A Novel Approach Based Deep RNN Using Hybrid NARX-LSTM Model For Solar Power Forecasting

The high variability of weather parameters is making photovoltaic energy generation intermittent and narrowly controllable. Threatened by the sudden discontinuity between the load and the grid, energy management for smart grid systems highly require an accurate PV power forecasting model. In this regard, Nonlinear autoregressive exogenous (NARX) is one of the few potential models that handle time series analysis for long-horizon prediction. This later is efficient and high-performing. However, this model often suffers from the vanishing gradient problem which limits its performances. Thus, this paper discus NARX algorithm for long-range dependencies. However, despite its capabilities, it has been detected that this model has some issues coming especially from the vanishing gradient. For the aim of covering these weaknesses, this study suggests a hybrid technique combining long short-term memory (LSTM) with NARX networks under the umbrella of Evolution of recurrent systems with optimal linear output (EVOLINO). For the sake of illustration, this new approach is applied to PV power forecasting for one year in Australia. The proposed model enhances accuracy. This made the proposed algorithm outperform various benchmarked models.

[1]  Mattia Zorzi,et al.  Factor analysis of moving average processes , 2014, 2015 European Control Conference (ECC).

[2]  R. Buizza,et al.  Neural Network Load Forecasting with Weather Ensemble Predictions , 2002, IEEE Power Engineering Review.

[3]  N. Amjady,et al.  Solution of Optimal Power Flow Subject to Security Constraints by a New Improved Bacterial Foraging Method , 2012, IEEE Transactions on Power Systems.

[4]  Yitao Liu,et al.  Deterministic and probabilistic forecasting of photovoltaic power based on deep convolutional neural network , 2017 .

[5]  Zhihuan Song,et al.  Autoregressive Dynamic Latent Variable Models for Process Monitoring , 2017, IEEE Transactions on Control Systems Technology.

[6]  A. Koehler,et al.  Exponential Smoothing Model Selection for Forecasting , 2006 .

[7]  Yugang Niu,et al.  Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM , 2018 .

[8]  T. Swetnam,et al.  Direct and indirect climate controls predict heterogeneous early-mid 21st century wildfire burned area across western and boreal North America , 2017, PloS one.

[9]  Francesco Grimaccia,et al.  A Physical Hybrid Artificial Neural Network for Short Term Forecasting of PV Plant Power Output , 2015 .

[10]  Peter Bauer,et al.  The quiet revolution of numerical weather prediction , 2015, Nature.

[11]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[12]  Arash Bahrammirzaee,et al.  A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems , 2010, Neural Computing and Applications.

[13]  Swati Sharma.  Rise of Big Data and related issues , 2015, 2015 Annual IEEE India Conference (INDICON).

[14]  Fang Liu,et al.  IET Renewable Power Generation Special Issue: Performance Assessment and Condition Monitoring of Photovoltaic Systems for Improved Energy Yield Takagi–Sugeno fuzzy model-based approach considering multiple weather factors for the photovoltaic power short-term forecasting , 2020 .

[15]  Robert Tibshirani,et al.  Discriminant Adaptive Nearest Neighbor Classification and Regression , 1995, NIPS.

[16]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[17]  Yash Pal,et al.  Photovoltaic power forecasting methods in smart power grid , 2015, 2015 Annual IEEE India Conference (INDICON).

[18]  Cheng Hang,et al.  Forecasting Research of Long-Term Solar Irradiance and Output Power for Photovoltaic Generation System , 2012, 2012 Fourth International Conference on Computational and Information Sciences.

[19]  H Zareipour,et al.  Wind Power Prediction by a New Forecast Engine Composed of Modified Hybrid Neural Network and Enhanced Particle Swarm Optimization , 2011, IEEE Transactions on Sustainable Energy.

[20]  Salah Al-Sharhan,et al.  ARTIFICIAL IMMUNE SYSTEMS - MODELS, ALGORITHMS AND APPLICATIONS , 2010 .

[21]  S. Cohn,et al.  Applications of Estimation Theory to Numerical Weather Prediction , 1981 .

[22]  S. Santoso,et al.  Wind power forecasting and error analysis using the autoregressive moving average modeling , 2009, 2009 IEEE Power & Energy Society General Meeting.

[23]  Jianfeng Li,et al.  Exchange rate forecasting based on a new kind of nonlinear combination method , 2010, 2010 The 2nd International Conference on Computer and Automation Engineering (ICCAE).

[24]  Chris Chatfield,et al.  The Analysis of Time Series , 1990 .

[25]  Chul-Yong Lee,et al.  Forecasting future demand for large-screen television sets using conjoint analysis with diffusion model , 2006 .

[26]  Maria Grazia De Giorgi,et al.  Photovoltaic power forecasting using statistical methods: impact of weather data , 2014 .

[27]  Caston Sigauke,et al.  Peak electricity demand forecasting using time series regression models: An application to South African data , 2016 .

[28]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[29]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[30]  Mohamed Abdel-Nasser,et al.  Accurate photovoltaic power forecasting models using deep LSTM-RNN , 2017, Neural Computing and Applications.

[31]  H. R. Pota,et al.  Univariate time series prediction of solar power using a hybrid wavelet-ARMA-NARX prediction method , 2016, 2016 IEEE/PES Transmission and Distribution Conference and Exposition (T&D).

[32]  Akbar A. Javadi,et al.  A hybrid intelligent genetic algorithm , 2005, Adv. Eng. Informatics.

[33]  Eugen Diaconescu,et al.  The use of NARX neural networks to predict chaotic time series , 2008 .

[34]  M. Valipour,et al.  Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir , 2013 .

[35]  Jianhua Zhang,et al.  PV power forecasting using an integrated GA-PSO-ANFIS approach and Gaussian process regression based feature selection strategy , 2018, CSEE Journal of Power and Energy Systems.

[36]  K. Shashidhar Reddy,et al.  Statistical analysis of load and its frequency response for load forecasting in a medium voltage distribution system , 2017, 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS).

[37]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.