This study presents a mathematics-based simulation model for designing, analyzing, and optimizing offshore green hydrogen stations powered by solar photovoltaic systems, applicable to any location worldwide. Developed in Python, the model integrates environmental, physical, and technological parameters to simulate and forecast hydrogen production via water electrolysis using ALK or PEM electrolyzers, combined with an adiabatic compressor that enhances energy storage and facilitates integration into smart grids.

The five-phase modular methodology includes timeframe definition; estimation of solar electricity generation based on solar trajectory and the geographic orientation of photovoltaic panels; performance modeling of electrolyzers and compressors; and the integration of all components into a cohesive system. A case study demonstrates the model’s real-world applicability.

Results based on 2025 efficiency projections for ALK and PEM technologies show a substantial increase in solar energy capture in offshore environments, due to reduced atmospheric pollution and sea-surface reflectivity. Reflectivity is modeled as a function of sea surface flatness. A 20% increase in electrolyzer efficiency improves production by 32.28%, and the same efficiency gain in the compressor adds 0.81%. These impacts directly correlate with proportional reductions in the photovoltaic panel surface area required—greater electricity generation capacity translates into smaller infrastructure needs.

The model enables quantitative evaluation of trade-offs among solar irradiance, component performance, and system design. It supports cost reduction through optimized sizing and improved integration. This approach contributes to lowering the Levelized Cost of Electricity (LCOE) and promoting the viability of marine-based green hydrogen deployment.

Rural regions of Uzbekistan experience continuing issues of energy access because of poor grid networks and variable renewable sources. The solution is small-scale wind turbines and energy storage. But the wind speeds and load demand are variable and thus this solution needs intelligent control systems to perform its best.

This paper is an attempt to design an Adaptive Neuro-Fuzzy Inference System (ANFIS) controller to control a small wind power system with a battery storage unit. The controller will be intelligent to control the flow of power between the wind turbine, battery, and local loads. A model of MATLAB/Simulink is created to simulate the reaction of the system to various wind and load conditions.

The results of the simulation prove that the ANFIS controller is better at stabilizing the voltage, reducing the power fluctuations, and optimizing the battery charge-discharge cycle compared to other conventional PI and the standalone fuzzy controller. Environmental variability is effectively responded to by the system, making it more reliable and energy-efficient.

ANFIS control and wind–battery microgrid integration provides a feasible and expandable off-grid electrification solution to remote areas. This strategy promotes the renewable energy ambitions of Uzbekistan and offers an example of smart microgrid implementation in other resource-limited rural areas. The next steps would be on practical applications and hardware verification.

China's urgent need to retrofit 350 million residents' energy-inefficient housing faces critical coordination failures among diverse stakeholders. This paper investigates how digital platform principles, particularly those from Chinese super-apps, could enable community-driven sustainable housing transformations. Through systematic analysis of 27 digital platforms (15 Western, 12 Chinese) for housing services, we identify fundamental architectural divergences affecting retrofit coordination capabilities. Western platforms exhibit "fragmentation by design," prioritizing market competition over coordination efficiency, while Chinese super-apps demonstrate ecosystem integration but lack retrofit-specific mechanisms. Our analysis reveals five critical capability gaps: collective decision infrastructure, multi-stakeholder coordination, integrated compliance workflows, community benefit optimization, and trust beyond transactions. Based on these findings, we develop a conceptual framework comprising five interconnected modules operating above a unified data foundation: collective optimization (prioritizing community benefits over individual preferences), community coordination (structured decision-making), marketplace integration (trusted service provider connections), financial coordination (integrating diverse funding sources), and regulatory streamlining (proactive compliance support). The framework fundamentally inverts conventional platform logic from individual preference aggregation to collective benefit optimization, with algorithms weighting community outcomes at 80% versus individual preferences at 20%. This reconceptualization demonstrates how platform-mediated collective action becomes possible when technology design aligns with community social practices rather than imposing market logics, offering a pathway to accelerate China's sustainable housing transformation.

Small-scale businesses face persistent challenges in managing energy efficiently due to limited resources, rising operational costs, and the absence of real-time monitoring systems. These constraints often lead to unnecessary energy wastage, reduced profitability, and a higher environmental footprint. Artificial Intelligence (AI) and the Internet of Things (IoT) present affordable, practical solutions that can transform the way small enterprises monitor, analyze, and optimize their energy usage.

Problem Statement
• High operational costs due to energy wastage.
• Lack of affordable and user-friendly energy monitoring tools.
• Need for scalable, low-cost AI solutions tailored for SMEs.

Proposed Solution
The proposed system integrates IoT sensors, smart meters, and cloud-based AI analytics to continuously monitor energy consumption. Machine learning models are applied to both historical and live data to forecast consumption patterns, detect anomalies, and recommend operational adjustments for improved efficiency.

Methodology
1.Install IoT-enabled smart meters.
2.Collect and transmit energy usage data to the cloud.
3.Apply machine learning models for forecasting and anomaly detection.
4.Generate actionable recommendations via an intuitive user dashboard.

Expected Benefits
• 15–25% reduction in energy costs.
• Lower carbon emissions.
• Improved operational efficiency.
• Scalable for SMEs in both urban and rural settings.

Future Work
Future developments include integration with renewable energy sources such as solar and wind power, and expanding the system to manage energy at a community or regional level.

Conclusion
AI-enabled systems can make energy management accessible, cost-effective, and sustainable, empowering small businesses to contribute meaningfully to global climate change mitigation efforts.

It is important for Bangladesh to balance energy development and sustainable growth in light of the country’s need for net-zero emissions. In this study, we develop three hybrid models to forecast the growth of renewable energy and the level of CO2 emissions for target dates set by the country. This paper presents a prediction analysis of CO2 emissions and the renewable energy industry in terms of the necessary rate of mandated emissions based in probabilistic deep learning. We designed the first model, which combines Long Short-Term Memory (LSTM) with autoregressive integrated moving average (ARIMA) and XGBoost. The second hybrid model consists of deep neural networks (DNNs) and Gaussian process regression (GPR). The third model is a blend of random forest and LSTM with a Bayesian neural network (BNN). By exhaustive analysis of the results, we examine the values obtained from the generation of predictive models for the renewable energy sector along with progressive enhancement of energy production and decarbonization. The results demonstrate the promise of the hybrid methodologies for the improvement of energy efficiency and energy policy systems with the objective o net-zero in Bangladesh. The outcome of the prediction method reveals that hybrid model of deep neural networks (DNNs) with a Bayesian neural network (BNN) achieve the best accuracy with the highest performance parameters.

The deployment of Renewable Energy Communities (RECs) is a cornerstone of the transition toward low-carbon and resilient urban systems. Their effective planning requires decision-making tools capable of integrating environmental, social, and technical criteria within dynamic territorial and regulatory contexts. Traditional multi-criteria approaches (e.g., the Analytic Hierarchy Process) provide a solid methodological basis for site suitability analysis but are often limited by expert subjectivity, static weighting, and low adaptability to evolving conditions.

Artificial Intelligence (AI)-based tools could help at multiple stages of the decision-making process, from the automatic weighting of criteria to the optimization of alternative planning scenarios. Machine learning and deep learning algorithms can learn from historical data, such as energy performance records, socioeconomic indicators, or patterns of social acceptance, to calculate dynamic weights, thereby reducing dependence on subjective, judgment-based assessments. Adaptive multi-criteria systems can then update these weights in real time in response to regulatory changes, incentive availability, or variations in energy consumption. Natural Language Processing can further expand the decision base by extracting and classifying relevant information from complex sources, such as legislative documents, urban plans, and environmental impact reports, ensuring that planning processes remain aligned with current policies and sustainability goals. In parallel, optimization through AI metaheuristics, including genetic algorithms, swarm intelligence, or reinforcement learning, can identify optimal combinations of sites and configurations for RECs while balancing multiple constraints (e.g., landscape, historical, environmental, etc.). When integrated with Geographic Information Systems and remote sensing, these AI capabilities allow for continuously updated spatial analyses and transparent, explainable decision models.

The use of AI in energy planning offers a promising pathway to more adaptive, data-driven, and participatory frameworks for REC development, aligning local energy strategies with the broader objectives of circularity, sustainability, and resilience in the built environment.

Accurate forecasting of photovoltaic (PV) power is essential for the reliable operation of renewable energy systems. Conventional approaches fall into two extremes: physics-based models that provide theoretical accuracy but require extensive parameters, and data-driven machine learning models that can learn from historical trends but often behave as black boxes with limited interpretability. While machine learning has achieved strong short-term performance, its lack of physical grounding restricts generalization to unseen weather or operating conditions. This study introduces a physics-inspired machine learning framework for predicting PV power output under varying irradiance and temperature conditions. A dataset of PV system performance, meteorological variables, and solar irradiance is used to train a neural network. Unlike conventional models, the proposed framework integrates physics-informed regularization into the training process. Constraints derived from PV physics including the Shockley–Queisser efficiency limit, temperature dependence of bandgap energy, and diode-based current–voltage relations are embedded into the model’s loss function. These constraints ensure that predictions remain consistent with established photovoltaic principles while still adapting flexibly to real data. Preliminary evaluations show that the physics-regularized model reduces prediction error compared to standard neural networks and maintains robust performance under unseen conditions. More importantly, the approach offers interpretable and trustworthy forecasts, addressing a key gap in PV power prediction. By combining the adaptability of AI with the reliability of physical laws, this work contributes to the development of sustainable, data-driven tools for renewable energy system optimization.

Urban areas, now hosting over half of the global population and consuming 60–80% of total energy, make urban energy management a critical global priority. Historic cities, with their centuries-old and listed buildings, pose unique challenges but also offer significant opportunities for improving energy efficiency. Effective energy management requires comprehensive knowledge, supported by accurate diagnostics of building quality. Non-destructive testing (NDT) techniques, valued for their precision and non-invasive nature, offer effective solutions for complex urban environments. Among these, infrared thermography (IRT) plays a central role by enabling rapid and non-invasive acquisition of surface temperature distributions to support both qualitative and quantitative analyses. Drone-assisted IRT (UAV-IRT) further enhances these capabilities by facilitating energy audits, diagnosing heat losses, assessing HVAC efficiency, and inspecting renewable energy systems at the urban scale. Unlike ground-based imaging, UAV-IRT can access hard-to-reach areas and high-altitude structures (e.g., rooftops), without accessibility constraints, thereby improving the scope, accuracy, and efficiency of diagnostics.

Interpreting thermograms acquired via UAV-IRT for urban roof diagnostics remains challenging due to heterogeneous construction materials, complex thermal patterns, and the large volume of data generated. Manual inspection is often inefficient, subjective, and error-prone, particularly when distinguishing among insulation defects, moisture ingress, thermal bridges, and potential structural damage. This study presents a dataset of thermograms collected over two years from multiple historic buildings in Italy and applies machine learning for automated interpretation. The AI-based approach allows for the automatic detection and classification of thermal anomalies by reducing subjectivity and improving accuracy and consistency. It also enables surface segmentation by distinguishing between different materials and functional zones (e.g., roof coverings, mechanical systems, structural elements), revealing correlations between anomalies and underlying structural or energy-related conditions. This method demonstrates the feasibility of faster, more reliable, and predictive roof diagnostics, thereby supporting evidence-based strategies for energy management and conservation in historic cities.

Artificial intelligence (AI) is reshaping urban energy management by linking predictive analytics with closed-loop control across buildings, grids, mobility, and planning. This paper investigates which AI strategies deliver verified, scalable efficiency gains in cities and under what conditions they outperform conventional practice. Synthesizing recent applications, we compare measured and simulated outcomes across asset scales. In buildings, machine learning for forecasting, fault detection, and supervisory control, including reinforcement-learning policies, commonly yields ~10–37% operational energy savings while maintaining comfort. AI-enabled digital twins that fuse BIM/IoT with physics-guided models support anomaly detection and set-point optimization, with documented energy reductions of ~5–17% and improvements in indoor environmental quality. On the supply side, AI strengthens smart-grid operations through improved demand and renewable forecasting, demand–response orchestration, and predictive maintenance, enabling higher variable-renewable penetration and lowering peaks. In urban mobility, adaptive, AI-coordinated signaling reduces intersection delays by ~10–30%, with fuel and emission co-benefits. Realizing system-level gains, however, depends on high-quality data, robust calibration, and human-in-the-loop operation; key barriers include fragmented data governance, limited generalization across climates and vintages, interoperability gaps among BMS/IoT/twin platforms, and privacy–cybersecurity risks. We argue that durable impact will come from physics-guided ML and RL/MPC with explicit comfort, equity, and safety constraints; secure, interoperable digital-twin backbones; and standardized, transparent measurement-and-verification protocols. Implemented at scale alongside retrofits and clean power, AI-enhanced strategies can materially reduce urban energy use and CO₂ emissions while preserving service quality, offering a pragmatic path for cities to accelerate decarbonization

Addressing the challenge of optimizing energy consumption in central air conditioning systems under coupled multi-parameter and dynamic operating conditions, this study proposes an integrated approach combining cooling load forecasting with multi-objective collaborative optimization to enhance system energy efficiency and operational stability. Utilizing sensor data from a factory, a hybrid RF-CNN-LSTM forecasting model is developed. This model leverages random forest (RF) for feature selection, a convolutional neural network (CNN) for extracting local patterns, and a long short-term memory (LSTM) network for capturing temporal dependencies, achieving high-precision prediction of cooling capacity demand. Subsequently, an energy consumption model encompassing chillers, water pumps, and cooling towers is established. This study employs the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) to simultaneously optimize three objectives: minimizing the total system energy consumption, maximizing the coefficient of performance (COP) of the chillers, and minimizing the fluctuation of key operating parameters. The experimental results demonstrate that the forecasting model achieves a coefficient of determination (R²) of 0.9625 and a mean absolute error (MAE) of 143.62 kW on the test dataset. After optimization, the total system energy consumption is reduced by an average of 14.53%, reaching 124.58 kW. The chillers contribute 93.94 kW (75.4%) of this energy saving, while the combined energy saving rate for the chilled water pumps and condenser water pumps reaches 37.76%. Despite a 16.40 kW increase in cooling tower power consumption, the overall system achieved significant net energy savings. A reduction of 4.8 °C in the cooling water inlet temperature led to a 13.8% improvement in chiller COP. The multi-objective optimization strategy significantly reduced the temperature fluctuation of chilled water supply and return by 76.48% and 81.79%, respectively, effectively enhancing operational stability. For scenarios involving sudden increases in cooling load, although the fluctuation of the cooling water inlet temperature slightly increases, the response effectively overcomes the hysteresis typically associated with traditional control systems.