Cleaner Energy Systems最新文献

Diesel generators (DGs) are widely used in India by business and domestic consumers to provide resilience against unreliable power supplies, but have serious adverse environmental and health impacts. Low carbon alternatives to DGs are becoming more widely available and affordable, though technical and non-technical barriers remain to their widespread adoption. Targeted policy and financial interventions would help accelerate the deployment of these alternatives, where such interventions should be based on local needs. To this end, we use a Multi-Criteria Decision Analysis (MCDA) approach to identify appropriate technology alternatives for DGs in residential, industrial and agricultural applications in India. Within this study, the MCDA framework facilitates evidence-based decision-making through structured discussions with local stakeholders and for evaluating the most suitable option from a variety of available alternatives. Overall, our analysis concluded that a hybrid system combining solar PV and battery storage system are considered most suitable for residential, agricultural as well as industrial applications. This study sets out a pragmatic approach for decision makers considering how to minimise the adverse impacts of DGs while recognising the intricacies of requirements of different applications at a local level. Additionally, our approach showcases how co-creation of potential solutions, and ‘transparency’ in the process, can be accomplished in policy-making, which is critical for wider acceptance of interventions.

Forecasting wind power generation is crucial for ensuring grid security and the competitiveness of the power market. This paper presents an innovative approach that combines deep learning (DL) with Teaching-Learning-Based Optimization (TLBO) to predict wind power output accurately. Using a real dataset spanning diverse weather conditions and turbine specifications collected between January 2018 and March 2020, the study employs 18 features as inputs, including Ambient Temperature, Wind Direction, and Wind Speed, with real power output in kW as the target variable. Metaheuristic algorithms including Particle Swarm Optimization (PSO), Barnacles Mating Optimizer (BMO), Biogeography-Based Optimization (BBO), and Firefly Algorithm (FA) are comprehensively compared for model optimization. TLBO-DL consistently provides forecasts that closely align with actual wind power values across instances, substantiated by its low RMSE of 98.7601, indicating effective minimization of errors in wind power forecasting. Comparative analysis with other algorithms reveals that TLBO-DL outperforms PSO-DL (RMSE: 102.6627), BMO-DL (RMSE: 132.4839), BBO-DL (RMSE: 103.8517), and FA-DL (RMSE: 104.7282) in terms of overall forecasting accuracy. The variations in the performance of other algorithms across instances highlight the robustness and effectiveness of TLBO-DL in achieving accurate wind power forecasts. Overall, TLBO-DL emerges as a reliable and superior algorithm for wind power forecasting, consistently providing accurate forecasts across a range of instances.

The escalating global demand for energy and growing environmental concerns have stimulated the development of renewable energy-based power systems. In this context, solar power has gained significant attention, notably in the form of floating photovoltaic systems. These systems, installed on water bodies, not only boost efficiency but also reduce water evaporation from reservoirs. This research explores the power generation capabilities of floating photovoltaic systems in comparison to ground-mounted photovoltaic systems, considering a 250-watt monocrystalline photovoltaic panel. This study utilizes typical meteorological year data to comprehensively analyze four distinct locations in India. By using a single-diode model, this study finds that floating photovoltaic systems provide 6–7 % more power output than ground-mounted photovoltaic systems. This efficiency gain is because the floating photovoltaic panels operate at a lower temperature (4–6 °C) than their ground-mounted photovoltaic counterparts, positively influencing the overall performance. Furthermore, the degradation and soiling of ground-mounted photovoltaic and floating photovoltaic systems were also compared. The financial analysis reveals that ground-mounted photovoltaic systems typically have a lower levelized cost of electricity and shorter payback periods. Even though the financial indicators of floating photovoltaic systems are not favorable compared to ground-mounted photovoltaic systems, these results show how vital floating photovoltaic technology is for achieving the United Nations’ Sustainable Development Goals and how it could be used as an efficient technique to reduce land requirements for solar photovoltaic solutions in various geographical conditions.

Floating photovoltaic (FPV) power generation requires accurate short-term forecasting to optimize operational efficiency and enhance grid integration. This study investigates the application of machine learning models for predicting FPV power generation using data from the Universiti Malaysia Pahang Al-Sultan Abdullah (UMPSA) solar installation, which has a capacity of 157.20 kWp. Data were collected at 15-minute intervals from January 15 to January 21, 2024, encompassing nine input features such as ambient temperature, transient horizontal irradiation, daily horizontal irradiation, AC voltages, and AC currents for phases A, B, and C, with the total active power in kW as the target variable. The dataset was divided into a training set (first five days) and a testing set (remaining two days), and five machine learning models—Neural Networks (NN), Random Forest (RF), Extreme Learning Machine (ELM), Support Vector Regression (SVR), and Long Short-Term Memory (LSTM)—were employed. The results indicate that the Neural Networks model consistently outperforms the other machine learning algorithms in terms of predictive accuracy. These findings underscore the efficacy of machine learning techniques in forecasting FPV power generation, which has significant implications for enhancing the operational efficiency and grid integration of floating solar installations.

In rural areas lacking an electricity grid, cell phone operators use generators to power their facilities. At the same time, however, the local population is finding it difficult to use the cell phones and other electronic devices for which these operators are deploying their efforts. This situation, due to the problem of access to energy, hinders universal access to telecommunications. The present study aims to solve this problem using microgrid techniques. A microgrid consisting of photovoltaic panels, a genset and storage batteries has been designed to meet the needs of cell phone operators' sites in Bapure, a rural locality in Togo. The focus is on managing energy flows between the various sources of the microgrid, and between the needs of the cell phone operators' site and those of the local population. To resolve the lack of solar irradiation data at Bapure, hourly solar irradiation was predicted using the Adaptive Neuro Fuzzy Inference System (ANFIS) algorithm to obtain a realistic result. Optimization studies were then carried out using the Particle Swarm Optimization (PSO) algorithm to determine the optimum system configuration to ensure continuity of service at the operator's site. The simulation results show that the proposed system has a surplus of energy production at all times, which can be used to supply electricity to the population at a cost equal to 0.0185 USD, with a solar energy utilization rate of 98,95 % and a generator that only needs to operate at 0.15 % throughout the year. The results obtained indicate that a renewable energy system can provide a more efficient solution for electrifying the rural mobile operator's sites and the local population, and can improve the quality of service for the telecommunications industries.

Use of fossil fuel in industries causes Carbon emission, which is mostly responsible for global warming. Another aspect is that environment friendly energy production and sustainable development goal is highly dependent on the production of clean energy. According to the IEA solar energy has a huge potential and will contribute up to 16 % of the global electricity by 2050. Hence, prediction of solar energy production has a great deal of demand in renewable energy sector. This paper compares machine-learning algorithms to evaluate the impact of PV module back surface temperature (degC) on the generated power. Support Vector Machine for Regression (SMOreg), Multilayer Perceptron (ANN), Linear Regression, M5 Rules, k-Nearest-Neighbor (Ibk) and Random Forest methods are employed to test their performance in different ratio of training and testing data. The dataset comprises five independent parameters such as PV module back surface temperature (degC), Dry bulb temperature (degC), Relative humidity (%RH), Atmospheric pressure (mb), and Precipitation (mm). The dependent parameter is Maximum power of PV module (W). The correlation coefficient was determined by varying the percentage of training data from 60 % to 85 %. The numerical tests were done for two data sets, one dataset includes all the independent variables and another one excluded the PV module back surface temperature. Except for M5 Rules, other models exhibit consistent correlation coefficients with several of training data. All models demonstrate a dependency on the PV module back surface temperature, with Random Forest surpassing others in overall performance with a correlation coefficient of 0.9713 at 75 % of training set.

Modern agricultural practices encounter challenges related to operational efficiency and environmental effects. This prompts a demand for innovative solutions to foster sustainability in farming while emphasizing the limitations of conventional farming methods. To address these challenges in modern agriculture systems, this research proposes a comprehensive framework for smart farming. The proposed framework comprises of three technology integrations: 1) an efficient integration of renewable energy resources (RERs) with solar panels and battery energy storage systems (BESS), 2) an IoT-based environmental monitoring for precision irrigation, and 3) an android application-controlled precision robotic system for targeted chemical application. The proposed framework investigates a case study on Sharjah, United Arab Emirates (UAE) to explore and analyze optimal scenarios of multiple energy resources. Results demonstrate successful cross-prototype integration through the Blynk IoT platform providing users with a unified interface. Furthermore, the results provide a comprehensive analysis and investigation into the interactions between RERs and the grid across various combinations. The findings indicate the potential of this framework to revolutionize agriculture and thus offer a sustainable, efficient, and technologically advanced approach. It also represents the contribution of a complete solution to modern agricultural challenges presenting tangible results for a promising future in smart and sustainable farming practices.

Accurately estimating the State of Charge (SOC) in Electric Vehicles (EVs) is critical for battery management and operational efficiency. This paper presents a Deep Learning (DL) approach to address this challenge, utilizing Feed-Forward Neural Networks (FFNN) to estimate SOC in real-world EV scenarios. The research used data from 70 driving sessions with a BMW i3 EV. Each session recorded key factors like voltage, current, and temperature, providing inputs for the DL model. The recorded SOC values served as outputs. We divided the dataset into training, validation, and testing subsets to develop and evaluate the FFNN model. The results demonstrate that the FFNN model yields minimal errors and significantly improves SOC estimation accuracy. Our comparative analysis with other machine learning techniques shows that FFNN outperforms them, with an approximately 2.87 % lower root mean square error (RMSE) compared to the second-best method, Extreme Learning Machine (ELM). This work has significant implications for electric vehicle battery management, demonstrating that deep learning methods can enhance SOC estimation, thereby improving the efficiency and reliability of EV operations.

This paper proposes a new hybrid deep learning model to enhance the accuracy of forecasting very short-term wind power generation. The proposed model comprises a convolutional layer, a long-short-term memory (LSTM) unit, and fully connected neural network. Convolution layer can automatically learn complicated features from the raw input, whereas the LSTM layers can retain useful information through which gradient information may flow over extended periods. To obtain the best performance from the forecasting model, a random search optimization technique has been developed for tuning hyper-parameters of the model developed. The 5 min datasets from the White Rock wind farm, Australia are used to investigate the effectiveness of the proposed model as wind farms are participating in spot electricity market. To compare the effectiveness, the proposed model is compared with the existing models, such as convolution neural network (CNN), LSTM, gated recurrent unit (GRU), bidirectional LSTM (BiLSTM), artificial neural network (ANN), and support vector machine (SVM). The root-mean-square error (RMSE), mean absolute error (MAE), and Theil’s inequality coefficient (TIC) are used to analyze and compare the performances of the predictive models. Based on RMSE and MAE, the proposed model exhibits a higher accuracy of approximately 23.79% and 28.63% compared to other forecasting methods, respectively.

This research employs a comprehensive Strengths, Weaknesses, Opportunities, Threats (SWOT) analysis to investigate the advancement of photovoltaic (PV) energy in Northern Nigeria. The study delves into the intricacies of introducing PV systems within the context of economic challenges, including issues such as currency volatility and inflation, which amplify costs and impede capital investments. Environmental factors, such as dust and sandstorms, are identified as obstacles diminishing the efficiency of solar panels. Additionally, security concerns in remote areas elevate operational costs and influence investment decisions. This paper proposes effective mitigation strategies, encompassing widespread public awareness campaigns to augment market engagement, the establishment of mini-grid systems for enhanced energy distribution, customised on-the-job training programs to foster local expertise in PV technology, and the utilisation of micro-grid systems as experimental grounds for regulatory and policy testing. By synthesising these components, the study offers a comprehensive overview of the prerequisites essential for the successful proliferation of PV energy in Northern Nigeria. Emphasis is placed on the potential for solar energy to significantly contribute to the region's sustainable development and achieve energy independence when the identified strength, and opportunities are exploited. The key strength identified are the average Global horizontal irradiance (GHI) of 5.436 kWh/m², Direct Normal Irradiance (DNI) of 1534–1680 kWh/m², Levelised Cost of Electricity (LCoE) of $ 0.1, and an opportunity to fully utilise the over $ 7.88 million grant authorised by the African Development Bank (AfDB) from the Sustainable Energy Fund for Africa.