Decomposing global solar radiation into its diffuse and direct normal radiation

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].

show abstract

“…The latitude and longitude of the selected cities are shown in Table 2. 21 These locations are also shown on the map of Algeria in Figure 2.…”

Section: Meteorological Datamentioning

confidence: 89%

“…We have selected three cities that cover the different climatic regions, namely Algiers, Ghardaïa, and Adrar. The latitude and longitude of the selected cities are shown in Table 2 21 . These locations are also shown on the map of Algeria in Figure 2.…”

Section: General Methodologymentioning

confidence: 99%

Multi‐hour ahead forecasting of building energy through a new integrated model

Cherier

Hamdani

Guermoui

et al. 2022

Env Prog and Sustain Energy

Self Cite

View full text Add to dashboard Cite

show abstract

“…Synaptic weights connecting nodes are adjusted to minimize output errors. ANNs are adept at supervised learning when trained with labeled data using algorithms like the vanishing gradient method [94][95][96].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Advancements and Prospects of Electronic Nose in Various Applications: A Comprehensive Review

Rabehi,

Helal,

Zappa

et al. 2024

Applied Sciences

Self Cite

View full text Add to dashboard Cite

An electronic nose, designed to replicate human olfaction, captures distinctive ‘fingerprint’ data from mixed gases or odors. Comprising a gas sensing system and an information processing unit, electronic noses have evolved significantly since their inception in the 1980s. They have transitioned from bulky, costly, and energy-intensive devices to today’s streamlined, economical models with minimal power requirements. This paper presents a comprehensive and systematic review of the electronic nose technology domain, with a special focus on advancements over the last five years. It highlights emerging applications, innovative methodologies, and potential future directions that have not been extensively covered in previous reviews. The review explores the application of electronic noses across diverse fields such as food analysis, environmental monitoring, and medical diagnostics, including new domains like veterinary pathology and pest detection. This work aims to underline the adaptability of electronic noses and contribute to their continued development and application in various industries, thereby addressing gaps in current literature and suggesting avenues for future research.

show abstract

“…The estimated values and the measured values, when compared, in this work, using different statistical indexes, results in the assessment of the performance of models: Root Mean Square Error (RMSE), Relative Square Error (rRMSE), Determination Coefficient (R2), and Correlation Coefficient(r) (Gairaa et al, 2019) (Rabehi et al, 2020).…”

Section: Model Validation Metricsmentioning

confidence: 99%

Hybrid Models for Daily Global Solar Radiation Assessment

Souahlia

Rabehi

2023

J. Eng. Exact Sci.

View full text Add to dashboard Cite

Daily solar radiation forecasting has recently become critical in developing solar energy and its integration into grid systems. Despite the huge number of proposed forecasting techniques, an accurate estimation remains a significant challenge because of the non-stationary variation of solar radiation components due to the continuously changing climatic conditions. Usually, several input data predictors are used for the forecasting process, which can cause redundancy and correlation between data features. This work assesses a set of feature selection techniques to check their ability to select the relevant predictors and reduce redundant and irrelevant information. An Artificial Neural Network is used to fit the measured solar radiation based on the selected features. The developed model is evaluated through various objective evaluation metrics using historical data of three years measured at the Ghardaiaregion inAlgeria. Results show the effectiveness of the proposed method, where values of 0,0189, 0.0286, 5.4387, and 98.28% have been found as MABE, RMSE, nRMSE and r, respectively.

show abstract

Decomposing global solar radiation into its diffuse and direct normal radiation

Cited by 8 publications

References 17 publications

Multi‐hour ahead forecasting of building energy through a new integrated model

Multi‐hour ahead forecasting of building energy through a new integrated model

Advancements and Prospects of Electronic Nose in Various Applications: A Comprehensive Review

Hybrid Models for Daily Global Solar Radiation Assessment

Contact Info

Product

Resources

About