SqueezeNet for the forecasting of the energy demand using a combined version of the sewing training-based optimization algorithm

Simulating runoff changes and evaluating under climate change using CMIP6 data and the optimal SWAT model: a case study

This study examines the influence of climate change on hydrological processes, particularly runoff, and how it affects managing water resources and ecosystem sustainability. It uses CMIP6 data to analyze changes in runoff patterns under different Shared Socioeconomic Pathways (SSP). This study also uses a Deep belief network (DBN) and a Modified Sparrow Search Optimizer (MSSO) to enhance the runoff forecasting capabilities of the SWAT model. DBN can learn complex patterns in the data and improve the accuracy of runoff forecasting. The meta-heuristic algorithm optimizes the models through iterative search processes and finds the optimal parameter configuration in the SWAT model. The Optimal SWAT Model accurately predicts runoff patterns, with high precision in capturing variability, a strong connection between projected and actual data, and minimal inaccuracy in its predictions, as indicated by an ENS score of 0.7152 and an R2 coefficient of determination of 0.8012. The outcomes of the forecasts illustrated that the runoff will decrease in the coming years, which could threaten the water source. Therefore, managers should manage water resources with awareness of these conditions.

Evaluation of the impact of hydrological changes on reservoir water management: A comparative analysis the CanESM5 model and the optimized SWAT-SVR-LSTM

This research examines the impacts of climate change and socio-economic variables on the hydrological cycle, reservoir water management, and hydropower capacity at the Gezhouba Dam. The Gezhouba Dam serves as a crucial hydroelectric power station and dam, playing a vital role in regulating river flow and generating electricity. In this study, an innovative method is employed, combining the Soil and Water Assessment Tool (SWAT), Support Vector Regression (SVR), and Long Short-Term Memory (LSTM) models. This model is optimized using the Developed Thermal Exchange Optimizer. This optimized combined model significantly enhances the reliability and precision of the forecasting inflow and reservoir levels. By utilizing the Canadian Earth System Model version 5 (CanESM5), we examine climate variables across various scenarios of Representative Concentration Pathway (RCP) and Shared Socioeconomic Pathway (SSP). Under the SSP5-RCP8.5 scenario, the most aggressive in terms of emissions, we project a temperature rise of 2.6 % and a precipitation decrease of 2.7 %. This scenario leads to the most substantial changes in the hydrological cycle and altered river flow patterns. The results show a direct correlation between precipitation and inflow (0.952) and a strong inverse correlation between temperature and inflow (0.893). The study predicts significant decreases in all flow metrics, with mean high flow (Q5) periods affecting hydropower generation, especially under the SSP5-RCP8.5 scenario. Additionally, the filling frequency rate (FFR) and mean filling level (MFL) are projected to decrease, with a more pronounced decline in the far future, indicating a potential compromise of the reservoir's water storage and power generation capabilities, especially under the SSP5-RCP8.5 scenario.

Optimizing electric load forecasting with support vector regression/LSTM optimized by flexible Gorilla troops algorithm and neural networks a case study

This research work focuses on addressing the challenges of electric load forecasting through the combination of Support Vector Regression and Long Short-Term Memory (SVR/LSTM) methodology. The model has been modified by a flexible version of the Gorilla Troops optimization algorithm. The objective of this study is to enhance the precision and effectiveness of load forecasting models by integrating the adaptive functionalities of the Gorilla Troops algorithm within the SVR/LSTM framework. To assess the efficacy of the proposed methodology, a comprehensive series of experiments and evaluations have been undertaken, utilizing authentic data obtained from 200 residential properties located in Texas, United States of America. The dataset comprises historical records of electricity consumption, meteorological data, and other pertinent variables that exert an impact on energy demand. The presence of this general dataset enhances the dependability and inclusiveness of the empirical findings. The proposed methodology was evaluated against various contemporary load forecasting techniques that are widely employed in the industry. The results of a comprehensive evaluation and performance analysis indicate that the modified SVR/LSTM model exhibits superior performance compared to the existing methods in terms of accuracy and robustness. The comparison results unequivocally demonstrate the superiority of the proposed method in accurately forecasting electric load demand.

Assessing the impact of water scarcity on thermoelectric and hydroelectric potential and electricity price under climate change: Implications for future energy management

This study investigates the impact of water resource restrictions on thermoelectric and hydroelectric stations, analyzing its influence on demand and electricity prices. It uses General Circulation Models (GCMs) and Soil and Water Assessment Tools (SWAT) to forecast future temperature trends and estimate river flow patterns. The research provides insights into climate change's potential effects on water resources and electricity potential. The study shows a significant decrease in river flow, indicating potential issues with hydroelectric and thermoelectric systems. The study also uses an optimized Echo State Network (ESN) for accurate electricity demand, using the Modified Snow Leopard Optimization (MSLO) algorithm as a new metaheuristic model. The simulation results show a consistent increase in electricity demand scenarios, which is expected to lead to higher supply prices due to decreased production capacity. This could have significant economic effects. The investigation provides a comprehensive understanding of water resource management challenges in power production, aiding in informed decisions in the future energy industry.

Rigdelet neural network and improved partial reinforcement effect optimizer for music genre classification from sound spectrum images

In this paper, a new approach has been introduced for classifying the music genres. The proposed approach involves transforming an audio signal into a unified representation known as a sound spectrum, from which texture features have been extracted using an enhanced Rigdelet Neural Network (RNN). Additionally, the RNN has been optimized using an improved version of the partial reinforcement effect optimizer (IPREO) that effectively avoids local optima and enhances the RNN's generalization capability. The GTZAN dataset has been utilized in experiments to assess the effectiveness of the proposed RNN/IPREO model for music genre classification. The results show an impressive accuracy of 92 % by incorporating a combination of spectral centroid, Mel-spectrogram, and Mel-frequency cepstral coefficients (MFCCs) as features. This performance significantly outperformed K-Means (58 %) and Support Vector Machines (up to 68 %). Furthermore, the RNN/IPREO model outshined various deep learning architectures such as Neural Networks (65 %), RNNs (84 %), CNNs (88 %), DNNs (86 %), VGG-16 (91 %), and ResNet-50 (90 %). It is worth noting that the RNN/IPREO model was able to achieve comparable results to well-known deep models like VGG-16, ResNet-50, and RNN-LSTM, sometimes even surpassing their scores. This highlights the strength of its hybrid CNN-Bi-directional RNN design in conjunction with the IPREO parameter optimization algorithm for extracting intricate and sequential auditory data.

Developing a hybrid technique for energy demand forecasting based on optimized improved SVM by the boosted multi-verse optimizer: Investigation on affecting factors

Electricity demand prediction accuracy is crucial for operational energy resource management and strategy. In this study, we provide a multi-form model for electricity demand prediction in China that based on incorporating of an upgraded Support Vector Machine (SVM) and a Boosted Multi-Verse Optimizer (BMVO). The suggested model is proposed to address the shortcomings of existing prediction approaches, which frequently fail to internment the complicated nonlinear interactions between demand for electricity and the variables that influence it. The improved SVM algorithm incorporates a modified genetic algorithm based on kernel function for enhancing the stability of the model. The BMVO technique is employed to optimize the combined model's weights and increase its generalization effectiveness. The suggested approach is tested by real-world Chinese energy demand data. The findings show that it outperforms existing prediction approaches in terms of reliability and precision. Further, the number of samples chosen affects how well the proposed BMVO linked with the Incremental SVM (ISVM) predicts outcomes. Particularly, when 1735 samples are chosen, the lowest level of Mean Absolute Percent Error (MAPE) was noted. The Root Mean Square Error (RMSE) and MAPE values under the proposed BMVO/ISVM model are reduced by 53.72% and 55.22%, respectively, compared to the Artificial Neural Network (ANN) approach reported in literature. Finally, the suggested model is capable of accurately predicting the electricity demand in China and has the potential to be applied to other energy-demand prediction applications.

Improved chaos grasshopper optimizer and its application to HRES techno-economic evaluation

Current political and economic trends are moving more and more toward the use of renewable and clean energy as a result of rising energy use and diminishing fossil fuel supplies. In this paper, an improved chaos-based grasshopper optimizer used for techno-economic evaluation in integrated green power systems is investigated. The integrated system consists of a fuel cell system, a wind farm, and solar energy. The integrated solar, wind, and hydrogen fuel cell architectures increase the effectiveness and electrical output of the system while needing less energy storage in structures that are unconnected from the grid. The grasshopper optimization technique and chaos theory have been combined to create the suggested chaotic grasshopper optimizer in this study. The performance, precision, and robustness of this optimization were then assessed, using four benchmark tasks. The ICGO model is utilized to assign suitable ratings to all system devices, thereby guaranteeing the attainment of optimal performance and efficiency. The Net Present Cost (NPC) analysis revealed that the ICGO algorithm attained the lowest minimum NPC value of 274.541E4 USD and the highest maximum NPC value of 311.94E4 USD. The average NPC value of the ICGO algorithm (289.176E4 USD) was found to be comparable to the other algorithms examined in the study. These findings indicate that the ICGO algorithm outperformed other optimization algorithms in minimizing the cost of the renewable energy system. The chaotic grasshopper optimizer can handle several targets, restrictions, and variables with ease, and the results demonstrate that it is substantially more efficient and precise than standard optimization techniques. It is also quite durable, with minimal performance degradation as compared to the benchmark solutions. This study demonstrates the effectiveness of the chaos grasshopper optimizer as an HRES technique.

Maximizing micro-grid energy output with modified chaos grasshopper algorithms

This study presents a Modified version of Chaos Grasshopper Algorithm (MCGA) as a solution to the Techno-Economic Energy Management Strategy (TEMS) problem in microgrids. Our main contribution is the optimization of parameters to minimize the overall daily electricity price in an integrated clean energy micro-grid, incorporating fuel cell, battery storage, and photovoltaic systems. Through comparative simulations with established methods (HOMER, GAMS, GWO, and MILPA), we demonstrate the superiority of our proposed strategy. The results reveal that MCGA surpasses these methods, yielding significantly improved optimal solutions for the overall daily electricity price. Notably, the MCGA approach exhibits high precision, flexibility, and adaptability to power prices and environmental constraints, leading to accurate and flexible solutions. Thus, our proposed approach offers a promising and effective solution for the TEMS problem in microgrids, with the potential to greatly enhance microgrid performance.

Early diagnosis of oral cancer using a hybrid arrangement of deep belief networkand combined group teaching algorithm

Oral cancer can occur in different parts of the mouth, including the lips, palate, gums, and inside the cheeks. If not treated in time, it can be life-threatening. Incidentally, using CAD-based diagnosis systems can be so helpful for early detection of this disease and curing it. In this study, a new deep learning-based methodology has been proposed for optimal oral cancer diagnosis from the images. In this method, after some preprocessing steps, a new deep belief network (DBN) has been proposed as the main part of the diagnosis system. The main contribution of the proposed DBN is its combination with a developed version of a metaheuristic technique, known as the Combined Group Teaching Optimization algorithm to provide an efficient system of diagnosis. The presented method is then implemented in the "Oral Cancer (Lips and Tongue) images dataset" and a comparison is done between the results and other methods, including ANN, Bayesian, CNN, GSO-NN, and End-to-End NN to show the efficacy of the techniques. The results showed that the DBN-CGTO method achieved a precision rate of 97.71%, sensitivity rate of 92.37%, the Matthews Correlation Coefficient of 94.65%, and 94.65% F1 score, which signifies its ability as the highest efficiency among the others to accurately classify positive samples while remaining the independent correct classification of negative samples.

Energy-saving optimization of the parallel chillers system based on a multi-strategy improved sparrow search algorithm

The energy usage of parallel chillers systems accounts for 25-40 % of the total energy cost of a building. In light of global warming concerns and the need for energy conservation, it is essential to distribute the load of the parallel chillers systems effectively to achieve energy savings in buildings. Accordingly, this study presents a multi-strategy improved sparrow search algorithm (MSSA) to address optimization of the optimal chillers loading (OCL) problem. The proposed algorithm augments the basic sparrow search algorithm (SSA) by introducing the Sine chaotic map, Levy flight method, and Cauchy variation to enhance diversity, avoid local optima, and increase global and local search capacities. We use 9 benchmark functions to check the performance of the proposed MSSA algorithm, and the results are better than the selected algorithms such as particle swarm algorithm (PSO), harris hawks optimization (HHO), artificial rabbit optimization (ARO) and sparrow search algorithm (SSA). In addition, MSSA is applied to two typical cases to demonstrate its performance to optimal chillers loading and the results indicate that the MSSA outperforms similar algorithms. This study validates that MSSA can provide a promising solution to resolve the OCL problem.