Energy Informatics最新文献

Photovoltaic (PV) power forecasting technology enhances the absorption capacity of renewable energy. However, the PV power generation process is highly sensitive to fluctuations in weather conditions, making accurate forecasting challenging. In this paper, we propose a composite data augmentation method and a model that can effectively utilize the augmented data. The PV power generation process has a fluctuating nature over time, so an augmented sample set with temporal correlation was created. This was achieved by reconstructing meteorological features and screening measurements similar to historical meteorological conditions. To improve the feature extraction capability for multi-source heterogeneous data and the temporal modeling capability for fine-grained periods, a multi-source temporal-feature convolutional networks (MSTFCN) model is proposed. MSTFCN employs parallel convolution to capture local temporal patterns and improves global feature representation via a channel attention mechanism. Based on this, redundant information is suppressed by a cascading channel compression approach, and a temporal segmentation strategy is applied to model fine-grained temporal features. We conducted experiments on two publicly available datasets, and the results demonstrate that the proposed data augmentation method effectively improves the forecasting performance of the deep learning model. Moreover, MSTFCN achieves higher forecasting accuracy and exhibits stronger environmental adaptability than the compared models.

In response to the power supply security of power grid system caused by a large number of clean energy connected to the distribution network, based on the grid side energy storage investors, the butterfly optimization algorithm is improved by combining the dynamic switching probability coordination algorithm and the dynamic Gaussian mutation strategy. A Distributed Energy Storage System (DESS) planning for power grid is constructed. The results showed that the research model had high stability and convergence accuracy, which was superior to comparison algorithms. When two DESS power stations were connected to nodes 4 and 32, with rated powers of 1.63 MW and 1.78 MW, and rated capacities of 5.71 MWh and 7.33 MWh, the annual benefits of capacity decision, location decision, and system were 783,000 RMB, 394,400 RMB, and 388,600 RMB, respectively. This showed that the research method could help operators obtain the maximum equal life return and meet their investment expectations. Before connecting to DESS, the overall voltage deviation of each typical state decreased by 5.28 p.u., 5.79 p.u., 2.84 p.u., and 2.37 p.u., and the overall active power loss of the daily power grid decreased by 1.41 MW, 1.83 MW, 1.79 MW, and 1.68 MW, respectively, indicating significant optimization effects. The research results indicate that the proposed solution can improve the overall stability and economy of the power grid, with strong applicability. This is of great significance for leveraging the supportive role of energy storage in safe operation and promoting the large-scale application of energy storage systems.

Against the backdrop of the “dual carbon” strategy, building carbon emissions have been incorporated into the construction review process. Currently, the calculation and accounting of carbon emissions throughout the entire building lifecycle have become a hot and challenging issue in the field of building carbon emissions. Commercial office buildings, due to their large scale, high energy consumption, and significant carbon emission base, have become a key area for energy conservation and carbon reduction in public buildings. According to the building lifecycle carbon emission assessment system, the lifecycle of commercial office buildings can be divided into four stages: production of building materials, construction, operation and maintenance, and dismantling and recycling. This study takes an existing commercial office building in Beijing, China, as a case study, and based on data from energy audit reports, calculates the carbon emissions of each lifecycle stage using national standards and relevant software, and discusses the factors affecting building carbon emissions. At the same time, a comparative analysis of the differences between Chinese and Western national standards is conducted. Ultimately, strategies to reduce building carbon emissions are proposed. This study is of reference value for the precise calculation of carbon emissions throughout the lifecycle of commercial office buildings.

This paper presents a two-stage optimization framework for long-term energy management in microgrids, aiming to efficiently integrate various energy sources, storage systems, and consumption elements while addressing uncertainties in load demand and renewable generation. The framework consists of an offline optimization stage and an online optimization stage, each with distinct roles to balance long-term planning and real-time adaptability. In the offline stage, a robust two-stage mixed-integer linear programming (MILP) model is used to set annual targets for the state of charge (SoC) of energy storage systems. This stage applies a min-max-min approach to optimize for worst-case scenarios, establishing a cost-effective and reliable baseline plan that reduces dependency on conventional power sources and minimizes load deficits. The online stage, on the other hand, employs a new online convex optimization model that dynamically adjusts energy storage and dispatch decisions based on real-time data, allowing the microgrid to respond flexibly to fluctuations in demand and renewable generation. Simulation results using the Elia and North China datasets demonstrate the effectiveness of this two-stage approach. Offline optimization achieved up to 25% cost savings and reduced unmet demand by up to 99%, providing a stable foundation for efficient energy management. The online optimization stage further improved system responsiveness, minimizing reliance on backup generators and enhancing load reliability. This combined framework offers a comprehensive solution for optimizing microgrid performance, balancing predictive planning with real-time adaptability in complex, variable energy environments.

In the context of energy management during digital transformation, traditional energy storage devices face challenges in multi-source coordination and efficient management. The key issue for system optimization is how to stabilize the management of multiple energy storage units. To address this, the study innovatively proposes a Hybrid Energy Storage System integrating a Multi-Port Transformer and Direct Current Bus. By constructing multi-port control factors, the system achieves coordinated optimization of the energy storage units, through dynamic adjustment of multi-port control factors and energy conversion matrices, the system can flexibly allocate power output from various energy storage units according to load demands, ensuring stable system operation. Experimental results in a microgrid system show that the integrated control system has a response time of 2.3 ms under 80% load, significantly outperforming the Proportional Integral Control (8.7 ms) and during the energy storage unit switching process, the voltage fluctuation rate is only 0.8% with a switching time of just 1.8 ms, and system stability reaching 98.5%. Under high-load conditions, the energy conversion efficiency is 96.8%, and the power distribution error is only 1.2%. Compared to traditional energy storage devices, the initial investment cost of this device is reduced by 7.4%, and the annual maintenance cost is reduced by 21.7%. These results indicate that the improved hybrid energy storage device not only possesses excellent energy management capabilities but also significantly reduces operational costs and environmental impact. The study provides an efficient technical solution for managing complex energy systems, which is of great significance for promoting smart grid construction and achieving green, low-carbon goals.

The purpose of this study is to explore the impact of dynamic adaptation of corporate innovation culture and market demand on corporate sustainable development and the differences in corporate types and regions. The research sample covers 150 listed companies and 100 non-listed companies in eight industries and three economic regions: the eastern coastal area, the rise of central China, and the development of the western region from 2015 to 2020. The theoretical framework is constructed using the system dynamics model, and the empirical methods of multivariate regression analysis such as ordinary least squares, fixed effect model, and instrumental variable method are used for research. The main findings include that there is a significant positive synergistic relationship between corporate innovation culture and market demand, and there are differences in development models among enterprises of different types and regions. These results have important policy implications and can provide reference for the National Development and Reform Commission, the Ministry of Industry and Information Technology and other relevant departments to formulate policies such as industrial guidance and innovation incentives, help enterprises achieve sustainable development, and enhance the competitiveness of the national industry.

The paradigm shift towards Smart Grids, Smart Buildings, Smart Monitoring, and Operation has driven researchers to propose innovative solutions for designing and maintaining energy systems. Although the integration of Renewable Energy Sources (RES) supports sustainability goals, it also introduces vulnerabilities to unpredictable challenges such as grid stability, energy storage requirements, and infrastructure modernization. Machine Learning (ML) has emerged as a transformative tool to address these challenges, offering opportunities to enhance energy efficiency, and system design in alignment with Sustainable Development Goals (SDGs). The emphasis on these goals necessitates the study of new system designs that prioritize energy efficiency. Building on its proven success, researchers are increasingly adopting ML-driven approaches to accelerate advances in energy systems. This work presents a detailed review of current ML-driven research trends in energy systems, outlines the associated challenges, and provides potential research directions and recommendations. Unlike the existing literature, which focuses primarily on ML applications in the RES domain, this study offers a holistic perspective on ML-driven approaches across various aspects of energy systems, including energy policy and sustainability. It aims to serve as a comprehensive resource, bridging the gap between research advancements and practical implementations in energy systems through ML-driven innovation.

This study addresses the construction sector’s growing need for improved decision-making and reduced carbon emissions by integrating Lean principles into Building Information Modeling (BIM). A decision-support tool was developed using Python and RStudio to enhance stakeholder efficiency, reduce errors, and streamline communication. The tool combines Set-Based Design, Choosing By Advantages, and Big Room methods with Industry Foundation Classes (IFC) data to automatically generate and evaluate insulation options based on multi-criteria analysis. To test its adaptability and effectiveness, the tool was applied to two real-world case studies in different regions of France with distinct climatic conditions and project objectives. The first case study involved a mixed-use building in Rennes, where the objective was to enhance energy performance. The selected insulation material reduced heating needs by 13%, annual CO₂ emissions by 14%, and insulation costs by 45% over a 50-year period. The second case study focused on a residential building in Orléans, where the goal was to improve both energy efficiency and environmental impact. The tool achieved a 6% reduction in primary energy consumption, a 40% decrease in carbon footprint per (m^2) and a 6% reduction in annual CO₂ emissions. The tool’s ability to adapt to different building types and climatic conditions confirms its accuracy and reliability in optimizing energy performance and reducing environmental impact and project costs. This research provides a scalable tool for enhancing decision-making efficiency and improving building energy performance, environmental impact, and cost-effectiveness in construction projects.

Electric vehicles (EVs) are revolutionizing transportation, utilizing batteries as mobile energy storage to mitigate carbon emissions and fossil fuel depletion. Power utilities are increasingly employing EVs with dynamic energy storage for ancillary services such as frequency and voltage regulation. Additionally, EVs are utilized for dynamic damping services, where grid-connected EVs help mitigate frequency oscillations in weak grid conditions. This work presents a novel modified automatic voltage regulator (AVR)-integrated fuzzy logic-based control of EVs, incorporating a feedforward term to enhance damping services. A finely tuned AVR in a conventional generation improves synchronizing and damping torque for frequency oscillations. In this work, a modified AVR control loop is designed, combining the battery characteristics with linear controllers to generate additional damping vectors for frequency oscillations. Furthermore, an intelligent rule-based fuzzy logic (FL) controller is developed to replicate the traditional virtual synchronous control, enhancing the overall inertia and damping response. The proposed approach is validated using a modified IEEE 14-bus system under different case studies, such as load changes, EV variability, and integrated system dynamics. The results demonstrate superior performance over conventional droop control, achieving reduction in steady-state error, peak overshoot, and settling time. The comparative analysis validates the robustness and stability of the proposed control technique, marking a significant advancement in ancillary service support.