Metaheuristic-Based Hyperparameter Tuning for Recurrent Deep Learning: Application to the Prediction of Solar Energy Generation
Catalin Stoean,Miodrag Zivkovic,Aleksandra Božović,Nebojsa Bacanin,Roma Strulak-Wójcikiewicz,Milos Antonijevic,Ruxandra Stoean +6 more
TL;DR: In this article , the use of an LSTM and a BiLSTM was proposed for dealing with a data collection that, besides the time series values denoting the solar energy generation, also comprises corresponding information about the weather.
read more
Abstract: As solar energy generation has become more and more important for the economies of numerous countries in the last couple of decades, it is highly important to build accurate models for forecasting the amount of green energy that will be produced. Numerous recurrent deep learning approaches, mainly based on long short-term memory (LSTM), are proposed for dealing with such problems, but the most accurate models may differ from one test case to another with respect to architecture and hyperparameters. In the current study, the use of an LSTM and a bidirectional LSTM (BiLSTM) is proposed for dealing with a data collection that, besides the time series values denoting the solar energy generation, also comprises corresponding information about the weather. The proposed research additionally endows the models with hyperparameter tuning by means of an enhanced version of a recently proposed metaheuristic, the reptile search algorithm (RSA). The output of the proposed tuned recurrent neural network models is compared to the ones of several other state-of-the-art metaheuristic optimization approaches that are applied for the same task, using the same experimental setup, and the obtained results indicate the proposed approach as the better alternative. Moreover, the best recurrent model achieved the best results with R2 of 0.604, and a normalized MSE value of 0.014, which yields an improvement of around 13% over traditional machine learning models.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Review on Sustainable Energy Sources Using Machine Learning and Deep Learning Models
Ashok Bhansali,Namala Narasimhulu,Rocío Pérez de Prado,Parameshachari Bidare Divakarachari,Dayanand Lal Narayan +4 more
TL;DR: This review surveys machine learning and deep learning models for sustainable energy sources, evaluating their effectiveness in solar, wind, hydro, and tidal energy conversion systems, and identifying advantages and drawbacks of existing methodologies to inform future research.
31
Optimizing long-short-term memory models via metaheuristics for decomposition aided wind energy generation forecasting
Marijana Pavlov-Kagadejev,Luka Jovanovic,Nebojsa Bacanin,Muhammet Deveci,Miodrag Zivkovic,Milan Tuba,Ivana Strumberger,W. Pedrycz +7 more
TL;DR: This study proposed an approach that incorporates signal decomposition techniques with Long Short-Term Memory (LSTM) neural networks tuned via a modified metaheuristic algorithm used for wind power generation forecasting that notably exceed other contenders.
27
Software defects prediction by metaheuristics tuned extreme gradient boosting and analysis based on Shapley Additive Explanations
Tamara Živković,Bosko Nikolic,V. Simic,Dragan Pamučar,Nebojsa Bacanin +4 more
TL;DR: This study proposes a metaheuristics-tuned XGBoost model for software defect prediction, utilizing a modified reptile search optimization algorithm (HARSA) to optimize hyperparameters, achieving superior classification accuracy on two benchmark datasets and providing insights into software metric contributions via Shapley Additive Explanations.
27
Marine Vessel Classification and Multivariate Trajectories Forecasting Using Metaheuristics-Optimized eXtreme Gradient Boosting and Recurrent Neural Networks
Aleksandar Petrovic,Robertas Damaševičius,Luka Jovanovic,Ana Toskovic,Vladimir Simic,Nebojsa Bacanin,Miodrag Zivkovic,Petar Spalević +7 more
TL;DR: A boosted version of the well-known particle swarm optimization (PSO) algorithm was introduced specifically for tuning the hyperparameters of the models used in this study, to tackle two challenges of marine vessel classification and trajectory forecasting.
24
Reptile Search Algorithm: Theory, Variants, Applications, and Performance Evaluation
TL;DR: This study provides a comprehensive report of the classical RSA, and its improved variants and their applications in various domains, and a comprehensive comparison among RSA and its peer NIOAs is performed using mathematical benchmark functions.
22
References
•Proceedings Article
A unified approach to interpreting model predictions
Scott M. Lundberg,Su-In Lee +1 more
- 04 Dec 2017
TL;DR: In this article, a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), is presented, which assigns each feature an importance value for a particular prediction.
No free lunch theorems for optimization
TL;DR: A framework is developed to explore the connection between effective optimization algorithms and the problems they are solving and a number of "no free lunch" (NFL) theorems are presented which establish that for any algorithm, any elevated performance over one class of problems is offset by performance over another class.
Learning to forget: continual prediction with LSTM
Felix A. Gers,Jürgen Schmidhuber,Fred Cummins +2 more
- 01 Jan 1999
TL;DR: This work identifies a weakness of LSTM networks processing continual input streams without explicitly marked sequence ends and proposes an adaptive "forget gate" that enables an L STM cell to learn to reset itself at appropriate times, thus releasing internal resources.
5.5K
Learning to Forget: Continual Prediction with LSTM
TL;DR: This work identifies a weakness of LSTM networks processing continual input streams that are not a priori segmented into subsequences with explicitly marked ends at which the network's internal state could be reset, and proposes a novel, adaptive forget gate that enables an LSTm cell to learn to reset itself at appropriate times, thus releasing internal resources.
5.1K
Harris hawks optimization: Algorithm and applications
Ali Asghar Heidari,Ali Asghar Heidari,Seyedali Mirjalili,Hossam Faris,Ibrahim Aljarah,Majdi Mafarja,Huiling Chen +6 more
TL;DR: The statistical results and comparisons show that the HHO algorithm provides very promising and occasionally competitive results compared to well-established metaheuristic techniques.
4.7K