Long short-term memory-singular spectrum analysis-based model for electric load forecasting
- PDF / 3,094,107 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 66 Downloads / 200 Views
ORIGINAL PAPER
Long short-term memory-singular spectrum analysis-based model for electric load forecasting Neeraj Neeraj1
· Jimson Mathew1 · Mayank Agarwal1 · Ranjan Kumar Behera1
Received: 6 May 2019 / Accepted: 20 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Electrical load forecasting is a key player in building sustainable power systems and helps in efficient system planning. However, the irregular and noisy behavior in the observed data makes it difficult to achieve better forecasting accuracy. To handle this, we propose a new model, named singular spectrum analysis-long short- term memory (SSA-LSTM). SSA is a signal processing technique used to eliminate the noisy components of a skewed load series. LSTM model uses the outcome of SSA to forecast the final load. We have used five publicly available datasets from the Australian Energy Market Operator (AEMO) repository to assess the performance of the proposed model. The proposed model has superior forecasting accuracy compared to other existing state-of-the-art methods [persistence, autoregressive (AR), AR-exogenous, ARMAexogenous (ARMAX), support vector regression (SVR), random forest (RF), artificial neural network (ANN), deep belief network (DBN), empirical mode decomposition (EMD-SVR), EMD-ANN, ensemble DBN, and dynamic mode decomposition (DMD)] for half-hourly and one day ahead load forecasting using RMSE and MAPE error metrics. Keywords Short-term load forecasting · Singular spectrum analysis · Long short-term memory · Australian energy market operator
Nomenclature AEMO Australian Energy Market Operator repository AR Autoregressive model ARMAX Autoregressive Moving Average exogenous SVR Support Vector Regression RF Random Forest ANN Artificial Neural Network DBN Deep Belief Network EMD-SVR Empirical Mode Decomposition-Support Vector Regression EMD-ANN Empirical Mode Decomposition-Artificial Neural Network EDBN ensemble Deep Belief Network DMD Dynamic Mode Decomposition STLF Short-Term Load Forecasting RBM Restricted Boltzmann Machines IMFs Intrinsic Mode Functions
B 1
VMD SVD INFS ANFIS SOFM ft it Ct ot ht Y L EVG EV
Variational Mode Decomposition Singular Value Decomposition Integrated Nonlinear Feature Selection Adaptive Neuro-Fuzzy Inference System self-organizing feature map Forget gate layer of LSTM Input gate layer of LSTM Cell state of LSTM Output gate of LSTM Final output of LSTM Hankel matrix having equal elements on the diagonals Window size in constructing the Hankel matrix Eigenvalue Grouping Eigenvalues
1 Introduction Neeraj Neeraj [email protected] Department of Computer Science and Engineering, Indian Institute of Technology, Patna, Bihar, India
Electric load forecasting is increasingly attaining focus day by day. It is most useful in making power systems more intelligent, efficient, sustainable, and reliable. The most crit-
123
Electrical Engineering
ical role of electrical load forecasting is to make a balance between the generated load and end-user demand. Other areas of significa
Data Loading...
