Search

This paper focuses on the development and testing of the genetic algorithm (GA)-based regional flood frequency analysis (RFFA) models for eastern parts of Australia. The GA-based techniques do not impose a fixed model structure on the data and can better deal with nonlinearity of the input and output relationship. These nonlinear techniques have been applied successfully in many hydrologic problems; however, there have been only limited applications of these techniques in RFFA problems, particularly in Australia. A data set comprising of 452 stations is used to test the GA for artificial neural networks (ANN) optimization known as GAANN. The results from GAANN were compared with the results from back-propagation for ANN optimization known as BPANN. An independent testing shows that both the GAANN and BPANN methods are quite successful in RFFA and can be used as alternative methods to check the validity of the traditional linear models such as quantile regression technique. [ABSTRACT FROM AUTHOR]

Hybrid offshore renewable energy platforms have been proposed to optimise power production and reduce the levelised cost of energy by integrating or co-locating several renewable technologies. One example is a hybrid wave-wind energy system that combines offshore wind turbines with wave energy converters (WECs) on a single floating foundation. The design of such systems involves multiple parameters and performance measures, making it a complex, multi-modal, and expensive optimisation problem. This paper proposes a novel, robust and effective multi-objective swarm optimisation method (DMOGWA) to provide a design solution that best compromises between maximising WEC power output and minimising the effect on wind turbine nacelle acceleration. The proposed method uses a chaotic adaptive search strategy with a dynamic archive of non-dominated solutions based on diversity to speed up the convergence rate and enhance the Pareto front quality. Furthermore, a modified exploitation technique (Discretisation Strategy) is proposed to handle the large damping and spring coefficient of the Power Take-off (PTO) search space. To evaluate the efficiency of the proposed method, we compare the DMOGWA with four well-known multi-objective swarm intelligence methods (MOPSO, MALO, MODA, and MOGWA) and four popular evolutionary multi-objective algorithms (NSGA-II, MOEA/D, SPEA-II, and PESA-II) based on four potential deployment sites on the South Coast of Australia. The optimisation results demonstrate the dominance of the DMOGWA compared with the other eight methods in terms of convergence speed and quality of solutions proposed. Furthermore, adjusting the hybrid wave-wind model's parameters (WEC design and PTO parameters) using the proposed method (DMOGWA) leads to a considerably improved power output (average proximate boost of 138.5%) and a notable decline in wind turbine nacelle acceleration (41%) throughout the entire operational spectrum compared with the other methods. This improvement could lead to millions of dollars in additional income per year over the lifespan of hybrid offshore renewable energy platforms. • A new multiobjective optimisation method proposed and enhanced hybrid wave-wind platform. • A new combination of chaotic adaptive exploration and dynamic archive is introduced. • Effective and practical discretisation method improved performance of hybrid platform. • The performance of the proposed optimiser is validated on four real sea studies. [ABSTRACT FROM AUTHOR]

In this paper, a modified backpropagation neural network is combined with a chaos-search genetic algorithm and simulated annealing algorithm for very short term electrical energy demand prediction in deregulated power industry. Multiple modifications are carried out on the conventional backpropagation algorithm such as improvements in the momentum factor and adaptive learning rate. In the hybrid scheme, the initial parameters of the modified neural network are optimized by using the global search ability of genetic algorithm, improved by cat chaotic mapping to enrich its optimization capability. The solution set provided by the optimized genetic algorithm is further improved by using the strong local search ability of simulated annealing algorithm. The real data of New South Wales, Australian grid, is used in the experimentation for 1-h-ahead forecast with an emphasis on data analysis and preprocessing framework. The correlation analysis is used for the identification and selection of the most influential input variables. The simulation results reveal that the proposed combination technique effectively enhanced the prediction accuracy as compared to the available conventional methods. The prediction of 1-h-ahead load demand is critically important for decision-making response of the modern smart grid system. The acceptable precision of the proposed model concludes that it can be applied in the smart grid to enhance its demand responsiveness and other intelligent features. [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]

Several climatic variables like precipitation, temperature, fog, dew, humidity, and wind significantly impact agricultural production. While formulating policies for agriculture and other industrial sectors, precise knowledge regarding climatic variables is essential and helpful. The Bureau of Meteorology (BOM) monitored various climatic variables at more than 226 meteorological stations in New South Wales (NSW), Australia. However, the placement of these monitoring stations was not systematic. As a result, predictions for unobserved sites turn out to be erroneous. Inadequate or poorly placed meteorological stations can lead to inaccurate weather forecasts, make it difficult to fully understand local and regional weather patterns, and, lastly, make it impossible to identify the early warnings for severe weather events like hurricanes, tornadoes, and flash floods. Therefore, the study aims to optimize and suggest a monitoring network to minimize the prediction error of these climatic variables. The optimized monitoring network can be found by optimally adding new meteorological monitoring stations or withdrawing existing ones while still ensuring the reliability of weather data. In this study, the meteorological monitoring network of NSW, Australia was optimized using two stochastic search algorithms: Spatial Simulated Annealing (SSA) and Genetic Algorithms (GA). The Average Kriging Variance (AKV) is considered an accuracy measure for SSA and GA. Ordinary kriging (OK) and Universal Kriging (UK), two popular prediction methods, are used using covariation modeled by the Matheron variogram model. The results reveal that the time consumption for SSA and GA are relatively similar, but the SSA utilizing the UK gives a lower AKV than GA. The optimized meteorological monitoring will be useful for ensuring accurate weather forecasts, providing early warnings of severe weather events, and enabling scientific research to understand and mitigate the effects of climate change. Furthermore, this novel optimization strategy will not only be helpful for the government of Australia but will significantly improve prediction accuracy, providing more reliable information for various weather-related activities, such as agriculture, construction, and emergency management. [ABSTRACT FROM AUTHOR]

Satellite remote sensing provides a unique opportunity for calibrating land surface models due to their direct measurements of various hydrological variables as well as extensive spatial and temporal coverage. This study aims to apply terrestrial water storage (TWS) estimated from the gravity recovery and climate experiment (GRACE) mission as well as soil moisture products from advanced microwave scanning radiometer–earth observing system (AMSR-E) to calibrate a land surface model using multi-objective evolutionary algorithms. For this purpose, the non-dominated sorting genetic algorithm (NSGA) is used to improve the model's parameters. The calibration is carried out for the period of two years 2003 and 2010 (calibration period) in Australia, and the impact is further monitored over 2011 (forecasting period). A new combined objective function based on the observations' uncertainty is developed to efficiently improve the model parameters for a consistent and reliable forecasting skill. According to the evaluation of the results against independent measurements, it is found that the calibrated model parameters lead to better model simulations both in the calibration and forecasting period. [ABSTRACT FROM AUTHOR]

Data-driven models provide upgradeable environments to simulate inflow to reservoirs. An important aspect in the development of an adaptive neural fuzzy inference system (ANFIS) model is to choose the correct procedure (i.e. efficient and effective) to train the model. In this study, a daily timescale ANFIS-based model was developed to simulate aggregated monthly long-term inflow to the Ross River reservoir in northern Queensland, Australia. The suitability of different evolutionary algorithms (EAs) was evaluated to train an ANFIS-based model, including a genetic algorithm (GA), particle swarm optimisation (PSO), shuffled frog leaping algorithm, biogeography-based optimisation, harmony search algorithm, differential evolution algorithm, invasive weed optimisation (IWO) and a cultural algorithm. Four indices – the root mean square error, Nash–Sutcliffe efficiency, reliability index and vulnerability index – were used to measure the performance of the model. It was found that application of either IWO, GA or PSO provided accurate simulated inflow time series. The outputs obtained using the other EAs were not sufficiently accurate. Use of a coupled EA–ANFIS-based model was found to improve the accuracy of simulating long-term monthly inflow compared with other models used in a few previous recent studies. [ABSTRACT FROM AUTHOR]

Abstract: This work defines Transit Schedule Design (TSD) as an optimization problem to construct the transit schedule with the decision variables of the location of timing points and the amount of slack time associated with each timing point. Two heuristic procedures, Ant Colony and Genetic Algorithms, are developed for constructing optimal schedules for a fixed bus route. The paper presents a comparison of the fundamental features of the two algorithms. They are then calibrated based on data generated from micro-simulation of a bus route in Melbourne, Australia, to give rise to (near) optimal schedule designs. The algorithms are compared in terms of their accuracy and efficiency in providing the minimum cost solution. Although both procedures prove the ability to find the optimal solution, the Ant Colony procedure demonstrates a higher efficiency by evaluating less schedule designs to arrive at a ‘good’ solution. Potential benefits of the developed algorithms in bus route planning are also discussed. [Copyright &y& Elsevier]

Abstract: The Australian River Assessment System (AusRivAS) is a nation-wide programme designed to assess the health of Australian rivers and streams. In order to produce river health assessments, the AusRivAS method uses the outcomes of cluster analysis applied to macroinvertebrate data from a number of different locations. At present, the clustering step is conducted using the statistical Unweighted Pair Group Arithmetic Averaging (UPGMA) method. A potential shortcoming of this approach is that it uses a linear performance measure for grouping similar data points. A recently developed approach for clustering ecological data (MIR-max) overcomes this limitation by using mutual information as the performance measure. However, MIR-max uses a hill-climbing approach for optimising mutual information, which could become trapped in local optima of the search space. In this paper, the potential of using evolutionary algorithms (EAs), such as genetic algorithms and ant colony optimisation algorithms, for maximising the mutual information of ecological data clusters is investigated. The MIR-max and EA-based approaches are applied to the South Australian combined season riffle AusRivAS data, and the results obtained are compared with those obtained using the UPGMA method. The results indicate that the overall mutual information values of the clusters obtained using MIR-max and the EA-based approaches are significantly higher than those obtained using the UPGMA method, and that the use of genetic and ant colony optimisation algorithms is successful in determining clusters with higher overall mutual information values compared with those obtained using MIR-max for the case study considered. [Copyright &y& Elsevier]

Eradication programs for invasive ants are often hampered by a lack of effective tools to detect, contain and kill the pests. Among the range of tools employed in the course of a 20-year eradication program for red imported fire ant, Solenopsis invicta, in Australia, two of the most crucial for success are genetic analysis at both individual colony and population scales, and remote sensing for the detection of S. invicta mounds over large areas. Several genetic analyses are used by the program as an everyday operational tool to guide the eradication effort; for example, genotyping of the social form determines where and how far we need to search and treat, whereas nest relatedness derived from microsatellites aids in deciding when and where to target investigations into human-assisted movement of the pest. Microsatellite genotyping can determine the origin of new invasions into the country and has been used to verify the eradication of six distinct incursions of S. invicta in Australia, as well as demonstrating the pressure being exerted on the remaining Queensland population by the current eradication activities. Remote sensing played a key role in delimiting the extent of the S. invicta infestation in southeast Queensland in 2015, and in the future will assist in both delimitation and in verifying eradication of this ant in treatment areas as part of the proof of freedom process. Unquestionably, without these tools, the battle to eradicate S. invicta from Australia would be severely constrained, if not lost. These technologies may be applicable in management or eradication programs for S. invicta worldwide, and potentially for other invasive ant species. [ABSTRACT FROM AUTHOR]

Deep learning approaches have shown superior advantages than shallow techniques in the field of electrical load forecasting; however, their applications in existing studies encounter thorny issues despite their excellent forecasting performance: heavy computing costs due to complicated network structure and restricted to the deterministic point forecasting. This paper aims to solve above two problems by proposing a deep learning approach based on K -nearest neighbors to capture uncertainty and reflect the range of electrical load fluctuation. First, the K -nearest neighbors algorithm is applied to seek features of historical electrical load time series that are similar to the future values by calculating the distance between the training and testing datasets. Then the second generation of non-dominated sorting genetic algorithm is adopted for multi-objective optimization to find out the smallest category number of K -nearest neighbors and the highest forecasting accuracy. Based on the forecasting results of the deep belief network, modified non-parameter kernel density estimation is used to obtain the prediction intervals. Five datasets collected from Australia are employed to examine the effectiveness of the proposed model. By a series of comparisons with other state-of-the-art models, experimental results confirm that the proposed interval forecasting model cannot only improve the forecasting efficiency and accuracy, but also simplify the forecasting process of deep learning approaches, which can provide great referential value for future work. • A KNN-based deep learning model for electrical load interval forecasting is proposed. • NSGA-II is adopted for multi-objective optimization to improve forecasting accuracy. • Modify non-parameter kernel density estimation to obtain prediction intervals. • The developed model outperforms traditional models in electrical load forecasting. [ABSTRACT FROM AUTHOR]

A methodology for determining the optimal spatial distribution of a river pollutant detection network using a geographic information system and genetic algorithms (GAs) is developed. Two case studies are investigated to evaluate the performance of the developed methodology: (1) a hypothesized river system consisting of only 11 reaches; (2) the Logan and Albert Rivers in Southeast Queensland. Plausible results are obtained, encouraging the possibility of applying GAs in designing a river monitoring network. [ABSTRACT FROM AUTHOR]

A central authority, in a conventional centralized energy trading market, superintends energy and financial transactions. The central authority manages and controls transparent energy trading between producer and consumer, imposes a penalty in case of contract violation, and disburses numerous rewards. However, the management and control through the third party pose a significant threat to the security and privacy of consumers'/producers' (participants) profiles. The energy transactions between participants involving central authority utilize users' time, money, and impose a computational burden over the central controlling authority. The Blockchain-based decentralized energy transaction concept, bypassing the central authority, is proposed in Smart Grid (SG) by researchers. Blockchain technology braces the concept of Peer-to-Peer (P2P) energy transactions. This work encompasses the SolarCoin-based digital currency blockchain model for SG incorporating RE. Energy transactions from Prosumer (P) to Prosumer, Energy District to Energy District, and Energy District to SG are thoroughly investigated and analyzed in this work. A robust demand-side optimized model is proposed using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) to maximize Prosumer Energy Surplus (PES), Grid revenue (GR), percentage energy transactions accomplished, and decreased Prosumer Energy Cost (PEC). Real-time averaged energy data of Australia are employed, and a piece-wise energy price mechanism is implemented in this work. The graphical analysis and tabular statistics manifest the efficacy of the proposed model. [ABSTRACT FROM AUTHOR]

Crude protein estimation is an important parameter for perennial ryegrass (Lolium perenne) management. This study aims to establish an effective and affordable approach for a non-destructive, near-real-time crude protein retrieval based solely on top-of-canopy reflectance. The study contrasts different spectral ranges while selecting a minimal number of bands and analyzing achievable accuracies for crude protein expressed as a dry matter fraction or on a weight-per-area basis. In addition, the model's prediction performance in known and new locations is compared. This data collection comprised 266 full-range (350–2500 nm) proximal spectral measurements and corresponding ground truth observations in Australia and the Netherlands from May to November 2018. An exhaustive-search (based on a genetic algorithm) successfully selected band subsets within different regions and across the full spectral range, minimizing both the number of bands and an error metric. For field conditions, our results indicate that the best approach for crude protein estimation relies on the use of the visible to near-infrared range (400–1100 nm). Within this range, eleven sparse broad bands (of 10 nm bandwidth) provide performance better than or equivalent to those of previous studies that used a higher number of bands and narrower bandwidths. Additionally, when using top-of-canopy reflectance, our results demonstrate that the highest accuracy is achievable when estimating crude protein on its weight-per-area basis (RMSEP 80 kg.ha − 1 ). These models can be employed in new unseen locations, resulting in a minor decrease in accuracy (RMSEP 85.5 kg.ha − 1 ). Crude protein as a dry matter fraction presents a bottom-line accuracy (RMSEP) ranging from 2.5–3.0 percent dry matter in optimal models (requiring ten bands). However, these models display a low explanatory ability for the observed variability (R2 > 0.5), rendering them only suitable for qualitative grading. [ABSTRACT FROM AUTHOR]