Term Load Forecasting With Different Aggregation Strategies , 2018, DAC 2018.

[9]  Jie Zhang,et al.  A data-driven multi-model methodology with deep feature selection for short-term wind forecasting , 2017 .

[10]  Feng Liu,et al.  A hybrid forecasting model based on date-framework strategy and improved feature selection technology for short-term load forecasting , 2017 .

[11]  Ram Rajagopal,et al.  A scaling law for short term load forecasting on varying levels of aggregation , 2018, International Journal of Electrical Power & Energy Systems.

[12]  Mohamed A. Meguid,et al.  Robust ensemble learning framework for day-ahead forecasting of household based energy consumption , 2018 .

[13]  Jing Ma,et al.  Research and application of a hybrid wavelet neural network model with the improved cuckoo search algorithm for electrical power system forecasting , 2017 .

[14]  Chongqing Kang,et al.  An Ensemble Forecasting Method for the Aggregated Load With Subprofiles , 2018, IEEE Transactions on Smart Grid.

[15]  Alagan Anpalagan,et al.  Joint bagged-boosted artificial neural networks: Using ensemble machine learning to improve short-term electricity load forecasting , 2020 .

[16]  Zafar A. Khan,et al.  Load forecasting, dynamic pricing and DSM in smart grid: A review , 2016 .

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

[18]  Rob J. Hyndman,et al.  Optimal combination forecasts for hierarchical time series , 2011, Comput. Stat. Data Anal..

[19]  Rob J Hyndman,et al.  Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond , 2016 .

[20]  Jiafan Yu,et al.  Regularization in Hierarchical Time Series Forecasting with Application to Electricity Smart Meter Data , 2017, AAAI.

[21]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[22]  Priyanka Singh,et al.  Integration of new evolutionary approach with artificial neural network for solving short term load forecast problem , 2018 .

[23]  Vivek Srikumar,et al.  Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks , 2018 .

[24]  Bri-Mathias Hodge,et al.  Unsupervised Clustering-Based Short-Term Solar Forecasting , 2019, IEEE Transactions on Sustainable Energy.

[25]  Federico Silvestro,et al.  Implementation of advanced functionalities for Distribution Management Systems: Load forecasting and modeling through Artificial Neural Networks ensembles , 2019, Electric Power Systems Research.

[26]  M. Hadi Amini,et al.  A novel multi-time-scale modeling for electric power demand forecasting: From short-term to medium-term horizon , 2017 .

[27]  Jie Zhang,et al.  Short-term global horizontal irradiance forecasting based on sky imaging and pattern recognition , 2017, 2017 IEEE Power & Energy Society General Meeting.

[28]  Tao Hong,et al.  Temperature Scenario Generation for Probabilistic Load Forecasting , 2018, IEEE Transactions on Smart Grid.

[29]  Wei-Jen Lee,et al.  Short-Term Load Forecasting Using Comprehensive Combination Based on Multimeteorological Information , 2009, IEEE Transactions on Industry Applications.

[30]  Jie Zhang,et al.  Reinforcement Learning based Dynamic Model Selection for Short-Term Load Forecasting , 2018, 2019 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).

[31]  Rob J. Hyndman,et al.  Forecasting hierarchical and grouped time series through trace minimization , 2015 .

[32]  Abbas Khosravi,et al.  A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings , 2015 .

[33]  Abbas Khosravi,et al.  Examining performance of aggregation algorithms for neural network-based electricity demand forecasting , 2015 .

[34]  Mohammad Moradzadeh,et al.  A novel hybrid algorithm for electricity price and load forecasting in smart grids with demand-side management , 2016 .

[35]  Silja Meyer-Nieberg,et al.  Electric load forecasting methods: Tools for decision making , 2009, Eur. J. Oper. Res..

[36]  Jie Zhang,et al.  Hourly-Similarity Based Solar Forecasting Using Multi-Model Machine Learning Blending , 2018, 2018 IEEE Power & Energy Society General Meeting (PESGM).

[37]  Rui Zhang,et al.  Short-term load forecasting of Australian National Electricity Market by an ensemble model of extreme learning machine , 2013 .

[38]  Jie Zhang,et al.  Reinforced Deterministic and Probabilistic Load Forecasting via $Q$ -Learning Dynamic Model Selection , 2020, IEEE Transactions on Smart Grid.

[39]  David J. Hill,et al.  Short-Term Residential Load Forecasting Based on Resident Behaviour Learning , 2018, IEEE Transactions on Power Systems.

[40]  Chen Wang,et al.  A combined model based on multiple seasonal patterns and modified firefly algorithm for electrical load forecasting , 2016 .

[41]  Pierre Pinson,et al.  Global Energy Forecasting Competition 2012 , 2014 .

[42]  Tao Hong,et al.  Relative Humidity for Load Forecasting Models , 2018, IEEE Transactions on Smart Grid.

[43]  Yoseba K. Penya,et al.  Evaluating Combined Load Forecasting in Large Power Systems and Smart Grids , 2013, IEEE Transactions on Industrial Informatics.

[44]  Dazhi Yang,et al.  Reconciling solar forecasts: Geographical hierarchy , 2017 .