• Energy Research

The potential or reference evapotranspiration (ET0) is considered as one of the fundamental variables for irrigation management, agricultural planning, and modeling different hydrological pr°Cesses, and therefore, its accurate prediction is highly essential. The study validates the feasibility of new temperature based heuristic models (i.e., group method of data handling neural network (GMDHNN), multivariate adaptive regression spline (MARS), and M5 model tree (M5Tree)) for estimating monthly ET0. The outcomes of the newly developed models are compared with empirical formulations including Hargreaves-Samani (HS), calibrated HS, and Stephens-Stewart (SS) models based on mean absolute error (MAE), root mean square error (RMSE), and Nash-Sutcliffe efficiency. Monthly maximum and minimum temperatures (Tmax and Tmin) observed at two stations in Turkey are utilized as inputs for model development. In the applications, three data division scenarios are utilized and the effect of periodicity component (PC) on models’ accuracies are also examined. By importing PC into the model inputs, the RMSE accuracy of GMDHNN, MARS, and M5Tree models increased by 1.4%, 8%, and 6% in one station, respectively. The GMDHNN model with periodic input provides a superior performance to the other alternatives in both stations. The recommended model reduced the average error of MARS, M5Tree, HS, CHS, and SS models with respect to RMSE by 3.7–6.4%, 10.7–3.9%, 76–75%, 10–35%, and 0.8–17% in estimating monthly ET0, respectively. The HS model provides the worst accuracy while the calibrated version significantly improves its accuracy. The GMDHNN, MARS, M5Tree, SS, and CHS models are also compared in estimating monthly mean ET0. The GMDHNN generally gave the best accuracy while the CHS provides considerably over/under-estimations. The study indicated that the only one data splitting scenario may mislead the modeler and for better validation of the heuristic methods, more data splitting scenarios should be applied.

In recent studies, Thermo-Electric Coolers (TEC) have been utilized for dehumidification purposes, which is mainly based on the extraction of moisture from humid atmospheric air. The reviewed literature showed that the rate of water collection from the TEC-based system can be affected by various parameters such as the module’s input voltage, the heat sink orientation, and tilt angles. In this research, the analysis of variance (ANOVA) was used to examine the significance of these factors and their interaction within the system on the TEC-based dehumidification system. Four levels were investigated for both, the Peltier’s input voltage and the rotation angle, and three levels for the tilt angle. This study indicated the significance of the studied factors and their interactions within the dehumidification system along with performing an overall numerical optimization. The experiments were conducted under the same working conditions in an enclosed environment to minimize errors. According to the overall numerical optimization, which was validated experimentally, the optimum system performance was predicted to be obtained at approximately 6.8V Peltier input volt, 65° rotation angle, and 90° tilt angles, with predicted optimum productivities of 0.32278 L/kWh and 13.03 mL/hr. For the same set of parameters, the variation between the experiment and the numerical optimization was less than 4%. The experiments show that when optimizing water collection rates for thermoelectric cooling heat sinks​ under high humidity conditions, the orientation of the heat sink should be considered.

L'utilisation durable du rayonnement solaire librement disponible comme source d'énergie renouvelable nécessite des modèles prédictifs précis pour évaluer quantitativement les potentiels énergétiques futurs. Dans cette recherche, une évaluation de la précision du modèle de machine d'apprentissage extrême (ELM) en tant que cadre rapide et efficace pour estimer le rayonnement solaire incident global (G) est entreprise. Des ensembles de données météorologiques quotidiennes adaptés à l'estimation de G appartiennent aux parties nord du bassin de Cheliff, dans le nord-ouest de l'Algérie, et sont utilisés pour construire le modèle d'estimation. Des fonctions de corrélation croisée sont appliquées entre les entrées et la variable cible (c'est-à-dire G) où plusieurs informations climatologiques sont utilisées comme prédicteurs pour l'estimation du niveau de surface G. Les entrées de modèle les plus significatives sont déterminées conformément aux corrélations croisées les plus élevées compte tenu de la covariance des prédicteurs avec l'ensemble de données G. Par la suite, sept modèles ELM avec des architectures neuronales uniques en termes de neurones d'entrée-sortie cachés sont développés avec des combinaisons d'entrée appropriées. Les performances d'estimation du modèle ELM prescrit au cours de la phase de test sont évaluées par rapport à des régressions linéaires multiples (MLR), à des modèles de moyenne mobile intégrée autorégressive (ARIMA) et à plusieurs études documentaires bien établies. Cela se fait conformément à plusieurs mesures de score statistiques. En termes quantitatifs, l'erreur quadratique moyenne (RMSE) et l'erreur absolue moyenne (MAE) sont considérablement plus faibles pour le modèle ELM optimal avec RMSE et MAE = 3,28 et 2,32 Wm -2 par rapport à 4,24 et 3,24 Wm -2 (MLR) et 8,33 et 5,37 Wm -2 (ARIMA). La utilización sostenible de la radiación solar disponible gratuitamente como fuente de energía renovable requiere modelos predictivos precisos para evaluar cuantitativamente los potenciales energéticos futuros. En esta investigación, se realiza una evaluación de la precisión del modelo de máquina de aprendizaje extremo (ELM) como un marco rápido y eficiente para estimar la radiación solar incidente global (G). Los conjuntos de datos meteorológicos diarios adecuados para la estimación de G pertenecen a las partes septentrionales de la cuenca de Cheliff en el noroeste de Argelia, se utilizan para construir el modelo de estimación. Las funciones de correlación cruzada se aplican entre las entradas y la variable objetivo (es decir, G), donde se utilizan varias informaciones climatológicas como predictores para la estimación del nivel de superficie G. Las entradas del modelo más significativas se determinan de acuerdo con las correlaciones cruzadas más altas considerando la covarianza de los predictores con el conjunto de datos G. Posteriormente, se desarrollan siete modelos ELM con arquitecturas neuronales únicas en términos de sus neuronas de entrada-salida oculta con combinaciones de entrada apropiadas. El rendimiento de estimación del modelo ELM prescrito durante la fase de prueba se evalúa frente a regresiones lineales múltiples (MLR), modelos de media móvil integrada autorregresiva (ARIMA) y varios estudios de literatura bien establecidos. Esto se hace de acuerdo con varias métricas de puntuación estadística. En términos cuantitativos, el error cuadrático medio (RMSE) y el error absoluto medio (MAE) son dramáticamente más bajos para el modelo ELM óptimo con RMSE y MAE = 3.28 y 2.32 Wm -2 en comparación con 4.24 y 3.24 Wm -2 (MLR) y 8.33 y 5.37 Wm -2 (ARIMA). Sustainable utilization of the freely available solar radiation as renewable energy source requires accurate predictive models to quantitatively evaluate future energy potentials. In this research, an evaluation of the preciseness of extreme learning machine (ELM) model as a fast and efficient framework for estimating global incident solar radiation (G) is undertaken. Daily meteorological datasets suitable for G estimation belongs to the northern parts of the Cheliff Basin in Northwest Algeria, is used to construct the estimation model. Cross-correlation functions are applied between the inputs and the target variable (i.e., G) where several climatological information's are used as the predictors for surface level G estimation. The most significant model inputs are determined in accordance with highest cross-correlations considering the covariance of the predictors with the G dataset. Subsequently, seven ELM models with unique neuronal architectures in terms of their input-hidden-output neurons are developed with appropriate input combinations. The prescribed ELM model's estimation performance over the testing phase is evaluated against multiple linear regressions (MLR), autoregressive integrated moving average (ARIMA) models and several well-established literature studies. This is done in accordance with several statistical score metrics. In quantitative terms, the root mean square error (RMSE) and mean absolute error (MAE) are dramatically lower for the optimal ELM model with RMSE and MAE = 3.28 and 2.32 Wm -2 compared to 4.24 and 3.24 Wm -2 (MLR) and 8.33 and 5.37 Wm -2 (ARIMA). يتطلب الاستخدام المستدام للإشعاع الشمسي المتاح مجانًا كمصدر للطاقة المتجددة نماذج تنبؤية دقيقة للتقييم الكمي لإمكانات الطاقة المستقبلية. في هذا البحث، يتم إجراء تقييم لدقة نموذج آلة التعلم المتطرفة (ELM) كإطار سريع وفعال لتقدير الإشعاع الشمسي الساقط العالمي (G). مجموعات بيانات الأرصاد الجوية اليومية المناسبة لتقدير G تنتمي إلى الأجزاء الشمالية من حوض Cheliff في شمال غرب الجزائر، ويستخدم لبناء نموذج التقدير. يتم تطبيق وظائف الارتباط المتبادل بين المدخلات والمتغير المستهدف (أي G) حيث يتم استخدام العديد من المعلومات المناخية كمؤشرات لتقدير المستوى السطحي G. يتم تحديد مدخلات النموذج الأكثر أهمية وفقًا لأعلى الارتباطات المتبادلة مع الأخذ في الاعتبار التباين المشترك للمتنبئين مع مجموعة البيانات G. في وقت لاحق، يتم تطوير سبعة نماذج ELM مع بنى عصبية فريدة من نوعها من حيث الخلايا العصبية المخفية للمدخلات والمخرجات مع تركيبات المدخلات المناسبة. يتم تقييم أداء تقدير نموذج علم المحدد خلال مرحلة الاختبار مقابل الانحدارات الخطية المتعددة (MLR)، ونماذج المتوسط المتحرك المتكامل الانحداري الذاتي (ARIMA) والعديد من الدراسات الأدبية الراسخة. ويتم ذلك وفقًا للعديد من مقاييس الدرجات الإحصائية. من الناحية الكمية، فإن متوسط خطأ الجذر التربيعي (RMSE) ومتوسط الخطأ المطلق (MAE) أقل بشكل كبير لنموذج ELM الأمثل مع RMSE و MAE = 3.28 و 2.32 Wm -2 مقارنة بـ 4.24 و 3.24 Wm -2 (MLR) و 8.33 و 5.37 Wm -2 (ARIMA).

In low-latitude areas less than 10° in latitude angle, the solar radiation that goes into the solar still increases as the cover slope approaches the latitude angle. However, the amount of water that is condensed and then falls toward the solar-still basin is also increased in this case. Consequently, the solar yield still is significantly decreased, and the accuracy of the prediction method is affected. This reduction in the yield and the accuracy of the prediction method is inversely proportional to the time in which the condensed water stays on the inner side of the condensing cover without collection because more drops will fall down into the basin of the solar-still. Different numbers of scraper motions per hour (NSM), that is, 1, 2, 3, 4, 5, 6, and 7, are implemented to increase the hourly yield of solar still (HYSS) of the double-slope solar still hybrid with rubber scrapers (DSSSHS) in areas at low latitudes and develop an accurate model for forecasting the HYSS. The proposed model is developed by determining the best values of the constant factors that are associated with NSM, and the optimal values of exponent (n) and the unknown constant (C) for the Nusselt number expression (Nu). These variables are used in formulating the models for estimating HYSS. The particle swarm optimization (PSO) algorithm is used to solve the optimization problem, thereby determining the optimal yields. Water that condensed and accumulated inside the condensing glass cover of the DSSSHS is collected by increasing NSM. This process increases in the specific productivity of DSSSHS and the accuracy of the HYSS prediction model. Results show that the proposed model can consistently and accurately estimate HYSS. Based on the relative root mean square error (RRMSE), the proposed model PSO–HYSS attained a minimum value (2.81), whereas the validation models attained Dunkle’s (78.68) and Kumar and Tiwari’s (141.37).

In this research, two hybrid intelligent models are proposed for prediction accuracy enhancement for wind speed and power modeling. The established models are based on the hybridisation of Ensemble Empirical Mode Decomposition (EEMD) with a Pattern Sequence-based Forecasting (PSF) model and the integration of EEMD-PSF with Autoregressive Integrated Moving Average (ARIMA) model. In both models (i.e., EEMD-PSF and EEMD-PSF-ARIMA), the EEMD method is used to decompose the time-series into a set of sub-series and the forecasting of each sub-series is initiated by respective prediction models. In the EEMD-PSF model, all sub-series are predicted using the PSF model, whereas in the EEMD-PSF-ARIMA model, the sub-series with high and low frequencies are predicted using PSF and ARIMA, respectively. The selection of the PSF or ARIMA models for the prediction process is dependent on the time-series characteristics of the decomposed series obtained with the EEMD method. The proposed models are examined for predicting wind speed and wind power time-series at Maharashtra state, India. In case of short-term wind power time-series prediction, both proposed methods have shown at least 18.03 and 14.78 percentage improvement in forecast accuracy in terms of root mean square error (RMSE) as compared to contemporary methods considered in this study for direct and iterated strategies, respectively. Similarly, for wind speed data, those improvement observed to be 20.00 and 23.80 percentages, respectively. These attained prediction results evidenced the potential of the proposed models for the wind speed and wind power forecasting. The current proposed methodology is transformed into R package ‘decomposedPSF’ which is discussed in the Appendix.