Search results

Solar power forecasting will have a significant impact on the future of large-scale renewable energy plants. Predicting photovoltaic power generation depends heavily on climate conditions, which fluctuate over time. In this research, we propose a hybrid model that combines machine-learning methods with Theta statistical method for more accurate prediction of future solar power generation from renewable energy plants. The machine learning models include long short-term memory (LSTM), gate recurrent unit (GRU), AutoEncoder LSTM (Auto-LSTM) and a newly proposed Auto-GRU. To enhance the accuracy of the proposed Machine learning and Statistical Hybrid Model (MLSHM), we employ two diversity techniques, i.e. structural diversity and data diversity. To combine the prediction of the ensemble members in the proposed MLSHM, we exploit four combining methods: simple averaging approach, weighted averaging using linear approach and using non-linear approach, and combination through variance using inverse approach. The proposed MLSHM scheme was validated on two real-time series datasets, that sre Shagaya in Kuwait and Cocoa in the USA. The experiments show that the proposed MLSHM, using all the combination methods, achieved higher accuracy compared to the prediction of the traditional individual models. Results demonstrate that a hybrid model combining machine-learning methods with statistical method outperformed a hybrid model that only combines machine-learning models without statistical method.

The use of renewable energy has become necessary because of the harmful effects of current energy sources on the environment, limited availability and financial crisis. Transparent solar panels have emerged as a promising technology for integrating renewable energy generation into building structures. Therefore, this paper aims to explore the feasibility of transparent solar panels for high-rise building façades in Sri Lanka.

The research apprehended a qualitative approach, including two expert interview rounds adhering to the Delphi technique with 17 and 15 experts each per round. Manual content analysis was incorporated to analyse the collected data.

Regarding operation and maintenance, the study emphasizes the importance of regular inspection, cleaning and repair of transparent solar panels to ensure optimal performance and longevity. These activities contribute to maximizing energy generation and maintaining the aesthetic appeal of the building. The benefits of implementing transparent solar panels on building façades are manifold. They include renewable energy generation, reduced greenhouse gas emissions, improved energy efficiency and enhanced architectural aesthetics. Furthermore, the research findings underscore the potential of transparent solar panels to contribute to Sri Lanka’s sustainable development goals and address the country’s increasing energy demand. However, the study also identifies challenges that need to be addressed for successful implementation.

This study contributes to understanding the feasibility of transparent solar panels for high-rise building façades in Sri Lanka. The research findings offer valuable insights into the operation and maintenance aspects, benefits, challenges and strategies for implementing transparent solar panels effectively. This knowledge can guide policymakers, architects and developers in making informed decisions regarding the integration of transparent solar panels, thereby promoting sustainable and energy-efficient building practices in Sri Lanka.

Blockchain for energy trading is a trending research area in the current context. However, a noticeable gap exists in the review articles focussing on solar energy trading with blockchain technology. Thus, this study aims to systematically examine and synthesise the existing research on implementing blockchain technology in sustainable solar energy trading.

The study pursued a systematic literature review to achieve its aim. The data extraction process focussed on the Scopus and Web of Science (WoS) databases, yielding an initial set of 129 articles. Subsequent screening and removal of duplicates led to 87 articles for bibliometric analysis, utilising VOSviewer software to discern evolutionary progress in the field. Following the establishment of inclusion and exclusion criteria, a manual content analysis was conducted on a subset of 19 articles.

The results indicated a rising interest in publications on solar energy trading with blockchain technology. Some studies are exploring the integration of new technologies like machine learning and artificial intelligence in this domain. However, challenges and limitations were identified, such as the absence of real-world solar energy trading projects.

This study offers a distinctive approach by integrating bibliometric and manual content analyses, a methodology seldom explored. It provides valuable recommendations for academia and industry, influencing future research and industry practices. Insights include integrating blockchain into solar energy trading and addressing knowledge gaps. These findings advance societal goals, such as transitioning to renewable energy sources (RES) and mitigating carbon emissions, fostering a sustainable future.

This study aims to study the thermal identification issue by harvesting both solar energy and atmospheric thermal updraft for a solar-powered unmanned aerial vehicle (SUAV) and its electric energy performance under continuous soaring conditions.

The authors develop a specific dynamic model for SUAVs in both soaring and cruise modes. The support vector machine regression (SVMR) is adopted to estimate the thermal position, and it is combined with feedback control to implement the SUAV soaring in the updraft. Then, the optimal path model is built based on the graph theory considering the existence of several thermals distributed in the environment. The procedure is proposed to estimate the electricity cost of SUAV during flight as well as soaring, and making use of dynamic programming to maximize electric energy.

The simulation results present the integrated control method could allow SUAV to soar with the updraft. In addition, the proposed approach allows the SUAV to fly to the destination using distributed thermals while reducing the electric energy use.

Two simplified dynamic models are constructed for simulation considering there are different flight mode. Besides, the data-driven-based SVMR method is proposed to support SUAV soaring. Furthermore, instead of using length, the energy cost coefficient in optimization problem is set as electric power, which is more suitable for SUAV because its advantage is to transfer the three-dimensional path planning problem into the two-dimensional.

This paper aims to Solar photovoltaic (PV) power can significantly impact the power system because of its intermittent nature. Hence, an accurate solar PV power forecasting model is required for appropriate power system planning.

In this paper, a long short-term memory (LSTM)-based double deep Q-learning (DDQL) neural network (NN) is proposed for forecasting solar PV power indirectly over the long-term horizon. The past solar irradiance, temperature and wind speed are used for forecasting the solar PV power for a place using the proposed forecasting model.

The LSTM-based DDQL NN reduces over- and underestimation and avoids gradient vanishing. Thus, the proposed model improves the forecasting accuracy of solar PV power using deep learning techniques (DLTs). In addition, the proposed model requires less training time and forecasts solar PV power with improved stability.

The proposed model is trained and validated for several places with different climatic patterns and seasons. The proposed model is also tested for a place with a temperate climatic pattern by constructing an experimental solar PV system. The training, validation and testing results have confirmed the practicality of the proposed solar PV power forecasting model using LSTM-based DDQL NN.

Research on solar energy adoption offers a multidimensional scope and warrants exploration from multiple perspectives, including political, economic, management, behavioral, policy and innovation aspects. The aim of this paper is to comprehensively consolidate major research findings on the premise of solar energy adoption and to disclose gaps in the existing literature.

A bibliometric analysis of the vast literature is conducted on 1,009 meticulously shortlisted articles following the semi-systematic literature review methodology. A text analytics tool named BibExcel is used for synthesizing the literature, and the results are visualized using Gephi, Pajek and a spreadsheet application.

This paper reports the evolution of research in the selected domain. It is noted that research in this domain was primarily concentrated on four broad themes, namely, peer effects and spatial patterns, public perceptions, policies and economics and technological evolution. The analysis further reveals the merging of two of these themes as a result of transdisciplinary research and also projects future research trends emphasizing political interventions in technological evolution and diffusion.

Research trends and future research scope are identified and discussed in detail. The information revealed from the analysis, along with the research implications, will assist policymakers in noting the flaws in the current doctrines and practices, entrepreneurs in understanding potential enablers and barriers influencing solar energy adoption and budding scholars in comprehending the current research status and framing promising research objectives to close the existing research gaps.

This study aims to conduct the domain mapping of consumer behaviour research in the context of solar energy. The study can help in understanding the intellectual structure, evolution of keywords and key research producers (at the author, institutional and source level) related to the domain of solar energy consumer research.

This study uses R-studios’ bibliometrix package for analysing the bibliographical data collected from the Scopus database. Analysis has been conducted at the descriptive level (summary, author, institution and source) and analytical level (co-citation analysis, co-occurrence analysis, thematic maps and historiography).

This study finds out the most relevant authors, institutions and sources using criteria such as production, citations and H-index. Relevant research clusters have been identified using the clustering of authors, co-citations and keywords. Thematic mapping has identified the basic and motor themes. Historical citation analysis shows the direct linkage of previous studies. Overall, this study reports the most relevant bibliometric indicators in the domain of solar energy consumer research.

Identified patterns can help policymakers, business experts, social marketers and energy conservation organisations to study consumer behaviour.

Thiis bibliometric study can effectively assess sustainable development goals and suggest improved action plans.

This study examined bibliometric analysis in solar energy products (SEPs), recognised varied domains of research work on consumers’ intention to purchase solar household products and mapped them into six groups. This study provides an overview of 40 years of research on consumer behaviour towards SEPs and discusses its findings to identify the research gap.

The present study aims to provide a roadmap for meeting the carbon-free, green energy production target within the stipulated period while also considering climate targets through a sustainable auctioning scheme.

The research outlines the opportunity to design auctions based on qualitative research, the impact of auctions on energy costs and thus the feasibility of suggested auctioning schemes based on country-specific empirical evidence and benefits.

The conclusions show that this may result in various advantages for emerging economies relating to technology-neutral site-specific auctions if designed according to state-specific socio-economic conditions.

The planned addition to the state-of-the-art in the renewable energy (RE) field of this paper is that it intends to bridge the gap between theory and practice. The analysis has concepts for research, practice and/or community. Thus, it can serve as a primary source of literature reference for those willing to learn more about the aspects of cost related to RE.

The purpose of the paper is to assess the systemic risk in the new energy stock markets of China.

This paper first uses the VaR method to study individual stock market risks. It then introduces the DCC model to capture the dynamic conditional correlation among the new energy stock markets.

The paper shows a generally upward trend of the stock market risk over time in the recent decade. Among all the markets considered, the solar power market demonstrates the highest risk, closely followed by the wind power market, while the hydropower market exhibits the lowest risk. Furthermore, the average dynamic conditional correlations among the new energy markets stay high during the period under investigation though daily correlations vary and significantly declined in 2020.

To the best of the authors’ knowledge, this paper is the first of its kind to study the systemic risk within the new energy stock market context. In addition, it not only investigates individual new energy stock market risks but also examines the dynamic linkages among those markets, thus providing comprehensive and unprecedented evidence of systemic risk in China new energy markets, which have useful implications for both regulators and investors.

This study aims to examine the impact of socioeconomic factors on electricity usage and assess the feasibility of implementing a mini-grid system in Kasangazi, Malawi. The primary aim is to understand the community’s current and potential utilisation of electrical equipment.

A mixed-methods approach was used to collect quantitative and qualitative data. Information was gathered through structured questionnaires, and energy audits were conducted among 87 randomly selected households from 28 Kasangazi communities. Data analysis relied on descriptive statistics using IBM SPSS version 28.

The study indicates that every household in Kasangazi uses non-renewable energy sources: 60 households use disposable batteries for lighting, 20 for radios and all use firewood, freely sourced from local forests, for cooking and heating water. The study shows that firewood is the community’s preferred energy source, illustrating the challenges faced in the fight against deforestation. Most household income comes from farming, with smaller contributions from businesses, employment and family remittances. Access to higher education is scarce, with only one out of 349 family members receiving tertiary education. Despite the constraints of low education levels and income, there is a demand for larger electrical appliances such as stoves and refrigerators. This underscores the need for mini-grid solutions, even in less technologically advanced, agriculture-dependent communities.

This study underscores that in Sub-Saharan Africa, factors like household size, income and education levels do not significantly influence the electricity demand but should be taken as part of the fundamental human rights. Rural populations express a desire for electricity due to the convenience it offers, particularly for appliances like refrigerators and stoves. Mini-grids emerge as a viable alternative in regions where grid electricity provision is challenging. It is concluded from this paper that the issue of using renewable energy should not only be taken for environmental preservation but also to promote energy access, augmenting efforts in supplying electricity to the remotest parts of the country.