Search

This paper introduces an innovative framework for wind power prediction that focuses on the future of energy forecasting utilizing intelligent deep learning and strategic feature engineering. This research investigates the application of a state-of-the-art deep learning model for wind energy prediction to make extremely short-term forecasts using real-time data on wind generation from New South Wales, Australia. In contrast with typical approaches to wind energy forecasting, this model relies entirely on historical data and strategic feature engineering to make predictions, rather than relying on meteorological parameters. A hybrid feature engineering strategy that integrates features from several feature generation techniques to obtain the optimal input parameters is a significant contribution to this work. The model's performance is assessed using key metrics, yielding optimal results with a Mean Absolute Error (MAE) of 8.76, Mean Squared Error (MSE) of 139.49, Root Mean Squared Error (RMSE) of 11.81, R-squared score of 0.997, and Mean Absolute Percentage Error (MAPE) of 4.85%. Additionally, the proposed framework outperforms six other deep learning and hybrid deep learning models in terms of wind energy prediction accuracy. These findings highlight the importance of advanced data analysis for feature generation in data processing, pointing to its key role in boosting the precision of forecasting applications. [ABSTRACT FROM AUTHOR]

Paleomagnetic studies in the Lachlan Orogen have indicated rotation of elements within it, but the evidence for rotation is limited and has significant statistical uncertainty. This study presents a detailed paleomagnetic investigation, assisted by X-ray analysis of magnetic mineralogy of middle Cambrian to lower Silurian sedimentary and igneous rocks in Victoria and New South Wales. Four demagnetisation behaviours (types A, B, C and D) have been recognised. Type A is characterised by a single component, resulting in an approximately linear path over the magnetite unblocking temperature range. Type B specimens exhibit slow progressive demagnetisation over a wide temperature range, with clustering of demagnetised directions above the magnetite Curie temperature, indicating hematite. Behaviour C is also characterised by clustering of directions, but this extends over a wider temperature range. Samples with behaviour D show noisy and non-informative demagnetisation, indicating very low magnetic stability. Hysteresis data confirm that samples with behaviour B and C have high coercivities and remain unsaturated above 300 mT. Mineral liberation analysis of selected samples indicates presence of iron oxides, magnetite, titanomagnetite, botryoidal hematite and iron hydroxides. Only three sites yielded specimens with type A primary magnetisation, with a poorly defined pole from the Dookie Volcanics on the central limb of the orocline, which does match a previous result from the same district. Two paleopoles, of type B and C specimens from the rocks in Tabberabbera Zone and the Rockley Volcanics, plot within the confidence limit of poles defining the late Silurian to Early Devonian Australian apparent polar wander path. These poles match other poles representing Devonian overprints around the margins of the Lachlan Orogen that have been interpreted to be the result of alteration mineralisation produced by fluids driven by tectonic compression during events in the Bindian (420–410 Ma) or early Tabberabberan (405–380 Ma) orogenies. Paleomagnetic techniques have been used to test the rotation within the elements of the Lachlan Orocline in southeast Australia. Results suggest that the original remanence in the rocks is obscured owing to post-deformation overprint. This overprint is widespread in the Lachlan Orogen and is associated with the deformation during Bindian/Tabberabberan orogenic events. [ABSTRACT FROM AUTHOR]

Stable electric load forecasting plays a significant role in power system operation and grid management. Improving the accuracy of electric load forecasting is not only a hot topic for energy managers and researchers of the power system, but also a fair challenging and difficult task due to its complex nonlinearity characteristics. This paper proposes a new combination model, which uses the least squares support vector machine, extreme learning machine, and generalized regression neural network to predict the electric load in New South Wales, Australia. In addition, the model employs a heuristic algorithm–whale optimization algorithm to optimize the weight coefficient. To verify the usability and generalization ability of the model, this paper also applies the proposed combined model to electricity price forecasting and compares it with the benchmark method. The experimental results demonstrate that the combined model not only can get accurate results for short-term electric load forecasting, but also achieves fine accuracy for the same period of electricity price forecasting. [ABSTRACT FROM AUTHOR]

This paper presents the results from a study on the application of an artificial neural network (ANN) model for regional flood frequency analysis (RFFA). The study was conducted using stream flow data from 88 gauging stations across New South Wales (NSW) in Australia. Five different models consisting of three to eight predictor variables (i.e., annual rainfall, drainage area, fraction forested area, potential evapotranspiration, rainfall intensity, river slope, shape factor and stream density) were tested. The results show that an ANN model with a higher number of predictor variables does not always improve the performance of RFFA models. For example, the model with three predictor variables performs considerably better than the models using a higher number of predictor variables, except for the one which contains all the eight predictor variables. The model with three predictor variables exhibits smaller median relative error values for 2- and 20-year return periods compared to the model containing eight predictor variables. However, for 5-, 10-, 50- and 100-year return periods, the model with eight predictor variables shows smaller median relative error values. The proposed ANN modelling framework can be adapted to other regions in Australia and abroad. [ABSTRACT FROM AUTHOR]