The shift from fossil fuels to renewable energy (RE) is a key component in achieving global sustainability and dealing with climate change. Natural resources, such as sunlight, air, water, and biomass, have tremendous potential to create clean energy; however, exploiting these resources in an efficient, stable, and large-scale integration manner is difficult due to their variable and distributed nature. Artificial intelligence (AI) approaches that mimic human learning and decision-making have recently become viable approaches to solve renewable energy problems. This study mainly examines the current landscape of AI applications across solar, wind, hydro, geothermal, ocean, hydrogen, bioenergy, and hybrid energy systems. Findings indicate that AI enhances renewable energy forecasting, improves power system frequency analysis and stability assessments, and optimizes dispatch and distribution networks. Beyond technical optimization, AI also contributes to broader sustainability goals, including energy efficiency improvements, intelligent smart grid management, and enabling mechanisms such as carbon trading and circular economy practices to reduce exposure to climate extremes. Drawing on evidence from a range of renewable energy areas, this study highlights the importance of artificial intelligence (AI) in bridging the link between technology innovation and sustainable energy management. This paper discusses potential future research avenues, such as building sophisticated AI designs, energy-efficient chips, and data communication networks. Ultimately, the synergy between AI and renewable energy systems represents not only a technological advancement but also a transformative pathway toward a resilient, low-carbon future.

Sunlight, air, and other natural resources are invaluable gifts that must be utilized responsibly to enhance human welfare while preserving the environment and protecting all forms of life. The reliance on fossil fuels has increasingly threatened these resources, which has made the exploration of sunlight and air as major renewable energy sources a critical focus of research and development. Artificial intelligence (AI) originally developed to mimic human thought and decision-making processes that have become a transformative force in renewable energy systems by optimizing energy generation, management, and distribution for greater efficiency and sustainability. This paper shows the advances of AI as it applied and continues to research in wind, solar, geothermal, hydro, ocean, bioenergy, hydrogen, and hybrid energy systems during the last decades. A bibliometric analysis, conducted via VOSviewer and Bibliometrix, of the literature was conducted systematically by reviewing relevant journal articles between 2000 and 2025. AI and energy provide a recent lit of energy trends in research, collaboration maps, future use applications, and newly explored domains. Different studies shows AI technologies measurability improve several aspects of renewable energy for the purpose of integrating operations into the grid for users, specifically forecasting, improving system stability and frequency, and obtaining a means to assess transient stability. This research offers meaningful recommendations to facilitate the development of AI, accelerate the application and promotion of AI technology in the field of renewable energy, and build efficient models, processors, and data centers through shifting to renewable energy.

This bibliometric analysis examines the evolution and structural dynamics of scientific knowledge on the application of digital technologies and digital twins in the energy systems of horticultural greenhouses. Within the global context of digital transformation and the urgent need to optimize energy use in protected agriculture, the development of intelligent, efficient, and sustainable greenhouse systems has become a strategic challenge. Nevertheless, the integration of digital twins into greenhouse energy management remains a fragmented and emerging research area. To characterize this field, a comprehensive search was conducted in Scopus (2016–2025) using the following query: TITLE-ABS-KEY (("digital twin" OR "digital design") AND "greenhouse" AND ("energy system" OR "solar energy")) AND NOT ("greenhouse gas*"). The retrieved records were analyzed using Bibliometrix (R) and VOSviewer, enabling the identification of keyword co-occurrence networks, temporal production trends, and international collaboration patterns. The final dataset comprised 19 documents published in 14 sources, authored by 154 researchers none of whom were single authors with an annual growth rate of 24.1% and an international co-authorship rate of 10.5%. The dominant subject areas were Computer Science (15 documents) and Engineering (9), followed by Mathematics and Agricultural and Biological Sciences. The average number of citations per article was 12.2, and the mean document age was 2.37 years, underscoring the novelty and rapid consolidation of the field. The most frequent keywords were energy management, greenhouses, embedded systems, and artificial intelligence, reflecting the convergence between automation, digital design, and energy efficiency. The results suggest that the use of digital twins and intelligent control in greenhouses is primarily directed toward thermal simulation, energy optimization, and solar system integration. The analysis highlights the leadership of Wageningen University & Research and points to significant opportunities for advancing this research within low-cost and tropical agricultural contexts, where digital energy management could enhance both productivity and sustainability.

Introduction:
Optimizing solar energy systems is essential for improving efficiency and reliability in the shift toward renewable energy. Artificial Intelligence (AI) plays a key role by enabling precise forecasting, adaptive control, and real-time optimization of photovoltaic (PV) technologies. This study examines the use of AI methods, such as neural networks, hybrid deep learning, and machine learning, to enhance solar irradiance prediction, panel orientation, and maximum power point tracking (MPPT).

Methods:
Multiple AI models were examined, including Artificial Neural Networks (ANNs), Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNNs), and hybrid CNN-LSTM frameworks. These models utilized datasets containing meteorological variables such as solar irradiance, temperature, humidity, and historical PV output. Optimization tasks incorporated Random Forest Regressors with Grid Search, ANFIS for MPPT, and reinforcement learning for tilt adjustment.

Results and Discussion:

The GRU model achieved a 23.3% lower RMSE compared to standard backpropagation neural networks and 11.9% improvement over traditional RNNs. A hybrid CNN-LSTM model demonstrated superior performance, reaching an RMSE of 0.0187 and an R² of 0.9915. In large-scale deployments like the Benban Solar Park, the model yielded a MAPE of 2.04% and R² of 0.99. For MPPT enhancement, AI models using ANFIS improved thermal and electrical efficiency by up to 12.3% under dynamic irradiance conditions. AI-based orientation control using reinforcement learning improved annual energy yield by 10–15%, while supervised ML methods increased energy output by an average of 3.98% over fixed-tilt systems.

Conclusion:
The integration of AI in solar energy systems yields significant quantitative benefits. Forecasting accuracy improves with hybrid models achieving <2% MAPE and >0.99 R², while orientation and MPPT optimizations result in 10–15% higher efficiency and up to 30% energy savings. These advancements highlight AI’s role in transforming solar technologies from static, reactive systems into dynamic, intelligent energy infrastructures.

Rapid urbanization and unplanned land development have transformed Dhaka into one of the most densely built metropolitan areas in South Asia, leading to increased surface heat accumulation and energy consumption within the built environment. Numerous studies have reported a progressive rise in Dhaka’s Land Surface Temperature (LST), ranging between 19 °C and 31 °C during the pre-monsoon months, accompanied by a strong negative correlation between the Normalized Difference Vegetation Index (NDVI) and LST, and a positive correlation between the Normalized Difference Built-Up Index (NDBI) and LST. This indicates that decreasing vegetation and expanding impervious surfaces are major contributors to the city’s thermal inefficiency. The present study aims to assess energy efficiency patterns in the urban landscape of Dhaka by integrating remote sensing, GIS, and data-driven modeling techniques. Landsat 9 imagery and VIIRS nighttime light data were processed to derive NDVI, NDBI, and LST layers, while building footprints and road networks were extracted from OpenStreetMap to represent urban form. A supervised Random Forest model was employed to estimate the relative importance (weights) of these variables in influencing surface temperature distribution. Spatial overlay analysis and correlation assessment revealed that areas with high built-up intensity and low vegetation cover exhibit significantly higher surface temperatures, implying lower energy efficiency. In contrast, green and peri-urban zones demonstrate lower LST values, reflecting enhanced cooling potential. The resulting energy-efficiency map delineates critical urban heat zones that require mitigation through landscape-based interventions. This research underscores the importance of urban greening, reflective roofing, and compact yet sustainable vertical development as strategies to reduce thermal stress and improve energy performance. This study contributes to evidence-based urban planning approaches that can guide policymakers in designing more climate-resilient and energy-efficient cities in Bangladesh.

The combination of solar and biomass energy represents a sustainable alternative for thermal generation in rural areas, particularly in agro-industrial processes such as crop drying and food preservation. Hybrid configurations enable continuous operation under variable solar radiation, improving thermal efficiency and reducing fossil fuel dependence. However, the literature on this topic remains limited and fragmented. Therefore, a technical and bibliometric review was conducted to identify research trends, key actors, and knowledge gaps in hybrid solar–biomass systems applied to agricultural and food sectors. The Scopus database was used for the 2005–2025 period, applying the query TITLE-ABS-KEY(("hybrid" W/2 (solar AND biomass)) AND (dryer OR drying OR "process heat") AND (agricultur OR food OR agroindustrial))*. A total of 22 documents published in 21 sources were analyzed, including 15 journal articles, 3 reviews, and 4 conference papers. Results indicate an annual growth rate of 3.5%, an average of 7.18 co-authors per document, and an international collaboration rate of 27.3%, reflecting a small but increasingly connected research community. India leads scientific production (11 papers), followed by Nigeria, Malaysia, and Spain, with major contributions from the Indian Institute of Technology Delhi and the Federal University of Agriculture. Thematic mapping revealed four clusters: (i) biomass–solar drying and food preservation as motor themes; (ii) energy efficiency and food processing as niche technologies; (iii) hybrid systems, renewable energies, and cost effectiveness as basic developing topics; and (iv) temperature, heat transfer, and desiccation as emerging research areas reactivated by advances in modeling, CFD simulation, and intelligent control. Overall, the results highlight a growing focus on the design and optimization of hybrid solar–biomass systems as key enablers of rural energy transition and sustainable agro-industrial development.

The modernization of cacao fermentation is essential to improve quality consistency, energy efficiency, and process traceability within tropical agro-industries. Traditional fermenters remain highly empirical, lacking thermal control and data-driven optimization. This study presents a technical–bibliometric review of recent research on cacao fermentation systems integrating design, modeling, and intelligent control approaches. A Scopus search covering 2016–2025 retrieved 20 documents from 13 sources, authored by 93 researchers with an international co-authorship rate of 30 % and an annual growth of 8 %. Data were analyzed through bibliometric mapping using VOSviewer and Biblioshiny, focusing on keyword co-occurrence and thematic evolution. Colombia emerged as the leading contributor, followed by Brazil, Canada, China, Côte d’Ivoire, and Ecuador, reflecting the strategic importance of cacao in tropical research agendas. The keyword network revealed three main clusters: (1) a bioprocess–thermal control cluster (red) linking fermentation process, thermal variables, and cocoa beans, oriented to modeling temperature, pH, and microbial kinetics; (2) a machine-learning and predictive modeling cluster (green) including random forests, adaptive boosting, and discriminant analysis, emphasizing algorithmic prediction of fermentation quality; and (3) an IoT and smart devices cluster (blue) focused on process monitoring, sensor networks, and energy control. Despite the growing integration of AI and digital tools, the analysis exposed notable gaps: limited use of hybrid energy systems, scarce CFD-based thermal modeling, and few pilot-scale intelligent fermenter designs for real tropical conditions. Future research should couple renewable-energy management, real-time data analytics, and AI-driven control architectures to develop scalable, sustainable fermentation technologies. These findings position cacao fermentation as an emerging interdisciplinary domain bridging food bioprocess engineering, smart energy design, and artificial intelligence for sustainable agro-industrial transformation.

Modern smart buildings and urban infrastructures increasingly depend on artificial intelligence to monitor, predict, and optimize energy performance. Deploying such intelligent systems across distributed devices and facilities requires approaches that are not only accurate and adaptive but also energy-efficient and privacy-preserving. Traditional centralized machine learning models are often less effective in this context, facing significant data privacy constraints and communication bottlenecks. Federated Learning (FL) provides a decentralized framework that allows multiple local agents, including smart meters, HVAC controllers, and building management nodes, to collaboratively train models without transmitting sensitive data to a central server. This study explores how FL can support lightweight decision and prediction models, including compact language or foundation models, designed for real-time energy monitoring and management. These models can operate efficiently on edge devices with limited computational power, a crucial requirement for widespread deployment. By emphasizing parameter-efficient and resource-aware learning, FL can reduce computational demands and communication costs, making continuous learning feasible within energy-constrained environments. This enables enhanced capabilities such as predictive maintenance scheduling, real-time load balancing, and personalized occupant comfort profiles. The integration of such distributed AI systems lays the foundation for intelligent, adaptive, and low-energy decision-support frameworks in sustainable buildings and urban infrastructures, advancing the vision of resilient and self-optimizing smart environments.

The rapid growth of urban populations has intensified the global demand for clean and renewable energy sources. Among these, solar power has emerged as a vital element in sustainable urban planning. Integrating solar photovoltaic (PV) systems into city energy infrastructures represents a key step toward achieving sustainable urban transitions. Nevertheless, fluctuating weather conditions create significant challenges for optimizing solar energy generation and its seamless integration into urban energy networks. This study introduces an artificial intelligence-driven predictive modeling framework designed to support the development of sustainable urban solar energy systems. The proposed approach utilizes advanced machine learning algorithms to predict the degradation of solar energy systems by incorporating meteorological variables and urban air quality indicators within the densely populated capital of Bangladesh. The model is trained and validated using historical weather data alongside real-time degradation records from solar installations in Dhaka, Bangladesh. The results indicate that the proposed predictive model notably improves forecasting accuracy. This research highlights the potential of machine learning as a robust and precise tool for modeling complex urban solar energy dynamics. Furthermore, the developed framework offers practical value to urban planners, utility managers, and system operators by enhancing operational performance, supporting grid integration, and improving the financial sustainability of solar projects. The insights gained contribute to advancing smarter, more resilient, and sustainable urban energy infrastructures.

The integration of renewable energy sources, like solar power, is crucial for achieving sustainable computing infrastructure, especially in off-grid systems. The variable nature of solar energy often leads to surplus generation, particularly at midday, that cannot be efficiently stored or consumed. To address this challenge, we propose an AI-enabled demand response system that dynamically scales server utilization based on real-time solar availability. The system is also adaptable for integration with grid-connected networks for broader energy optimization. Leveraging recent advances in Artificial Intelligence (AI) and drawing from the peer-reviewed literature, reputable conference proceedings, and industry white papers, we evaluated an AI-driven framework for server scaling and resource allocation in Large Language Model (LLM) training. Real-time data on energy production and consumption, as well as battery storage, were collected from various sources, including Battery Management Systems (BMSs), Maximum Power Point Tracking (MPPT) units, and smart inverters. Supplementary solar forecasts were likewise integrated from third-party services (e.g., Solcast). These data were fed into a Tools AI Agent Node, and implemented within n8n, a low-code workflow automation platform, using the Ollama chat model gpt-oss:20b. This agent evaluates whether surplus energy would otherwise be unutilized for computational workloads and, if so, decides to use our proposed tool, activating or shutting-down the selected RAM-only provisioned servers optimized for LLM execution, effectively repurposing otherwise-wasted energy. Preliminary evaluations demonstrated high operational reliability (99%), near-real-time responsiveness (<1s latency), and accurate surplus energy detection. Workloads were successfully executed aligned with solar availability, validating the operational stability of the system. This research demonstrates that AI-driven demand response can repurpose surplus solar output into a valuable resource for sustainable computing, contributing to energy-efficient data centers and a broader transition toward renewable-powered infrastructures.