Search Results (48)

The central challenge of the energy transition lies in whether an economy possesses the institutional capacity to systematically regulate its own energy inputs and carbon emissions. Drawing upon social metabolism theory, this study constructs an indicator of carbon–energy metabolic control capacity (CMCC). Building on business ecosystem theory, it conceptualizes the intelligent economic ecosystem (IEE) and incorporates industrial chain intellectual property empowerment (IP) into a causal framework of institutional provision → ecosystem development → enhancement of metabolic control capacity. Using panel data from 30 provincial-level administrative regions in China covering the period 2010–2022, this study employs a spatial Durbin difference-in-differences (SDID) model and a double machine learning (DML) framework for empirical analysis. The results indicate that industrial chain intellectual property empowerment significantly enhances carbon–energy metabolic control capacity and generates positive spatial spillover effects on neighboring regions through the public diffusion of patent information. Furthermore, intelligent economic ecological development serves as a significant partial mediator between intellectual property empowerment and carbon–energy metabolic control capacity, with the indirect effect accounting for more than one-third of the total effect. This mediating mechanism remains robust after replacing machine learning algorithms, altering sample-splitting ratios, controlling for concurrent innovation policies, and excluding the impact of the COVID-19 pandemic. Path-specific mediation analysis further reveals that computing power acquisition and value transformation together with digital substrate robustness constitute the dominant transmission channels, whereas innovation metabolic flux contributes a relatively smaller mediating effect due to the long gestation period required for translating fundamental research into practical applications. Heterogeneity analysis further demonstrates that the transmission mechanism exhibits full mediation in the dimension of metabolic structure, indicating that the contribution of industrial chain intellectual property empowerment to the clean substitution of energy structures depends almost entirely on the mediating role of the intelligent economic ecosystem. These findings provide clear actionable guidelines for three specific policy-making domains to advance low-carbon transitions. First, intellectual property authorities should transition from quantity-driven patent creation to establishing cross-regional patent navigation and industrial chain IP pooling. Second, digital economy and industry regulators need to prioritize computing power value conversion (CCV) over raw infrastructure expansion to mitigate energy rebound effects. Third, energy and environmental agencies ought to integrate real-time algorithmic dispatching with green finance incentives. Ultimately, this study demonstrates that achieving deep low-carbon transformation requires leveraging institutional public goods to catalyze digital ecosystems, which in turn enable precise, dynamic carbon–energy metabolic control. Full article

The rapid proliferation of Internet of Things (IoT) devices within 5G-enabled smart city environments has introduced unprecedented challenges in communication protocol management across heterogeneous network architectures. With connected IoT devices projected to reach 21.1 billion by the end of 2025 and approximately 39 billion by 2030, existing static protocol selection mechanisms are unable to accommodate the dynamic Quality of Service (QoS) requirements of different smart city applications, such as enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communication (URLLC), and massive Machine-Type Communication (mMTC). This paper presents APO-DRL (Adaptive Protocol Optimization using Deep Reinforcement Learning), a framework that utilizes a Dueling Double Deep Q-Network (D3QN) combined with a Prioritized Experience Replay mechanism for intelligent, real-time communication protocol selection and parameter optimization in heterogeneous IoT networks. The proposed framework formulates the protocol optimization problem as a Markov Decision Process (MDP), wherein the DRL agent dynamically selects the optimal communication protocol (NB-IoT, LTE-M, LTE Cat-1, or 5G NR) and adaptively tunes transmission parameters based on real-time network conditions. Experimental evaluation in a 3GPP TR 38.901 Urban Macro simulation environment with N = 30 devices demonstrates that APO-DRL achieves a 138.9% improvement in average throughput compared to Static Allocation (60.00 vs. 25.12 Mbps), while simultaneously achieving the highest QoS satisfaction (83.38%) across all methods, albeit with higher energy consumption and packet loss than Static Allocation. Relative to D3QN+PER, APO-DRL exhibits substantially lower cross-seed throughput variance (±0.88 vs. ±11.03 Mbps), confirming that QA-PER produces a more stable and reproducible learned policy. Full article

Accurate urban building energy modeling (UBEM) is constrained by mismatches between standard climate inputs and actual urban microclimate conditions. This study introduces a scalable, bottom-up, framework that integrates EnergyPlus building energy modeling simulation outputs with Earth observational and geographical-based urban morphology data, which are enhanced through machine learning techniques to improve energy demand predictions in urban settings. Applied to Los Angeles (LA), California, we evaluate the representativeness of typical meteorological year (TMYx) sampling sites against actual urban environmental conditions. We find that while satellite-derived surface temperatures show reasonable alignment with average city conditions, significant discrepancies are observed in urban form metrics such as tree cover, street cover, and building density, suggesting that TMYx stations should be placed in denser urban areas. We augment EnergyPlus simulations for 19 single-family buildings, with remote sensing data using machine learning models, to generate city-wide residential energy consumption heatmaps corrected for microclimate conditions. Models capture substantial intra-urban variation, with predicted energy use differing by approximately 10% between neighborhoods. Feature importance analysis highlights land surface temperature as a key predictor, underscoring its relevance to building energy research. We also find the majority of TMY3 sampling sites to be in low-vulnerability areas, underscoring the structural mismatch that is embedded in urban form and climate. This framework offers a scalable path for integrating urban microclimate effects into energy modeling to enable more precise and equitable energy policy and planning. Full article

Green hydrogen is increasingly discussed as an energy carrier that can link electricity, gas, heat, and transport sectors. However, many existing reviews address this topic from separate viewpoints, such as hydrogen production technologies, Artificial Intelligence (AI) applications, or system integration, with less attention to how policy and market conditions affect deployment. This review brings these related aspects together in one structured discussion. The paper first reviews the hydrogen supply chain, including production, storage, transport, and utilization. It then discusses an integrated multi-energy architecture in which hydrogen interacts with electricity, natural gas, heat, and cooling networks. Policy instruments in five major economies, including the European Union, the United States, China, Japan, and India, are compared. The review also summarizes the main barriers to large-scale deployment, including high production costs, limited infrastructure, technological challenges, regulatory uncertainty, and supply-chain constraints. In addition, the current market structure and selected large-scale hydrogen projects planned in the United States are reviewed. The paper also examines the role of artificial intelligence in green hydrogen systems. AI applications are grouped into four main stages of the hydrogen value chain: forecasting renewable energy generation, improving electrolyzer design and operation, optimizing storage and distribution, and supporting system-level techno-economic assessment. Recent Machine Learning (ML) studies are compared based on their methods and their contributions to operation and planning. Overall, this review highlights the role of AI in enabling green hydrogen integration within multi-energy systems. Full article

Buildings are the primary energy consumption layer of Renewable Energy Communities (RECs) and a key target for net-zero policy under the EPBD recast. This scoping review applies the PRISMA-ScR framework to map Digital Twin (DT) architectures for building-scale and community-scale energy management in REC configurations. A Scopus search yielded a final analytical corpus of 102 studies, coded through an eight-dimensional thematic matrix covering lifecycle phases, digitalization objectives, enabling technologies, DT capability dimensions, and data realism. DT is the dominant enabling technology (55.9%), followed by IoT (23.5%) and machine learning (22.5%). Research is concentrated in the Planning and Design phase (77.5%) and markedly underrepresented in Implementation and Commissioning (16.7%). Notably, only 10.8% of studies integrate real-time operational data, exposing a significant gap between simulation-based research and the deployment conditions required under current EPBD mandates. The evidence base supports building energy monitoring, demand forecasting, and flexible grid operation but remains limited for retrofit verification, standardized net-zero KPIs, and operational workflows in existing stock. Critical DT capability gaps persist in Data Services (7.8%) and User Experience (18.6%). Overall, DT architectures show genuine potential for grid-interactive, net-zero building management, yet the field presents unresolved structural challenges for large-scale real-world deployment. Full article

Market competition is increasingly intense and sustainable development has attracted widespread attention. The flexible job shop scheduling problem requires the collaborative optimization of production efficiency and machine energy consumption. This scheduling problem has high solution complexity. It is difficult to balance multiple conflicting objectives and obtain stable scheduling results with traditional optimization methods. A Dual-Layer Proximal Policy Optimization algorithm (DL-PPO) based on a hierarchical decision-making mechanism is proposed to achieve the collaborative optimization of production efficiency and energy consumption in solving the Energy-Aware Flexible Job Shop Scheduling Problem (EA-FJSP). First, a hierarchical scheduling framework based on DL-PPO is designed to solve the EA-FJSP. In this framework, the high-level controller selects sub-objectives from a global optimization perspective, while the low-level controller executes feasible dispatching rules according to the selected sub-objectives. Twelve key state features extracted from four dimensions, time, energy consumption, job, and machine, are used to construct a multi-dimensional state space. These features enable a comprehensive state representation of the scheduling environment and provide accurate input for the DL-PPO. The global optimization objective is decomposed into four sub-objectives employing a goal decoupling policy. Four dedicated reward functions are designed for the sub-objectives to guide the low-level controller to make optimal decisions in terms of time and energy consumption, thereby achieving multi-objective collaborative optimization. Considering the two decisions of job selection and machine assignment in solving the EA-FJSP, twenty dual-decision-point dispatching rules are designed as the action space for the low-level controller to achieve the global optimization objective. Finally, the effectiveness, applicability, and superiority of the DL-PPO in EA-FJSP are demonstrated through comparisons with dispatching rules and other deep reinforcement learning methods. Full article

Development of sustainability systems for assessment of environmental impacts remains a paramount challenge for green and circular manufacturing of polymers. In this study, a comprehensive life cycle assessment (LCA) framework is developed for European polymeric waste by integrating OpenLCA, Ecoinvent v3.11, and Python-based machine learning (ML) algorithms. Cradle-to-gate, service-life, and cradle-to-grave assessments are performed for representative thermoplastic composite systems, including PP–PET–cotton, HDPE–glass fiber, and PEEK–carbon fiber composites, covering domestic, engineering, and high-performance polymer categories. The results demonstrate that raw material extraction and manufacturing stages dominate environmental impacts, contributing the highest shares to climate change, ecotoxicity, and non-renewable energy consumption. PP-based composite systems exhibit the lowest overall environmental burdens due to lower processing energy and simpler molecular structures, while HDPE-based systems show moderate impacts. PEEK-based composites present the highest impacts per unit mass, driven by energy-intensive synthesis and high processing temperature. Environmental impacts are evaluated using EF v3.1 and ReCiPe methodologies, supported by Monte Carlo simulations and ML-assisted uncertainty quantification. Monte Carlo simulations and ML-assisted LCA provide probabilistic ranges, uncertainty quantification, and predictive insights into impact indicators, enabling the development of a quantitative sustainability system based on probability–impact relationships. A Europe-wide assessment of 57 Mt of polymeric waste highlights that environmental burdens are concentrated in countries with high polymer production and consumption, emphasizing the importance of energy mix, recycling efficiency, and waste management strategies. Overall, this work demonstrates that digitalized LCA coupled with ML offers a powerful decision-support framework for sustainable polymer design, recycling optimization, and circular economy policy development, supporting the transition toward low-carbon and resource-efficient polymer systems in Europe. Full article

Energy poverty poses a critical threat to global sustainable development by undermining household well-being and deepening social inequality. This study draws on data from 17,778 households across six waves of the China Family Panel Studies (CFPS) from 2012 to 2022 to examine the dynamics, determinants, and predictive patterns of household energy poverty in China. Our study also enhances and optimises the four-quadrant classification framework within the Low-Income, High-Cost (LIHC) framework, which jointly evaluates income and energy expenditure using dynamic thresholds. This approach enables us to identify not only households experiencing energy poverty but also those facing heightened vulnerability. In the sample, 7.96% were classified as energy-poor, 29.10% as at risk of energy poverty, 24.14% as at risk of income poverty, and 38.81% as not at risk, indicating that the number of households facing hidden risks far exceeds that of households identified as poor using traditional binary diagnostic methods. Next, we implement a Bayesian-optimised Extreme Gradient Boosting (XGBoost) model to improve predictive accuracy. Thus, the trained model achieved a prediction accuracy of 78%. We employ Shapley Additive exPlanations (SHAP) analysis to interpret the relative importance and interaction of explanatory variables. Our findings reveal three key patterns. First, households at risk of energy insecurity substantially outnumber those already in energy poverty, indicating a large latent vulnerable population that conventional measures often overlook. Second, housing conditions and energy expenditures remain the dominant structural drivers of energy poverty; however, financial pressures related to healthcare, education, and other non-energy expenditures increasingly intensify vulnerability. Third, Bayesian optimisation significantly enhances the model’s capacity to capture nonlinear relationships and complex household heterogeneity. By integrating dynamic measurement with interpretable machine learning, this study advances methodological approaches to energy poverty assessment and provides robust empirical evidence for early-warning systems, differentiated governance strategies, and targeted policy design in the context of China’s energy transition. Full article

The accelerating generation of waste streams is observed globally. Spanning lignocellulosic biomass, plastic waste, sewage sludge, and industrial residues, this review presents both an urgent management challenge and a compelling materials opportunity. Carbon materials derived from these waste streams offer a sustainable route to functional carbons applicable in electrochemical energy storage, adsorption, heterogeneous catalysis, and high-temperature applications. Yet their rational design remains constrained by incomplete understanding of the relationships between feedstock composition, processing pathway, structural characteristics, and functional performance. This review provides an integrated analysis of waste-derived carbon materials from processing pathways to structure–property–function relationships. The principal feedstock categories are examined for their compositional characteristics and implications for carbon yield and structure. Five primary processing routes are assessed. The five routes examined are pyrolysis, hydrothermal carbonisation, physical and chemical activation, and microwave-assisted processing. They are assessed comparatively with emphasis on structural outcomes and governing parameters. The resulting structural characteristics are discussed. These are morphology, hierarchical pore architecture, surface chemistry, heteroatom doping, and crystallinity. They are discussed alongside their characterisation methods and known limitations as performance predictors. Structure–property relationships are examined quantitatively. Heteroatom-doped hierarchical porous carbons achieve 612 F/g specific capacitance. Turbostratic hard carbons deliver 450 mAh/g sodium storage with over 90% retention. Hierarchical porous carbons demonstrate CO₂ uptake of 5.0 mmol/g and dye adsorption exceeding 9000 mg/g under optimised laboratory conditions; these values reflect individual studies and are not directly comparable across systems. Biomass-derived sulfonated carbon catalysts sustain biodiesel yields above 90% over multiple cycles. Challenges of feedstock variability, process scalability, environmental compliance, and economic feasibility are addressed, and machine learning-guided design, standardised characterisation methodology, and circular economy policy frameworks are identified as key enablers for translating laboratory performance into industrial reality. Full article

Mitigating energy intensity stands as a core linchpin for fulfilling China’s “dual carbon” strategic goals and facilitating the low-carbon green transition of the economic system. Against the backdrop of the in-depth convergence of the digital economy and the real economy, a critical unresolved research question persists: whether and through what pathways digital government construction can improve energy utilization efficiency by enabling the development of emerging strategic industries. Against this background, this study systematically investigates the combined effects and intrinsic transmission mechanisms between digital government construction, the high-quality development of the low-altitude economy (hereafter referred to as LAE), and regional energy intensity. Specifically, this study addresses four core research gaps: first, whether digital government construction can exert a direct curbing effect on energy intensity; second, what functional role the high-quality development of the LAE plays in this causal relationship; third, whether spatial spillover effects exist between the two core factors on regional energy intensity; and fourth, whether the industrial, market, and policy dimensions of LAE development have heterogeneous influences in the above transmission mechanism. To answer the above research questions, this study constructs a unified analytical framework that incorporates digital government construction, high-quality LAE development, and regional energy intensity. We employ panel data covering 30 provinces in China from 2012 to 2022, taking the institutional reform of provincial big data management authorities as a quasi-natural experiment to identify the policy effects of digital government construction. Meanwhile, we build a comprehensive evaluation system to quantify the high-quality development level of the LAE from three core dimensions: industrial development, market maturity, and policy support. On this basis, the spatial difference-in-differences (SDID) model and double machine learning (DML) model are adopted to carry out systematic empirical tests. The empirical results reveal the following core findings: First, both digital government construction and the high-quality development of the LAE have a significant direct inhibitory effect on regional energy intensity. Second, the spatial spillover effects of the two factors present pronounced heterogeneous characteristics: the radiation effect of digital government construction on adjacent regions depends on the dual premise of geographical proximity and economic development similarity, while the technology spillover effect of LAE development can be effectively realized under the single condition of economic similarity. Third, the high-quality development of the LAE plays a significant mediating role in the causal chain of digital government construction affecting regional energy intensity, and this transmission mechanism remains statistically robust after a series of robustness tests, including algorithm replacement, adjustment of sample splitting ratios, and exclusion of interference from concurrent policy shocks. Fourth, further decomposition tests of the transmission path demonstrate that the industrial dimension plays the most core and fundamental role, acting as the “material basis” for transforming the governance efficiency of digital government into actual energy-saving effects, while the market and policy dimensions function as key supporting collaborative mechanisms, whose transmission intensity is highly dependent on the foundation of industrial development. This study unpacks the intrinsic transmission mechanism through which digital government construction enables the LAE to curb regional energy intensity, offering solid theoretical underpinnings and actionable policy implications for emerging market economies to advance energy “dual control” targets and foster the development of new quality productive forces. Full article

The design of differentiated fiscal instruments for industrial sustainability requires robust, data-driven tools capable of capturing the heterogeneity of environmental performance across manufacturing units—a challenge that conventional econometric approaches address only partially, given the non-linear nature of operational–environmental interactions in reconfigurable production systems. This study introduces a two-phase computational framework that integrates unsupervised machine learning and supervised classification to generate evidence-based sustainability profiles for fiscal policy targeting. Its principal contribution is the combination of K-Means clustering with a binary artificial neural network (ANN) classifier, operationalized through an accessible decision-support interface that enables differentiated incentive allocation without requiring programming expertise from policymakers. A dataset of 1000 manufacturing records comprising seven operational and technological input variables—material usage, production capacity, reconfiguration time, downtime, AI optimization, IoT connectivity, and predictive maintenance—and three environmental output indicators—energy consumption, carbon emissions, and waste generation—was analyzed. In Phase One, K-Means segmentation with k = 6, selected through multi-criteria convergence (Silhouette = 0.102; Elbow, Davies–Bouldin, and Calinski–Harabasz indices), identified six distinct sustainability profiles with marked environmental differentiation. In Phase Two, a binary ANN classifier (architecture: 7 → 64 → 32 → 1 neurons; ReLU and sigmoid activations) was trained to distinguish the reference cluster C0 (low environmental impact: energy 145.1 kWh, emissions 45.2 CO₂-eq) from the high-impact cluster C1 (emissions 67.8 CO₂-eq, waste 41.5 kg). The trained classifier achieved an overall accuracy of 75.4% and an AUC-ROC of 0.774 on the held-out test set, with a macro-averaged F1-score of 0.753 and a Cohen’s kappa coefficient of 0.508, indicating moderate-to-substantial agreement beyond chance. Class C1 (high-impact establishments) achieved a precision of 0.794 and a recall of 0.730, supporting reliable identification of manufacturing units that would most benefit from targeted fiscal support. The framework is deployed through a Gradio-based graphical interface incorporating a traffic-light sustainability classification (green/yellow/red), enabling direct and interactive application by tax authorities and industrial policymakers. The modular architecture supports adaptation to larger or sector-specific datasets, making it transferable across industrial policy contexts. Full article

The Brazilian residential sector is one of the largest consumers of electricity, making residential energy consumption a critical component of national energy systems. Electricity consumption patterns in this sector are closely associated with household appliance ownership and, consequently, with socioeconomic status. For residential energy planning to operate more equitably and efficiently, it is essential that consumption analyses be aligned with the socioeconomic conditions of the population. This study examines the role of socioeconomic variables in residential energy planning through the application of supervised machine learning algorithms within a data-driven socioeconomic segmentation framework. Decision trees, support vector machines, and artificial neural networks were implemented using data from the Brazilian residential sector to evaluate model performance and to determine the extent to which household socioeconomic status can be inferred from variables related to appliance ownership and electricity consumption characteristics. The results showed that household appliances, such as refrigerators, microwave ovens, and air conditioners, exhibited substantial predictive power in relation to socioeconomic status, thus improving the interpretation and understanding of residential energy consumption from a multidimensional perspective. The neural network model achieved the highest predictive performance. By enabling data-driven socioeconomic segmentation based on observable electricity consumption patterns, this approach provides relevant insights for residential energy planning and contributes to more targeted and equitable energy policy design, supporting Sustainable Development Goal 7 on Affordable and Clean Energy and Sustainable Development Goal 10 on Reduced Inequalities. Full article

This study examines how digital trade contributes to decarbonization within global value chains (GVCs), focusing on the roles of AI-enabled logistics, carbon pricing, and renewable energy policy. Using a monthly panel of 38 OECD economies from 2000 to 2024, we combine econometric models with machine-learning techniques to identify threshold effects and conditional relationships. The empirical specification includes fixed effects, interaction terms for AI-enhanced logistics, and carbon-pricing threshold analysis. At the same time, structural equation modelling (SEM) is used to assess mediation through renewable energy and regulatory stringency. The results indicate that GVC participation is significantly associated with lower CO₂ emissions (β = −0.064, p < 0.01). Digital trade alone is not statistically significant (β = −0.030), but its environmental effect becomes stronger when combined with AI-enhanced logistics. We identify a carbon-pricing threshold of USD 40 per tonne, above which emissions decline significantly (Δ = −15%, p < 0.01). Renewable energy adoption further reinforces the beneficial effect of digital trade under stronger regulatory conditions. These findings suggest that the emissions effects of digital trade are conditional rather than uniform and depend on complementary policy, technological, and energy factors. While the analysis is limited to OECD economies and monthly aggregate data, the study helps explain mixed findings in the literature by identifying the conditions under which digital trade is more likely to support emissions reduction. Full article

Transparent and evidence-based representations of global crude oil refining systems remain limited in the public literature, constraining robust energy systems modeling and policy analysis. This study develops a comprehensive, configuration-based modeling framework for all operating crude oil refineries worldwide using plant-level process unit data. Forty unique refinery configurations are identified through an unsupervised decision tree-based clustering approach that accounts for process unit presence and relative conversion intensity. An extremely randomized trees (ETR) machine learning model is trained on approximately 11,000 refinery-year observations to predict refined product yields as a function of refinery configuration, capacity, and crude oil diet. The model achieves out-of-sample coefficients of determination exceeding 0.90 for all major products and outperforms multiple linear regression and other ensemble methods. The predictive model is integrated with a differential evolution optimization algorithm to enable refinery programming under operational and feedstock constraints. The application of this model to Gulf Cooperation Council (GCC) refineries shows that, under existing technologies, petrochemical feedstock yields are bounded at approximately 37%, significantly below announced long-term diversification targets of 70–85%. Yield improvements of up to 6 percentage points are feasible through operational optimization but are associated with capacity utilization adjustments and product trade-offs. The framework provides a scalable tool for refinery benchmarking, energy transition analysis, and strategic planning across facility, national, and global levels. Full article

Against the backdrop of the in-depth adjustment of the global energy pattern and the accelerated advancement of the energy transition, coupled with the frequent occurrence of extreme climate events and the continuous intensification of risks such as supply fluctuations and external shocks faced by urban energy systems, improving urban energy resilience has become a core measure for all countries to address the vulnerability of energy systems and promote urban sustainable development. As a core technical carrier of intelligent manufacturing, the enabling role of industrial robots (IRs) in enhancing urban energy resilience (UER) has also become an important research topic in the field of the energy economy. This paper takes 280 prefecture-level and above cities in China from 2009 to 2023 as research samples and empirically examines their impact effects by constructing a Double Machine Learning (DML) model, transmission mechanism, and moderating effect of IRs on UER and ensures the reliability of conclusions through various robustness tests. The research findings indicate that IRs significantly promote the improvement of UER; industrial structure upgrading and green technology innovation are the main mediating paths, verifying how IRs affect UER from two different aspects and both environmental regulation (ER) and science expenditure (SE) positively moderate the promoting effect of IRs on UER, with the coefficients of the interaction terms being significantly positive. Robustness tests show that the core conclusions are highly reliable. This study fills the research gap in the transmission mechanism between IRs and UER and provides empirical evidence for the formulation of relevant policies. Accordingly, it is proposed that governments should strengthen the policy support for the application of industrial robots in high-energy-consuming industries, optimize the synergy mechanism between environmental regulation and scientific and technological expenditure, guide the deep integration of industrial robots with industrial structure upgrading and green technology innovation, and formulate differentiated promotion strategies based on regional energy resilience characteristics and industrial development foundations, so as to fully release the energy-resilience-improvement effect of industrial robots. Full article