Search

A new pre-processing methodology for gridded Satellite Precipitation Products (SPPs) is developed to improve the performance of Machine Learning (ML) algorithms for runoff prediction. The developed approach was applied to capture the rainfall patterns, and to select relevant input data. This approach was tested using the FeedForward Neural Network (FFNN) and the Extreme Learning Machine (ELM) given their flexibility and ability in hydrological modelling. The methodology was tested in a semiarid transboundary watershed located in North Africa (Algeria, Tunisia) with the Integrated MultisatellitE Retrievals for Global Precipitation Measurement (GPMIMERG) and the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) products. The results demonstrate the effectiveness of the proposed approach using all employed SPPs. In terms of Nash-Sutcliffe efficiency, the suggested pre-processing technique improved the prediction ability of FFNN by 13%, and of ELM by 15%, which highlights how pre-processing techniques significantly enhance ML models with SPP data. [ABSTRACT FROM AUTHOR]

This paper discusses the efficient implementation of a new hybrid approach to forecasting short-term PV power production for four different PV plants in Algeria. The developed model incorporates a time-varying filter-empirical mode decomposition (TVFEMD) and an extreme learning machine (ELM) as an essence regression. The TVF-EMD technique is used to deal with the fluctuation of PV power data by splitting it into a series of more stable and constant subseries. The specified set of features (intrinsic mode functions (IMFs)) is utilized for training and improving our forecasting extreme learning machine model. The adjusted ELM model is used to evaluate prediction e1ciency. The suggested TVF-EMD-ELM model is assessed and verified in various Algerian locations with varying climate conditions. In all examined regions, the TVF-EMD-ELM model generates less than 4% error in terms of normalized root mean square error (nRMSE). [ABSTRACT FROM AUTHOR]

This study presents two machine learning models, namely, the light gradient boosting machine (LightGBM) and categorical boosting (CatBoost), for the first time for predicting flash flood susceptibility (FFS) in the Wadi System (Hurghada, Egypt). A flood inventory map with 445 flash flood sites was produced and randomly divided into two groups for training (70%) and testing (30%). Fourteen flood controlling factors were selected and evaluated for their relative importance in flood occurrence prediction. The performance of the two models was assessed using various indexes in comparison to the common random forest (RF) method. The results show areas under the receiver operating characteristic curves (AUROC) of above 97% for all models and that LightGBM outperforms other models in terms of classification metrics and processing time. The developed FFS maps demonstrate that highly populated areas are the most susceptible to flash floods. The present study proves that the employed algorithms (LightGBM and CatBoost) can be efficiently used for FFS mapping. [ABSTRACT FROM AUTHOR]

The increase in electricity demand requires improved energy planning programs, which involve better energy distribution. Therefore, precise energy demand forecasting is of great importance for optimizing energy distribution. In this respect, a new hybrid forecasting model was proposed in this study for multi‐hour forecasting of total energy requirement (cooling and heating load of buildings) in three different regions in Algeria with different climate conditions. The proposed models are based on two main steps: In the first step, time‐series data were decomposed using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) into a different intrinsic function (IMFs), and then extreme learning machine (ELM) is employed as essence predictors. The proposed CEEMDAN‐ELM model uses the decomposed IMFs as input data, and the total energy concern as a desired output. The integrated CEEMDAN‐ELM model was evaluated and validated on three different databases each of which had 2 years of measurement on an hourly scale. Experimental results show that the hybridization mechanism CEEMDAN‐ELM outperform the stand‐alone model (ELM) in terms of forecasting errors over the entire forecasting horizon. Forecasting results of CEEMDAN‐ELM led to a normalized root mean square error (nRMSE) in the range of [0.71–4.66] for all studied regions and horizons whereas conventional ELM provides an nRMSE in the range of [0.93–16.89]. [ABSTRACT FROM AUTHOR]

Integrating photovoltaic power into the power system can offer significant economic and environmental benefits. However, the intermittent and random nature of photovoltaic power generation poses a challenge to the current power system's planning and operation. Accurate photovoltaic power generation forecasting is crucial for delivering high-quality electric energy to consumers and increasing system reliability.In this study, a multi-stage approach is proposed. In the first stage, three decomposition techniques (Iterative Filtering decomposition, Variational Mode Decomposition, and Wavelet Packet Decomposition) are employed for time series decomposition. Then, for each Intrinsic Mode Function (IMF) component resulting from the decomposition block, five machine learning and three deep learning algorithms are utilized, serving as local forecasting models. In the final forecast phase, the best forecasting result for each regressor is selected during the reconstruction phase. Two years of photovoltaic power data recorded in three grid-connected photovoltaic systems installed in South Algeria were utilized for training and testing the proposed forecasting models. Upon comprehensive analysis and examination of the outcomes, the proposed method exhibits the lowest normalized Root Mean Square Error values across all forecast horizons and monitoring stations. Particularly, for forecasting steps at time intervals +1, +3, and +5, the proposed method attains an average normalized Root Mean Square Error, showcasing its efficacy: 0.709%, 2.097%, and 3.241% for station 1; 1.147%, 3.546%, and 5.347% for station 2; and 0.922%, 2.158%, and 4.539% for station 3. The experimental results underscore the superiority of our approach over conventional regression algorithms, thus substantiating its prowess in delivering robust and competitive performance outcomes. [ABSTRACT FROM AUTHOR]

Accurate and effective forecasting of short-term global solar radiation is critical for the development of photovoltaic systems, particularly for integration into existing grid systems. However, its non-stationary characteristics caused by climatic factors make its estimation extremely challenging. In this regard, a newly designed learning technique for multi-hour global solar radiation forecasting is proposed based on a time-varying filter-empirical mode decomposition (TVF-EMD), feature selection, and extreme learning machine (ELM) as an essence regression. The proposed hybridization strategy consists of three main steps for understanding the fundamental behavioral aspects of hourly global solar radiation data. The first phase employs the TVF-EMD algorithm to deal with the variability of global solar radiation data by separating it into a series of more stable and constant subseries. Then, the feature selection step is employed to evaluate and identify distinctive features set from the whole decomposed subseries by means of the RReliefF algorithm. The selected feature sets are used to train and optimize our forecasting extreme learning machine model, then the tuned ELM model is used to assess the forecasting accuracy. The proposed TVF-EMD-RF-ELM model is evaluated and validated in different regions in Algeria with various climate conditions. The forecasting findings of the TVF-EMD algorithm demonstrate high accuracy compared to the recent version of empirical mode decomposition CEEMDAN. Overall forecasting periods, the TVF-EMD-RF-ELM model produces an error less than 8.3% in terms of normalized root mean square error nRMSE in all studied regions. • A detailed review of different decomposition techniques for global solar radiation forecasting. • An improved artificial intelligence model for multi-hour solar radiation forecasting has been developed. • A regional examination is established, with three sites. • The proposed hybrid model is validated against several models. • The suggested model has been validated for its ability to forecast hourly global solar radiation. [ABSTRACT FROM AUTHOR]

[Display omitted] • A new hybrid model IF-ELM is developed for multi-step ahead forecasting of PV power. • Two different architectures of IF-ELM are proposed. • Three PV plants database are analyzed. • Proposed IF-ELM boost the forecasting performance of PV power output compared to existing approaches. Photovoltaic (PV) solar power, which is considered as the most competitive clean energy source, contributes to a significant percentage of electricity production in many developed countries. However, accurate PV power forecasting is necessary due to its high variation that can be caused by several factors. Hence, the intermittent nature of PV production represents a major challenge to integrate PV systems into the electric grid. The scope of this paper deals with this issue through developing a new integrated PV power forecasting model. The proposed model is based on the use of a new decomposition methodology, named Iterative Filtering for decomposing PV power into different intrinsic functions (IMFs), then Extreme Learning Machine (ELM) is used as essence predictor. To this end, the proposed IF-ELM model is evaluated on three solar PV power plants installed at three different sites, with different climatic conditions. Direct and recursive IF-ELM methodologies are examined for multi-step ahead forecasting in a very short time-scale (up to 60 min). Overall, the forecasting results show high precision performance for the studied forecasting horizons- in terms of different statistical metrics compared to stand-alone models. Also, the proposed IF method shows its high performance when compared to the recently developed decomposition method. complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) in improving the forecasting accuracy of a single model. Forecasting results with the IF-ELM model led to an error in nRMSE that is less than 10% and a Correlation Coefficient greater than 98% over all forecasting horizons. [ABSTRACT FROM AUTHOR]

Solar radiation components assessment is a highly required parameter for solar energy applications. Due to the non-stationary behavior of solar radiation parameters and variety of atmosphere conditions, stand-alone forecasting models are insufficient for providing accurate estimation in some cases. In this respect, different hybrid models have been proposed in recent years to overcome the limitations of single models and boost the forecasting precision. In this paper, acomprehensive literature review of the recent trends in hybrid model techniques for solar radiation components assessment is presented. The main objective behind this study is to present a comparative study between different hybrid models, explore their application, and identify promising and potential models for solar radiation application assessment. The performance ranking of each hybrid model is complicated due the diversity of the data length and scale, forecasting horizon, performance metrics, time step and climate condition. Overall, the presented study provides preliminary guidelines for a complete view of the hybrid models and tools that can be used in order to improve solar radiation assessment. • In-depth review of different hybrid methods for solar radiation forecasting is presented. • Forecasting horizon for each category is discussed. • Worldwide regions and data are investigated. [ABSTRACT FROM AUTHOR]