Locational Marginal Price Forecasting Using Deep Learning Network Optimized by Mapping-Based Genetic Algorithm

The convolutional neural network (CNN) is commonly used in visual recognitions and classifications. However, CNN can also be applied as a forecaster that can extract features from spatiotemporal data. This paper proposes a 24h ahead electricity price forecasting method, which integrates CNN with an evolutionary algorithm and utilizes spatiotemporal data. The optimal structure of the CNN network for the locational marginal price (LMP) forecasting was obtained using a genetic algorithm (GA). A gene mapping scheme was initially encoded to represent the search space and the process of selection, mutation, and crossover eliminated structures that did not satisfy the validation fitness function and then competitive individuals were generated. The evolution process uses the root mean square error (RMSE) as the validation fitness function, which is optimzed by training the created CNN network. The proposed gene mapping scheme can be used to design an optimal CNN structure once the mapping between gene binary bits and parameters/hyperparameters of CNN is given. Day-ahead LMP and demand datasets from Pennsylvania-New Jersey-Maryland (PJM) power market were used to demonstrate the evolutionary capability of the proposed method and the finding of optimal CNN structures. Each studied dataset was grouped into 4 subsets corresponding to various seasonal characteristics (different types of situations in real life). Experimental results revealed that the proposed GA-CNN always yielded a higher forecasting accuracy and lower error rates than other forecasting methods.

[1]  Xiaoqing Han,et al.  Review on the research and practice of deep learning and reinforcement learning in smart grids , 2018, CSEE Journal of Power and Energy Systems.

[2]  Xiaochen Zhao,et al.  A hybrid model based on modified multi-objective cuckoo search algorithm for short-term load forecasting , 2019, Applied Energy.

[3]  Chip Stewart,et al.  Optimizing event selection with the random grid search , 2017, Comput. Phys. Commun..

[4]  Zijun Zhang,et al.  Short-Term Electricity Price Forecasting With Stacked Denoising Autoencoders , 2017, IEEE Transactions on Power Systems.

[5]  Prakash Ranganathan,et al.  A Hybrid Regression Model for Day-Ahead Energy Price Forecasting , 2019, IEEE Access.

[6]  Marc Parizeau,et al.  DEAP: evolutionary algorithms made easy , 2012, J. Mach. Learn. Res..

[7]  Alan L. Yuille,et al.  Genetic CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[8]  Mengjie Zhang,et al.  Evolving Deep Convolutional Neural Networks for Image Classification , 2017, IEEE Transactions on Evolutionary Computation.

[9]  Bin Wang,et al.  Evolving deep neural networks by multi-objective particle swarm optimization for image classification , 2019, GECCO.

[10]  Mohammad Shahidehpour,et al.  Market operations in electric power systems , 2002 .

[11]  Bart De Schutter,et al.  Forecasting day-ahead electricity prices in Europe: the importance of considering market integration , 2017, ArXiv.

[12]  Farshid Keynia,et al.  Mid‐term electricity load forecasting by a new composite method based on optimal learning MLP algorithm , 2020 .

[13]  Nikolaos G. Bourbakis,et al.  Genetic Optimal Regression of Relevance Vector Machines for Electricity Pricing Signal Forecasting in Smart Grids , 2015, IEEE Transactions on Smart Grid.

[14]  Nadeem Javaid,et al.  Electricity Price and Load Forecasting using Enhanced Convolutional Neural Network and Enhanced Support Vector Regression in Smart Grids , 2019, Electronics.

[15]  Enrico Maria Carlini,et al.  The 2.0 cost benefit analysis and its application to the national development plan 2017: Methodology for evaluating electricity grid projects' benefits: Current status and further improvements , 2017, 2017 AEIT International Annual Conference.

[16]  N. Amjady,et al.  Energy price forecasting - problems and proposals for such predictions , 2006 .

[17]  R. A. Swief,et al.  Support vector machines (SVM) based short term electricity load-price forecasting , 2009, 2009 IEEE Bucharest PowerTech.

[18]  Behrouz Maham,et al.  Electricity price forecasting using Support Vector Machines by considering oil and natural gas price impacts , 2015, 2015 IEEE International Conference on Smart Energy Grid Engineering (SEGE).

[19]  Wuneng Zhou,et al.  A hybrid electricity price forecasting model with Bayesian optimization for German energy exchange , 2019, International Journal of Electrical Power & Energy Systems.

[20]  Joao P. S. Catalao,et al.  Electricity price forecast using Combinatorial Neural Network trained by a new stochastic search method , 2015 .

[21]  T. Senjyu,et al.  A Novel Approach to Forecast Electricity Price for PJM Using Neural Network and Similar Days Method , 2007, IEEE Transactions on Power Systems.

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

[23]  Xin Wang,et al.  A short-term marginal price forecasting model based on ensemble learning , 2017, 2017 International Conference on Progress in Informatics and Computing (PIC).

[24]  Can Bikcora,et al.  Density forecasting of daily electricity demand with ARMA-GARCH, CAViaR, and CARE econometric models , 2018 .

[25]  Hazlee Azil Illias,et al.  Hybrid ANN and Artificial Cooperative Search Algorithm to Forecast Short-Term Electricity Price in De-Regulated Electricity Market , 2019, IEEE Access.

[26]  Bart De Moor,et al.  Hyperparameter Search in Machine Learning , 2015, ArXiv.

[27]  Madan Mohan Tripathi,et al.  Ensemble of relevance vector machines and boosted trees for electricity price forecasting , 2019, Applied Energy.

[28]  Johannes Urpelainen,et al.  Global Patterns of Power Sector Reform, 1982-2013 , 2018, Energy Strategy Reviews.

[29]  Yang Zhang,et al.  Effective Adam-Optimized LSTM Neural Network for Electricity Price Forecasting , 2018, 2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS).

[30]  Bimal K. Bose,et al.  Artificial Intelligence Techniques in Smart Grid and Renewable Energy Systems—Some Example Applications , 2017, Proceedings of the IEEE.

[31]  Zhang Yang,et al.  Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods , 2017 .

[32]  Kaustav Chatterjee,et al.  Cost benefit analysis of smart grid: A case study from India , 2017, 2017 North American Power Symposium (NAPS).

[33]  Bart De Schutter,et al.  Forecasting spot electricity prices Deep learning approaches and empirical comparison of traditional algorithms , 2018 .

[34]  Paras Mandal,et al.  A novel hybrid approach using wavelet, firefly algorithm, and fuzzy ARTMAP for day-ahead electricity price forecasting , 2013, IEEE Transactions on Power Systems.

[35]  Tao Hong,et al.  Long Term Probabilistic Load Forecasting and Normalization With Hourly Information , 2014, IEEE Transactions on Smart Grid.

[36]  Bin Wang,et al.  A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification , 2018, Australasian Conference on Artificial Intelligence.

[37]  Zhong-kai Feng,et al.  A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm , 2019, Applied Energy.

[38]  Jinliang Zhang,et al.  Day-ahead electricity price forecasting by a new hybrid method , 2012, Comput. Ind. Eng..

[39]  Ashwani Kumar,et al.  Parameter optimisation using genetic algorithm for support vector machine-based price-forecasting model in National electricity market , 2010 .

[40]  Fernando Luiz Cyrino Oliveira,et al.  Forecasting mid-long term electric energy consumption through bagging ARIMA and exponential smoothing methods , 2018 .

[41]  Kejun Wang,et al.  Photovoltaic power forecasting based LSTM-Convolutional Network , 2019 .

[42]  Ping-Huan Kuo,et al.  An Electricity Price Forecasting Model by Hybrid Structured Deep Neural Networks , 2018 .

[43]  M. Shahidehpour,et al.  A Hybrid Model for Day-Ahead Price Forecasting , 2010, IEEE Transactions on Power Systems.

[44]  Arun Sukumaran Nair,et al.  Deep Neural Networks (DNN) for Day-Ahead Electricity Price Markets , 2018, 2018 IEEE Electrical Power and Energy Conference (EPEC).

[45]  Ying-Yi Hong,et al.  A hybrid deep learning-based neural network for 24-h ahead wind power forecasting , 2019, Applied Energy.

[46]  Katarina Grolinger,et al.  Energy cost forecasting for event venues , 2015, 2015 IEEE Electrical Power and Energy Conference (EPEC).

[47]  Ilkay Oksuz,et al.  Electricity Price Forecasting Using Recurrent Neural Networks , 2018 .

[48]  Dipti Srinivasan,et al.  A hybrid intelligent model based on recurrent neural networks and excitable dynamics for price prediction in deregulated electricity market , 2013, Eng. Appl. Artif. Intell..

[49]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[50]  Fu Xiao,et al.  Price-responsive model-based optimal demand response control of inverter air conditioners using genetic algorithm , 2018, Applied Energy.