Abstract
The main purpose of this paper is to develop an efficient machine learning model to estimate the electric power load. The developed machine learning model can be used by electric power utilities for proper operation and maintenance of grid and also to trade electricity effectively in energy market. This paper proposes a machine learning model using gated recurrent unit (GRU) and random forest (RF). GRU has been employed to predict the electric power load, whereas RF has been used to reduce the input dimensions of the model. GRU has been estimating the load with good accuracy. RF reduces the input dimensions of the GRU that leads lightweight GRU model. The main benefits of the lightweight GRU models are less computation time and memory space. However, lightweight GRU models will loss small amount of accuracy comparing to the original GRU model. GRU along with RF has been used for the first for short load forecasting. All the machine learning model’s performance has been observed in stochastic environment. Impact of weekends on load forecasting also observed by considering the last 3-week load data.
Similar content being viewed by others
Abbreviations
- \(a_{t-1}\) :
-
Hidden neuron previous activation state
- \(a_{t}\) :
-
Hidden neuron current activation state
- \(b_{c}\) :
-
Bias parameter to compute cell state
- \(b_{r}\) :
-
Bias parameter to compute relevance gate
- \(b_{u}\) :
-
Bias parameter to compute update gate
- \(b_{y}\) :
-
Bias parameter for output layer
- \(c^{t}\) :
-
State of memory cell
- \(W_{c}\) :
-
Weight matrix to compute cell state
- \(W_{r}\) :
-
Weight matrix to compute relevance gate
- \(W_{u}\) :
-
Weight matrix to compute update gate
- \(W_{y}\) :
-
Weight matrix to compute output
- \(x_{t}\) :
-
Input feature at time stamp ‘t’
- \(Y_{i}^\mathrm{pred}\) :
-
Predicted load with ith sample
- \(Y_{i}^\mathrm{true}\) :
-
Actual load from ith sample
- L(T):
-
Load at Tth hour
- L(T-1):
-
Load at 1 h before from the time of prediction
- L(T-168):
-
Load at 1 week before from the time of prediction
- L(T-2):
-
Load at 2 h before from the time of prediction
- L(T-24):
-
Load at 1 day before from the time of prediction
- L(T-3):
-
Load at 3 h before from time of prediction
- L(T-336):
-
Load at 2 weeks before from the time of prediction
- L(T-48):
-
Load at 2 days before from the time of prediction
- L(T-504):
-
Load at 3 weeks before from time of prediction
- L(T-72):
-
Load at 3 days before from time of prediction
- MAE:
-
Mean absolute error
- MSE:
-
Mean square error
- RMSE:
-
Root mean square error
References
Alkaldy EAH, Albaqir MA, Hejazi MSA (2019) A new load forecasting model considering planned load shedding effect. Int J Energy Sector Manag
Almeshaiei E, Soltan H (2011) A methodology for electric power load forecasting. Alex Eng J 50(2):137–144
Awoyera P, Akinmusuru J, Krishna AS, Gobinath R, Arunkumar B, Sangeetha G (2020) Model development for strength properties of laterized concrete using artificial neural network principles. In: Soft computing for problem solving. Springer, pp 197–207
Chen Y, Kloft M, Yang Y, Li C, Li L (2018) Mixed kernel based extreme learning machine for electric load forecasting. Neurocomputing 312:90–106
Chen Y, Xu P, Chu Y, Li W, Wu Y, Ni L, Bao Y, Wang K (2017) Short-term electrical load forecasting using the support vector regression (svr) model to calculate the demand response baseline for office buildings. Appl Energy 195:659–670
Cho K, Van Merriënboer B, Bahdanau D, Bengio Y (2014) On the properties of neural machine translation: encoder–decoder approaches. arXiv preprint arXiv:1409.1259
Dash P, Liew A, Rahman S, Dash S (1995) Fuzzy and neuro-fuzzy computing models for electric load forecasting. Eng Appl Artif Intell 8(4):423–433
Dhandapani K, Venugopal K, Kumar JV (2019) Ecofriendly and green synthesis of carbon nanoparticles from rice bran: characterization and identification using image processing technique. Int J Plast Technol 23(1):56–66
Haben S, Giasemidis G, Ziel F, Arora S (2019) Short term load forecasting and the effect of temperature at the low voltage level. Int J Forecast 35(4):1469–1484
Hu R, Wen S, Zeng Z, Huang T (2017) A short-term power load forecasting model based on the generalized regression neural network with decreasing step fruit fly optimization algorithm. Neurocomputing 221:24–31
Hu Z, Bao Y, Xiong T, Chiong R (2015) Hybrid filter-wrapper feature selection for short-term load forecasting. Eng Appl Artif Intell 40:17–27
Karri C, Durgam R, Raghuram K (2018) Electricity price forecasting in deregulated power markets using wavelet-ANFIS-KHA. In: 2018 International conference on computing, power and communication technologies (GUCON). IEEE, pp 982–987
Ke K, Hongbin S, Chengkang Z, Brown C (2019) Short-term electrical load forecasting method based on stacked auto-encoding and GRU neural network. Evol Intel 12(3):385–394
Khodayar ME, Wu H (2015) Demand forecasting in the smart grid paradigm: features and challenges. Electr J 28(6):51–62
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
Kumar BA, Sangeetha G, Srinivas A, Awoyera P, Gobinath R, Ramana VV (2020) Models for predictions of mechanical properties of low-density self-compacting concrete prepared from mineral admixtures and pumice stone. In: Soft computing for problem solving. Springer, pp 677–690
Kumar SN, Kumar PP, Sandeep C, Shwetha S (2018) Opportunities for applying deep learning networks to tumour classification. Indian J Public Health Res Dev 9(11):742–747
Kwon BS, Park RJ, Song KB (2020) Short-term load forecasting based on deep neural networks using LSTM layer. J Electr Eng Technol
Li LL, Sun J, Wang CH, Zhou YT, Lin KP (2019) Enhanced gaussian process mixture model for short-term electric load forecasting. Inf Sci 477:386–398
Ramanathan R, Engle R, Granger CW, Vahid-Araghi F, Brace C (1997) Short-run forecasts of electricity loads and peaks. Int J Forecast 13(2):161–174
Salgado RM, Lemes RR (2013) A hybrid approach to the load forecasting based on decision trees. J Control Autom Electr Syst 24(6):854–862
Shaloudegi K, Madinehi N, Hosseinian S, Abyaneh HA (2012) A novel policy for locational marginal price calculation in distribution systems based on loss reduction allocation using game theory. IEEE Trans Power Syst 27(2):811–820
Sina A, Kaur D (2020) Short term load forecasting model based on kernel-support vector regression with social spider optimization algorithm. J Electr Eng Technol 15(1):393–402
Soares LJ, Souza LR (2006) Forecasting electricity demand using generalized long memory. Int J Forecast 22(1):17–28
Su P, Tian X, Wang Y, Deng S, Zhao J, An Q, Wang Y (2017) Recent trends in load forecasting technology for the operation optimization of distributed energy system. Energies 10(9):1303
Tripathi M, Upadhyay K, Singh S (2008) Short-term load forecasting using generalized regression and probabilistic neural networks in the electricity market. Electr J 21(9):24–34
Veeramsetty V, Chintham V, DM VK (2018) LMP computation at dg buses in radial distribution system. Int J Energy Sector Manag
Veeramsetty V, Chintham V, Vinod Kumar D (2018) Proportional nucleolus game theory-based locational marginal price computation for loss and emission reduction in a radial distribution system. Int Trans Electr Energy Syst 28(8):e2573
Veeramsetty V, Deshmukh R (2020) Electric power load forecasting on a 33/11 kv substation using artificial neural networks. SN Appl Sci 2(855). https://doi.org/10.1007/s42452-020-2601-y(2020)
Veeramsetty V, Mohnot A, Singal G, Salkuti SR (2021) Short term active power load prediction on a 33/11 kv substation using regression models. Energies 14(11):2981
Venkataramana V (2020) Active power load dataset. https://doi.org/10.17632/ycfwwyyx7d.2
Wang P, Liu B, Hong T (2016) Electric load forecasting with recency effect: a big data approach. Int J Forecast 32(3):585–597
Xie K, Yi H, Hu G, Li L, Fan, Z (2019) Short-term power load forecasting based on Elman neural network with particle swarm optimization. Neurocomputing
Yang Y, Che J, Deng C, Li L (2019) Sequential grid approach based support vector regression for short-term electric load forecasting. Appl Energy 238:1010–1021
Yang ZC (2015) Electric load movement evaluation and forecasting based on the Fourier-series model extend in the least-squares sense. J Control Autom Electr Syst 26(4):430–440
Zhang A, Zhang P, Feng Y (2019) Short-term load forecasting for microgrids based on DA-SVM. COMPEL Int J Comput Math Electr Electron Eng
Zhang Q, Zhang J (2020) Short-term load forecasting method based on EWT and IDBSCAN. J Electr Eng Technol 1–10
Acknowledgements
We thank S R engineering College, Warangal, for supporting us during this work. We thank 33/11-kV substation near Kakatiya University in Warangal for providing the historical load data.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Authors have declared that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Veeramsetty, V., Reddy, K.R., Santhosh, M. et al. Short-term electric power load forecasting using random forest and gated recurrent unit. Electr Eng 104, 307–329 (2022). https://doi.org/10.1007/s00202-021-01376-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00202-021-01376-5