Analysis of machine learning algorithms for biogas yield prediction
DOI:
https://doi.org/10.31548/energiya3(67).2023.100Abstract
Currently, effective management of biogas production remains a difficult task.
The purpose of the research is to analyze machine learning algorithms for predicting biogas output depending on the characteristics of biogas production.
Currently, there is no necessary set of data, analyzing which indicators can be obtained to optimize biogas production in our installation. At the same time, testing various optimization algorithms and deciding on the best takes a lot of time, as experience shows.
The application of machine algorithms for forecasting biogas production by using existing forecasting methods is considered. Provided that the control systems of typical biogas productions are equipped with the necessary sensing elements, there still remains the task of processing and analyzing data to make the best decision to meet the relevant technological requirements. The reason for this is the large volume of data and the complexity of the interaction of processes that are components of production. In this context, machine learning can be a useful tool for optimizing biogas production.
Key words: machine learning, biogas output, automated control, control algorithms, mathematical model
Downloads
References
Kaggle.com. JM Biogas production experiment analysis jumpstart. Available at: https://www.kaggle.com/code/ivandaudt/jm-biogas-production-experiment-analysis-jumpstart/notebook.
Amazon SageMaker Autopilot. Available at: [https://aws.amazon.com/sagemaker/autopilot/?nc1=h_ls&sagemaker-data-wrangler-whats-new.sort-by=item.additionalFields.postDateTime&sagemaker-data-wrangler-whats-new.sort-order=desc].
Essam Al Daoud. Comparison between XGBoost, LightGBM and CatBoost Using a Home Credit Dataseю Available at: [https://publications.waset.org/10009954/comparison-between-xgboost-lightgbm-and-catboost-using-a-home-credit-dataset].
Muhammad Waseem Ahmad, Jonathan Reynolds, Yacine Rezgui. Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees. Available at: [https://www.sciencedirect.com/science/article/pii/S0959652618325551].
Pierre Geurts, Damien Ernst, Louis Wehenkel. Extremely randomized trees. Available at: [https://link.springer.com/article/10.1007/s10994-006-6226-1].
J. A. Nelder, R. W. M. Wedderburn. Generalized Linear Models. Available at: [https://rss.onlinelibrary.wiley.com/doi/abs/10.2307/2344614].
Rita Yi Man Li, Herru Ching Yu Li, Beiqi Tang, WaiCheung Au. Fast AI classification for analyzing construction accidents claims. Available at[https://dl.acm.org/doi/abs/10.1145/3407703.3407705].
Sagar Imambi, Kolla Bhanu Prakash, G. R. Kanagachidambaresan. PyTorch. Available at: [https://link.springer.com/chapter/10.1007/978-3-030-57077-4_10].
Weijie Wang, Yanmin Lu . Analysis of the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE) in Assessing Rounding Model. Available at:[https://iopscience.iop.org/article/10.1088/1757-899X/324/1/012049/meta].
Kalyan Das, Jiming Jiang, J. N. K. Rao. Mean squared error of empirical predictor. Available at: [https://projecteuclid.org/journals/annals-of-statistics/volume-32/issue-2/Mean-squared-error-of-empirical-predictor/10.1214/009053604000000201.full].
Alon Brutzkus, Ran Gilad-Bachrach, Oren Elisha. Low Latency Privacy Preserving Inference. Available at [http://proceedings.mlr.press/v97/brutzkus19a].
Rich Caruana, Alexandru Niculescu-Mizil, Geoff Crew, Alex Ksikes. Ensemble selection from libraries of models. Available at: [https://dl.acm.org/doi/abs/10.1145/1015330.1015432].
Robert E. Weiss, Carlos G. Lazaro. Residual plots for repeated measures. Available at: [https://doi.org/10.1002/sim.4780110110].
Zhila Esna Ashari, Nairanjana Dasgupta, Kelly A Brayton, Shira L Broschat. An optimal set of features for predicting type IV secretion system effector proteins for a subset of species based on a multi-level feature selection approach. Available at: [http://dx.doi.org/10.1371/journal.pone.0197041].
Downloads
Published
Issue
Section
License
All materials are disseminated under the terms of the Creative Commons Attribution 4.0 International Public License, which permits others to distribute the manuscript with proper acknowledgement of the authorship and the original publication in this journal.
