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]

A large proportion of photovoltaic (PV) power generation is connected to the power grid, and its volatility and stochasticity have significant impacts on the power system. Accurate PV power forecasting is of great significance in optimizing the safe operation of the power grid and power market transactions. In this paper, a novel dual-channel PV power forecasting method based on a temporal convolutional network (TCN) is proposed. The method deeply integrates the PV station feature data with the model computing mechanism through the dual-channel model architecture; utilizes the combination of multihead attention (MHA) and TCN to extract the multidimensional spatio-temporal features between other meteorological variables and the PV power; and utilizes a single TCN to fully extract the temporal constraints of the power sequence elements. The weighted fusion of the dual-channel feature data ultimately yields the ideal forecasting results. The experimental data in this study are from a 26.52 kW PV power plant in central Australia. The experiments were carried out over seven different input window widths, and the two models that currently show superior performance within the field of PV power forecasting: the convolutional neural network (CNN), and the convolutional neural network combined with a long and short-term memory network (CNN_LSTM), are used as the baseline models. The experimental results show that the proposed model and the baseline models both obtained the best forecasting performance over a 1-day input window width, while the proposed model exhibited superior forecasting performance compared to the baseline model. It also shows that designing model architectures that deeply integrate the data input method with the model mechanism has research potential in the field of PV power forecasting. [ABSTRACT FROM AUTHOR]

To solve the problem of feature selection and error correction after mode decomposition and improve the ability of power load forecasting models to capture complex time series information, a two-stage short-term power load forecasting method based on recursive feature elimination with a cross validation (RFECV) algorithm and time convolution network–efficient channel attention mechanism–long short-term memory network (TCN–ECA–LSTM) is presented. First, the load sequence is decomposed into a relatively stable set of modal components using variational mode decomposition. Then, the RFECV-based method filters the feature set of each modal component to construct the best feature set. Finally, a two-stage prediction model based on TCN–ECA–LSTM is established. The first stage predicts each modal component and the second stage reconstructs the load forecast based on the predicted value of the previous stage. This paper takes actual data from New South Wales, Australia, as an example, and the results show that the method proposed in this paper can build the feature set reliably and efficiently and has a higher accuracy than the conventional prediction model. [ABSTRACT FROM AUTHOR]

Accurate short-term power load forecasting is crucial to maintaining a balance between energy supply and demand, thus minimizing operational costs. However, the intrinsic uncertainty and non-linearity of load data substantially impact the accuracy of forecasting results. To mitigate the influence of these uncertainties and non-linearity in electric load data on the forecasting results, we propose a hybrid network that integrates variational mode decomposition with a temporal convolutional network (TCN) and a bidirectional gated recurrent unit (BiGRU). This integrated approach aims to enhance the accuracy of short-term power load forecasting. The method was validated on load datasets from Singapore and Australia. The MAPE of this paper's model on the two datasets reached 0.42% and 1.79%, far less than other models, and the R2 reached 98.27% and 97.98, higher than other models. The experimental results show that the proposed network exhibits a better performance compared to other methods, and could improve the accuracy of short-term electricity load forecasting. [ABSTRACT FROM AUTHOR]

Fires in buildings are significant public safety hazards and can result in fatalities and substantial financial losses. Studies have shown that the socioeconomic makeup of a region can impact the occurrence of building fires. However, existing models based on the classical stepwise regression procedure have limitations. This paper proposes a more accurate predictive model of building fire rates using a set of socioeconomic variables. To improve the model's forecasting ability, a backward elimination by robust final predictor error (RFPE) criterion is introduced. The proposed approach is applied to census and fire incident data from the South East Queensland region of Australia. A cross-validation procedure is used to assess the model's accuracy, and comparative analyses are conducted using other elimination criteria such as p-value, Akaike's information criterion (AIC), Bayesian information criterion (BIC), and predicted residual error sum of squares (PRESS). The results demonstrate that the RFPE criterion is a more accurate predictive model based on several goodness-of-fit measures. Overall, the RFPE equation was found to be a suitable criterion for the backward elimination procedure in the socioeconomic modeling of building fires. [ABSTRACT FROM AUTHOR]

High precision short-term photovoltaic (PV) power prediction can reduce the damage associated with large-scale photovoltaic grid-connection to the power system. In this paper, a combination deep learning forecasting method based on variational mode decomposition (VMD), a fast correlation-based filter (FCBF) and bidirectional long short-term memory (BiLSTM) network is developed to minimize PV power forecasting error. In this model, VMD is used to extract the trend feature of PV power, then FCBF is adopted to select the optimal input-set to reduce the forecasting error caused by the redundant feature. Finally, the input-set is put into the BiLSTM network for training and testing. The performance of this model is tested by a case study using the public data-set provided by a PV station in Australia. Comparisons with common short-term PV power forecasting models are also presented. The results show that under the processing of trend feature extraction and feature selection, the proposed methodology provides a more stable and accurate forecasting effect than other forecasting models. [ABSTRACT FROM AUTHOR]

In this paper, a deep learning long-short-term memory (LSTM) method is applied to the forecasting of the critical frequency of the ionosphere F2 layer (foF2). Hourly values of foF2 from 10 ionospheric stations in China and Australia (based on availability) from 2006 to 2019 are used for training and verifying. While 2015 and 2019 are exclusive for verifying the forecasting accuracy. The inputs of the LSTM model are sequential data for the previous values, which include local time (LT), day number, solar zenith angle, the sunspot number (SSN), the daily F10.7 solar flux, geomagnetic the Ap and Kp indices, geographic coordinates, neutral winds, and the observed value of foF2 at the previous moment. To evaluate the forecasting ability of the deep learning LSTM model, two different neural network forecasting models: a back-propagation neural network (BPNN) and a genetic algorithm optimized backpropagation neural network (GABP) were established for comparative analysis. The foF2 parameters were forecasted under geomagnetic quiet and geomagnetic disturbed conditions during solar activity maximum (2015) and minimum (2019), respectively. The forecasting results of these models are compared with those of the international reference ionosphere model (IRI2016) and the measurements. The diurnal and seasonal variations of foF2 for the 4 models were compared and analyzed from 8 selected verification stations. The forecasting results reveal that the deep learning LSTM model presents the optimal performance of all models in forecasting the time series of foF2, while the IRI2016 model has the poorest forecasting performance, and the BPNN model and GABP model are between two of them. [ABSTRACT FROM AUTHOR]

Solar energy production is affected by the attenuation of incoming irradiance from underlying clouds. Often, improvements in the short-term predictability of irradiance using satellite irradiance models can assist grid operators in managing intermittent solar-generated electricity. In this paper, we develop and test a satellite irradiance model with short-term prediction capabilities using cloud motion vectors. Near-real time visible images from Himawari-8 satellite are used to derive cloud motion vectors using optical flow estimation techniques. The cloud motion vectors are used for the advection of pixels at future time horizons for predictions of irradiance at the surface. Firstly, the pixels are converted to cloud index using the historical satellite data accounting for clear, cloudy and cloud shadow pixels. Secondly, the cloud index is mapped to the clear sky index using a historical fitting function from the respective sites. Thirdly, the predicated all-sky irradiance is derived by scaling the clear sky irradiance with a clear sky index. Finally, a power conversion model trained at each site converts irradiance to power. The prediction of solar power tested at four sites in Australia using a one-month benchmark period with 5 min ahead prediction showed that errors were less than 10% at almost 34–60% of predicted times, decreasing to 18–26% of times under live predictions, but it outperformed persistence by >50% of the days with errors <10% for all sites. Results show that increased latency in satellite images and errors resulting from the conversion of cloud index to irradiance and power can significantly affect the forecasts. [ABSTRACT FROM AUTHOR]

During the austral summer 2018/19, devastating floods occurred over northeast Australia that killed approximately 625,000 head of cattle and inundated over 3000 homes in Townsville. In this paper, the disastrous event was identified as a record-breaking subseasonal peak rainfall event (SPRE). The SPRE was mainly induced by an anomalously strong monsoon depression that was modulated by the convective phases of an MJO and an equatorial Rossby (ER) wave. The ER wave originated from an active equatorial deep convection associated with the El Niño warm sea surface temperatures near the dateline over the central Pacific. Based on the S2S Project Database, we analyzed the extended-range forecast skill of the SPRE from two different perspectives, the monsoon depression represented by an 850-hPa wind shear index and the 15-day accumulated precipitation characterized by the percentile rank (PR) and the ratio to the three-month seasonal (DJF) totals. The results of four S2S models of this study suggest that the monsoon depression can maintain the same level of skill as the short-range (3 days) forecast up to 8–10 days. For precipitation parameters, the conclusions are similar to the monsoon depression. For the 2019 northern Queensland SPRE, the model forecast was, in general, worse than the expectation derived from the hindcast analysis. The clear modulation of the ER wave that enhanced the SPRE monsoon depression circulation and precipitation is suspected as the main cause for the lower forecast skill. The analysis procedure proposed in this study can be applied to analyze the SPREs and their associated large-scale drivers in other regions. [ABSTRACT FROM AUTHOR]

Early prediction of sugarcane crop yield at the commercial block level (unit area of a single crop of the same variety, ratoon or planting date) offers significant benefit to growers, consultants, millers, policy makers, crop insurance companies and researchers. This current study explored a remote sensing based approach for predicting sugarcane yield at the block level by further developing a regionally specific Landsat time series model and including individual crop sowing (or previous seasons' harvest) date. For the Bundaberg growing region of Australia this extends over a five months period, from July to November. For this analysis, the sugarcane blocks were clustered into 10 groups based on their specific planting or ratoon commencement date within the specified five months period. These clustered or groups of blocks were named 'bins'. Cloud free (<20%) satellite data from the polar-orbiting Landsat-8 (launched 2013), Sentinel-2A (launched 2015) and Sentinel-2B (launched 2017) sensors were acquired over the cane growing region in Bundaberg (area of 32,983 ha), from the growing season starting in July 2014, with the average green normalised difference vegetation index (GNDVI) derived for each block. The number of images acquired for each season was defined by the number of cloud free acquisitions. Using the Simple Linear Machine Learning (ML) algorithm, the extracted Landsat derived GNDVI values for each of the blocks were converted to Sentinel GNDVI. The average GNDVI of each 'bin' was plotted and a quadratic model was fitted through the time series to identify the peak growth stage defined as the maximum GNDVI value. The model derived maximum GNDVI values for each of the bins were then regressed against the average actual yield (t·ha-1) achieved for the respective bin over the five growing years, producing strong correlations (R2 = 0.92 to 0.99). The quadratic curves developed for the different bins were shifted according to the specific planting or ratoon date of an individual block allowing for the peak GNDVI value of the block to be calculated, regressed against the actual block yield (t·ha-1) and the prediction of yield to be made. To validate the accuracies of the 10 time series algorithms representing each of the 10 bins, 592 individual blocks were selected from the Bundaberg region during the 2019 harvest season. The crops were clustered into the appropriate bins with the respective algorithm applied. From a Sentinel image acquired on the 5 May 2019, the prediction accuracies were encouraging (R2 = 0.87 and RMSE = 11.33 (t·ha-1)) when compared to actual harvested yield, as reported by the mill. The results presented in this paper demonstrate significant progress in the accurate prediction of sugarcane yield at the individual sugarcane block level using a remote sensing, time-series based approach. [ABSTRACT FROM AUTHOR]

It is critically meaningful to accurately predict the ionospheric F2 layer critical frequency (foF2), which greatly limits the efficiency of communications, radar, and navigation systems. This paper introduced the entropy weight method to develop the combination prediction model (CPM) for long-term foF2 at Darwin (12.4° S, 131.5° E) in Australia. The weight coefficient of each individual model in the CPM is determined by using the entropy weight method after completing the simulation of the individual model in the calibration period. We analyzed two sets of data to validate the method used in this study: One set is from 2000 and 2009, which are included in the calibration period (1998–2016), and the other set is outside the calibration cycle (from 1997 and 2017). To examine the performance, the root mean square error (RMSE) of the observed monthly median foF2 value, the proposed CPM, the Union Radio Scientifique Internationale (URSI), and the International Radio Consultative Committee (CCIR) are compared. The yearly RMSE average values calculated from CPM were less than those calculated from URSI and CCIR in 1997, 2000, 2009, and 2017. In 2000 and 2009, the average percentage improvement between CPM and URSI is 9.01%, and the average percentage improvement between CPM and CCIR is 13.04%. Beyond the calibration period, the average percentage improvement between CPM and URSI is 13.2%, and the average percentage improvement between CPM and CCIR is 12.6%. The prediction results demonstrated that the proposed CPM has higher precision of prediction and stability than that of the URSI and CCIR, both within the calibration period and outside the calibration period. [ABSTRACT FROM AUTHOR]

Electricity load forecasting plays an essential role in improving the management efficiency of power generation systems. A large number of load forecasting models aiming at promoting the forecasting effectiveness have been put forward in the past. However, many traditional models have no consideration for the significance of data preprocessing and the constraints of individual forecasting models. Moreover, most of them only focus on the forecasting accuracy but ignore the forecasting stability, resulting in nonoptimal performance in practical applications. This paper presents a novel hybrid model that combines an advanced data preprocessing strategy, a deep neural network, and an avant-garde multi-objective optimization algorithm, overcoming the defects of traditional models and thus improving the forecasting performance effectively. In order to evaluate the validity of the proposed hybrid model, the electricity load data sampled in 30-min intervals from Queensland, Australia are used as a case to study. The experiments show that the new proposed model is obviously superior to all other traditional models. Furthermore, it provides an effective technical forecasting means for smart grid management. [ABSTRACT FROM AUTHOR]