Energy Informatics最新文献

Integrating power forecasting with wind turbine maintenance planning enables an innovative, data-driven approach that maximizes energy output by predicting periods low wind production and aligning them with maintenance schedules, improving operational efficiency. Recently, many countries have met renewable energy targets, primarily using wind and solar, to promote sustainable growth and reduce emissions. Forecasting wind turbine power production is crucial for maintaining a stable and reliable power grid. As renewable energy integration increases, precise electricity demand forecasting becomes essential at every power system level. This study presents and compares nine machine learning (ML) methods for forecasting, Interpretable ML, Explainable ML, and Blackbox model. The interpretable ML includes Linear Regression (LR), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Random Forest (RF); the explainable ML consists of graphical Neural network (GNN); and the blackbox model includes Multi-layer Perceptron (MLP), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM). These methods are applied to the EDP datasets using three causal variable types: including temporal information, metrological information, and power curtailment information. Computational results show that the GNN-based forecasting model outperforms other benchmark methods regarding power forecasting accuracy. However, when considering computational resources such as memory and processing time, the XGBoost model provides optimal results, offering faster processing and reduced memory usage. Furthermore, we present forecasting results for various time windows and horizons, ranging from 10 minutes to a day.

The reliability of power communication networks is vital to ensure uninterrupted operation in power electronics. Self-healing techniques address this need by automating fault identification and recovery. However, existing methods struggle with dynamic challenges like voltage fluctuations, thermal overloads, and multidimensional sensor data, often leading to delays in fault recovery and reduced safety. This study aims to develop the Self Heal Power Safe Predictor (SHPSP) model to overcome the limitations of prior self-healing techniques. The primary objectives include improving fault prediction accuracy, enhancing recovery speed, and ensuring resilience under diverse and high-stress operational conditions. The SHPSP model employs an ensemble-based classification strategy within a majority voting framework, focusing on multidimensional sensor data such as voltage, temperature, and safety indicators. Feature selection is optimized using ensembled filter and wrapper techniques to prioritize critical parameters. The model is validated against conventional methods using metrics like accuracy, precision, recall, F1-score, and MCC. Experimental results demonstrate that the SHPSP model significantly outperforms previous approaches, achieving higher fault detection accuracy and faster recovery, particularly during voltage drops, power surges, and thermal stress. The SHPSP classifier obtained 91.4% accuracy, 88.2% precision, 89.5% recall, 89.8% F1-score, 81.0% MCC, and a 92.0% ROC-AUC curve. The SHPSP model ensures enhanced safety, dependability, and robustness for power electronics systems, marking a significant advancement in self-healing technology.

The highly integrated source-grid-load-storage energy system has received increasing attention in energy transformation strategies. However, the current static network isomorphism algorithm for distributed machine learning cannot meet the energy exchange needs of the integrated energy system. To better solve the energy loss problem caused by energy trading in the power system, prevent the clean energy loss, and ensure the stable operation of the power system, a distributed dynamic network heterogeneous algorithm is designed on the basis of distributed machine learning. The proposed method uses a dynamic network to balance communication load among servers while solving the hidden state vector errors that cannot be corrected timely due to static network isomorphism. Compared with other methods with a sensitivity of 25%, the sensitivity level of the improved algorithm was above 75%. When the accuracy of other algorithms was 50%, the improved algorithm was above 80%. In the application experiment, the temperature reached 50℃ with the increase of the power. The humidity value always remained above 20. Therefore, the proposed algorithm has superior performance and good application effects, providing new ideas for energy trading in source-grid-load-storage energy systems.

This study presents a distributed electricity trading system using smart contracts to improve transaction efficiency and reduce costs in power markets. Three trading models are analyzed: centralized trading, blockchain-based decentralized trading, and smart contract-driven automated trading. The advantages and challenges of each model are examined, focusing on factors like node inclusion time, transaction costs, and price stability. The results show that the smart contract-driven model outperforms the others by increasing market efficiency, lowering transaction costs, and reducing price fluctuations. Through simulations and real-world analysis, this study provides support for using blockchain technology in power markets and offers practical advice for improving electricity trading systems. The findings suggest that the proposed system could greatly enhance transparency, efficiency, and cost-effectiveness in distributed energy markets, even in uncertain market conditions.

In the context of global climate change and sustainable development, enterprise digital transformation has become key to improving efficiency and competitiveness. Digital twin technology, as an emerging tool, enables real-time monitoring, prediction, and optimization by creating dynamic virtual models of real-world processes. This paper explores the impact of digital twin-based transformation on renewable energy investment decisions. Through empirical analysis of over 200 companies globally, the study finds that companies using digital twin technology exhibit higher accuracy and efficiency in renewable energy investment decisions. These companies show improved forecasting of energy consumption and investment returns, gaining a competitive edge. On average, these companies experience a 15% ROI increase for their renewable energy investments and enjoy a 20% acceleration in the decision-making process. Furthermore, the study delves into how the adoption of digital twin technology differs across various company sizes and industries, providing actionable insights and guidance for enterprises embarking on their digital transformation journey.

It is necessary to establish a sufficiently advanced Battery Management System (BMS) for safe driving of electric vehicles. Lithium-ion batteries have been widely used in electric vehicles due to their advantages of high specific energy and low-temperature resistance, so this paper takes lithium-ion batteries as the research object. BMS can monitor various status information of lithium-ion batteries in real-time, and the State of Charge (SOC) of lithium-ion batteries is a key parameter among them. Accurate SOC estimation is crucial for ensuring the safety and reliability of energy storage applications and new energy vehicles. However, the value of SOC cannot be directly measured. In order to more accurately estimate the SOC, this paper proposes a prediction method that combines an immune genetic algorithm, gated recurrent unit, and multi-head attention mechanism (MHA), using battery experimental data from the University of Maryland as the dataset. Compared with the traditional parameter optimization approach, this paper uses the immune genetic algorithm to find the optimal hyperparameters of the model, which on the one hand has a wider choice of parameters, and on the other hand has been improved for the genetic algorithm is easy to fall into the local optimal solution, so as to improve the SOC estimation accuracy of the GRU model. The model also incorporates a multi-attention mechanism to capture different levels of information, which enhances the expressive power of the model. The data preprocessing part adopts the sliding window technique, through which the original time series data is converted into several different training samples when training the machine learning model, as a way to increase the diversity of the dataset and improve the robustness of the model. Finally, the prediction performance of the fusion model proposed in this paper is verified by Pycharm simulation, and the average absolute error, root mean square error and maximum prediction error of the model are 1.62%, 1.55% and 0.5%, respectively, which proves that the model can accurately predict the SOC of lithium-ion battery. It is shown that the model can significantly improve the accuracy and robustness of SOC estimation, enhance the intelligence, real-time and interpretability of the battery management system, and bring a more efficient, safe and long-lasting battery management solution to the fields of electric vehicles and energy storage systems.

To improve the intelligent adjustment ability and energy consumption prediction accuracy of the fresh air system in hospital buildings, this study constructs an energy consumption prediction model based on the Back Propagation Neural Network (BPNN). Meanwhile, it introduces the Genetic Algorithm (GA) and Fuzzy Logic Algorithm (FLA) to optimize the BPNN, thus enhancing the model’s global search ability and robustness. By comparing the proposed optimized model with other models, the study analyzes the advantages of the proposed model in terms of prediction accuracy and convergence speed. Moreover, its practical effectiveness in energy consumption and operational cost optimization is evaluated. The results show that the Genetic Algorithm-Fuzzy Logic Algorithm-Back Propagation (GA-FLA-BP) algorithm performs the best in load prediction, with prediction errors typically below 1.5%, particularly on the 5th and 18th days, demonstrating exceptional performance. Compared to the GA-BP and FLA-BP models, the GA-FLA-BP algorithm exhibits stronger capabilities in handling complex data and uncertainty. Regarding energy consumption and electricity cost optimization, GA-FLA-BP also outperforms other models. Its energy consumption prediction accuracy is 91.5% and an electricity cost prediction accuracy is 90.8%, resulting in savings of 29.2% in energy consumption and 31.2% in costs. Although other algorithms show improvements, GA-FLA-BP remains significantly ahead. Furthermore, the GA-FLA-BP algorithm excels in robustness, consistency, time complexity, and real-time performance. This algorithm demonstrates the highest stability and consistency, the fastest processing speed, and the shortest response time, proving its superior performance in energy consumption management and cost optimization. This study enhances the intelligent adjustment capability of the fresh air system in hospital buildings by optimizing the energy consumption prediction model. Therefore, the study significantly reduces energy consumption and operational costs, improving the efficiency and economy of energy management.

The new power system puts forward higher requirements for the functionality, real-time performance and reliability of relay protection equipment. Therefore, this paper designs a monitoring platform for the operation of relay protection equipment at distribution network side under the background of new power system. The platform obtains the running state of relay protection equipment by establishing simulation models of different types of relay protection equipment on the distribution network side. The fault time, fault type and current action of relay protection equipment at distribution network side are analyzed to realize the monitoring of operation state. At the same time, the visual representation method of monitoring data based on three-dimensional parallel scattergram and human-computer interaction is adopted for human-computer interaction, and the electromechanical protection device is controlled to realize current quick-break protection and overcurrent protection. The experimental results show that the platform can effectively monitor the operation of relay protection equipment on the distribution network side in real time and accurately judge the action of the equipment, and the application effect is good.

Green finance plays a pivotal role in advancing sustainable urban development by enhancing energy efficiency and supporting low-carbon transitions. This study empirically demonstrates that green finance maturity (GFM), which reflects the development and effectiveness of green financial systems, has a significant positive impact on urban energy efficiency (UEE). Using panel data from Chinese prefecture-level cities spanning 2006 to 2021, the analysis shows that a one-unit increase in GFM improves UEE by 0.221 standard deviations. Mechanism analysis reveals that this effect is primarily mediated through technological advancements and improvements in innovation capacity. Further heterogeneity analysis highlights that GFM’s impact is more pronounced in non-resource-based cities and in regions characterized by advanced financial systems, greater global market integration, and higher levels of urbanization. These findings offer valuable, context-specific insights for policymakers seeking to leverage green finance maturity as a tool to promote sustainable urban development across diverse socio-economic and institutional settings.