The Integration of Internet of Things and Machine Learning for Energy Prediction of Wind Turbines DOI Creative Commons

Christos Emexidis,

Panagiotis K. Gkonis

Applied Sciences, Год журнала: 2024, Номер 14(22), С. 10276 - 10276

Опубликована: Ноя. 8, 2024

Wind power has emerged as a crucial substitute for conventional fossil fuels. The combination of advanced technologies such the internet things (IoT) and machine learning (ML) given rise to new generation energy systems that are intelligent, reliable, efficient. wind sector utilizes IoT devices gather vital data, subsequently converting them into practical insights. aforementioned information aids among others in enhancement turbine efficiency, precise anticipation production, optimization maintenance approaches, detection potential risks. In this context, main goal work is combine with ML by processing weather data acquired from sensors predict generation. To end, three different regression models evaluated. under comparison include Linear Regression, Random Forest, Lasso which were evaluated using metrics coefficient determination (R²), adjusted R², mean squared error (MSE), root (RMSE), absolute (MAE). Moreover, Akaike Information Criterion (AIC) Bayesian (BIC) taken consideration well. After examining dataset included provided substantial insights regarding their capabilities responses preprocessing, well each model’s reaction terms statistical performance deviation indicators. Ultimately, analysis results criteria show Forest more suitable condition datasets than other two models. Both advantages shortcomings indicate integration will facilitate successful prediction.

Язык: Английский

The Integration of Internet of Things and Machine Learning for Energy Prediction of Wind Turbines DOI Creative Commons

Christos Emexidis,

Panagiotis K. Gkonis

Applied Sciences, Год журнала: 2024, Номер 14(22), С. 10276 - 10276

Опубликована: Ноя. 8, 2024

Wind power has emerged as a crucial substitute for conventional fossil fuels. The combination of advanced technologies such the internet things (IoT) and machine learning (ML) given rise to new generation energy systems that are intelligent, reliable, efficient. wind sector utilizes IoT devices gather vital data, subsequently converting them into practical insights. aforementioned information aids among others in enhancement turbine efficiency, precise anticipation production, optimization maintenance approaches, detection potential risks. In this context, main goal work is combine with ML by processing weather data acquired from sensors predict generation. To end, three different regression models evaluated. under comparison include Linear Regression, Random Forest, Lasso which were evaluated using metrics coefficient determination (R²), adjusted R², mean squared error (MSE), root (RMSE), absolute (MAE). Moreover, Akaike Information Criterion (AIC) Bayesian (BIC) taken consideration well. After examining dataset included provided substantial insights regarding their capabilities responses preprocessing, well each model’s reaction terms statistical performance deviation indicators. Ultimately, analysis results criteria show Forest more suitable condition datasets than other two models. Both advantages shortcomings indicate integration will facilitate successful prediction.

Язык: Английский

Процитировано

1