Historical Operation Data Research Articles

Investigation of hybrid modeling and its transferability in building load prediction used for district heating systems

In the district heating systems, the historical operation data of the buildings in those areas would be partially or entirely missing. The traditional data-driven model is hard to predict the ground truth results because the historical data is not available for model training. However, utilizing the physics-based methods for load calculation takes a long time to process and encounters low accuracy issues. This paper investigates several hybrid models that integrate the data-driven model and the physics-based models with different fusion methods. The physics-based models calculate envelope load and infiltration load, based on Fourier's law and the grand canonical ensemble theory, respectively. After undergoing load processing, features fusion, and residual connection, the best advanced hybrid models generate 21.35%, 16.35%, and 12.73% better prediction results compared with the data-driven model. Moreover, the advanced hybride models also perform strong transferability across all the data quantity groups. In terms of practical application, the advanced hybrid models could be deployed with effective generalization in limited data scenarios and robust transfer capabilities. The selected best model constructed by hybrid modeling displays the highest performance and saves the total training costs with strong transferability.

A distributed photovoltaic short-term power forecasting model based on lightweight AI for edge computing

Abstract In recent years, an immense amount of distributed photovoltaics are integrated into low-voltage distribution network, producing a substantial volume of operational data. The centralized cloud data center cannot process massive amounts of data precisely and promptly. Therefore, the operational status of distributed photovoltaic systems in low-voltage distribution network becomes difficult to predict. However, edge computing in the distribution network enables local data processing to improve the forecasting service’s real-time reliability. In this regard, this paper proposes a distributed photovoltaic short-term power forecasting model based on lightweight AI algorithms. Firstly, based on the Pearson correlation coefficient method, an analysis is conducted on the historical operational data in the network to extract important meteorological features correlated with the photovoltaic power output. Secondly, a distributed photovoltaic power forecasting model for the distribution network is constructed based on the Xception and attention mechanism. Finally, the model is trained using pruning, which removes redundant parts of the model, resulting in a compact and efficient forecasting model. By validating real-world datasets, the results demonstrate that the model presented in this article has a smaller size and higher forecasting accuracy than other state-of-the-art forecasting models.

Power flow distribution identification via machine learning algorithm and distributed resource clearing method

Abstract Under the background of dual carbon, a large number of distributed new energy sources are connected to the demand side, which leads to great risks in the operation of the power system. As an effective solution, distributed power transaction still has problems, such as high clearing time, unknown low-voltage distribution network structure, and resource scheduling ignoring user needs. Therefore, this paper proposes an optimal regulation method of demand-side resources based on distributed transactions. Based on the historical operation data of the distribution network, the eXtreme Gradient Boosting (XGBoost) algorithm is used to study the relationship between node injection power, node voltage, and node-side line power flow. It is also used to check the results of distributed transactions and design a market mechanism for rapid clearing and settlement of distributed transactions. The results of an example show that the identification of power flow distribution in a distribution network based on reinforcement learning can meet the security check requirements of distributed transaction results.

Maritime Supply Chain Optimisation: A Case Study of Blockchain Integration in Port Logistics Management

This research examines the potential for maritime supply chain optimisation through the integration of blockchain technology in port logistics management. In the era of global digitalisation, the maritime sector faces challenges to improve operational efficiency and transparency. This study uses a case study approach to evaluate the implementation of blockchain in one of Indonesia's major ports. The research methodology involved qualitative and quantitative analyses, including interviews with key stakeholders, direct observation of logistics processes, and analysis of historical port operational data. The blockchain system was implemented over a six-month period, and its performance was compared with conventional logistics management systems. Key challenges identified include the need for a large initial investment, resistance to change from some stakeholders, and the need for industry-wide standardisation of blockchain protocols. This research demonstrates the great potential of blockchain technology in optimising maritime supply chains. Recommendations for further implementation and future research are discussed, with an emphasis on the importance of industry collaboration and regulatory support to accelerate the adoption of this technology in the maritime sector.

A distributed photovoltaic short‐term power forecasting model based on lightweight AI for edge computing in low‐voltage distribution network

AbstractRecent years, the tremendous number of distributed photovoltaic are integrated into low‐voltage distribution network, generating a significant amount of operational data. The centralized cloud data centre is unable to process the massive data precisely and promptly. Therefore, the operational status of distributed photovoltaic systems in low‐voltage distribution network becomes difficult to predict. However, edge computing in the distribution network enable local processing of data to improve the real‐time and reliability of the forecasting service. In this regard, this paper proposes a distributed photovoltaic short‐term power forecasting model based on lightweight AI algorithms. Firstly, based on the Pearson correlation coefficient method, an analysis is conducted on the historical operational data in the network to extract important meteorological features that are correlated with the photovoltaic power output. Secondly, a distributed photovoltaic power forecasting model for the distribution network is constructed based on the Xception and attention mechanism. Finally, the model is trained using pruning, which involves removing redundant parts of the model, resulting in a compact and efficient forecasting model. By conducting validation on real‐world datasets, the results demonstrate that the model presented in this article possesses a smaller size and higher forecasting accuracy compared to other state‐of‐the‐art forecasting models.

A method for measuring carbon emissions from power plants using a CNN-LSTM-Attention model with Bayesian optimization

Accurate measurement of CO2 emissions from coal-fired power plants is crucial for achieving China's “carbon neutrality” goal; however, traditional CO2 emission measurement methods have several limitations, and emerging prediction models rarely utilize real-time monitoring data from power plants at the micro level. To address these challenges, this study presents a novel hybrid convolutional neural network with long short-term memory (CNN-LSTM)-Attention model, leveraging real-time monitoring data to enhance the accuracy of CO2 emission predictions. The proposed model employs a hybrid architecture that leverages the strength of CNN, LSTM, and Attention mechanism. To address the challenges of multiple hyperparameters and difficult selection, the Bayesian optimization algorithm is used to optimize the hyperparameters ensuring optimal performance. Using historical operational data from a 660 MW generator set in Hubei province, the proposed model was evaluated and validated horizontally by using three evaluation metrics. Additionally, the vertical evaluation and validation of the proposed model were done using the operational data from other months. The results indicate that the proposed model achieved the highest performance across every evaluation index for predicting CO2 emissions from coalfired power plants, and the prediction accuracy of the CO2 emission in the future months is also guaranteed.

The role of hydropower in decarbonisation scenarios

An increased penetration of renewable energy sources is essential for the energy transition. A major role will be played by wind and solar, as they are widely available. Hydropower is another crucial resource, currently covering large shares of power generation (e.g., Norway, Italy, Brazil). Despite little expected growth, in a context of increasing electrification, improved integration of hydropower can play a critical role thanks to programmable operation. This work addresses the modelling of hydropower flexibility in energy system models and analyses the impact of hydropower operation on CO2 emission-constrained scenarios. To implement the study, a detailed dataset of the Italian programmable hydroelectric plants is created, using open-source information, covering location, rated power, and storage capacity. Inflow timeseries are derived from historical operational data. These new sets of data are employed in OMNI-ES (a multi-node, multi-sector, and multi-vector energy system model) to study optimal configurations and operation of the Italian energy system in decarbonisation scenarios, such as net-zero-CO2 and Fit-for-55 targets. Considering different operational strategies and multiple historical reference years (impacting the inflow), results demonstrate significant changes in hydropower behaviour and highlight its relevance as zero-carbon resource in terms of both power and energy output, influencing the installation of other technologies.

Research on priority scheduling strategy for smoothing power fluctuations of microgrid tie‐lines based on PER‐DDPG algorithm

AbstractThe variability of renewable energy within microgrids (MGs) necessitates the smoothing of power fluctuations through the effective scheduling of internal power equipment. Otherwise, significant power variations on the tie‐line connecting the MG to the main power grid could occur. This study introduces an innovative scheduling strategy that utilizes a data‐driven approach, employing a deep reinforcement learning algorithm to achieve this smoothing effect. The strategy prioritizes the scheduling of MG's internal power devices, taking into account the stochastic charging patterns of electric vehicles. The scheduling optimization model is initially described as a Markov decision process with the goal of minimizing power fluctuations on the interconnection lines and operational costs of the MG. Subsequently, after preprocessing the historical operational data of the MG, an enhanced scheduling strategy is developed through a neural network learning process. Finally, the results from four scheduling scenarios demonstrate the significant impact of the proposed strategy. Comparisons of reward curves before and after data preprocessing underscore its importance. In contrast to optimization results from deep deterministic policy gradient, soft actor‐critic, and particle swarm optimization algorithms, the superiority of the deep deterministic policy gradient algorithm with the addition of a priority experience replay mechanism is highlighted.

Prediction of Hard Drive Failure using Machine Learning

The reliability of hard drives is paramount for maintaining data integrity and availability in cloud services and enterprise-level data centers where unexpected failures significantly impact operational efficiency and general performance. This work aims to develop a predictive model using regression analysis to accurately forecast imminent hard drive failures based on historical operational data, specifically SMART (Self-Monitoring Analysis and Reporting Technology) attributes. The study evaluated various regression models which comprises Decision Tree, Random Forest, Support Vector Machine (SVM), Gradient Boosting, and Neural Network. The outcomes indicated that the Random Forest model, with an MSE of 24.7427 and an R2 of 0.9876 and the Neural Network model, with an MSE of 22.6011 and an R2of 0.7442, as the best performing models as they demonstrated high predictive accuracy and robustness. In contrast, the SVM model showed poor performance with an MSE of 2888.8623 and a negative R2of -0.4465. Based on these outcomes, the Random Forest and Neural Network models are recommended for predicting hard drive failures as they delivered a balance of accuracy and interpretability.

Anomaly Detection for Charging Voltage Profiles in Battery Cells in an Energy Storage Station Based on Robust Principal Component Analysis

Lithium-ion batteries, with their high energy density, long cycle life, and non-polluting advantages, are widely used in energy storage stations. Connecting lithium batteries in series to form a battery pack can achieve the required capacity and voltage. However, as the batteries are used for extended periods, some individual cells in the battery pack may experience abnormal failures, affecting the performance and safety of the battery pack. At the same time, as batteries operate in complex environments, the data collected by sensors are susceptible to random noise and drift interference, which can affect the accuracy of anomaly detection in individual battery cells. In order to solve this problem, this article proposes an anomaly detection method for battery cells based on Robust Principal Component Analysis (RPCA), taking the historical operation and maintenance data of a large-scale battery pack from an energy storage station as the research subject. Firstly, theRPCA is used to denoise the observed voltage data of the battery cells to an extreme degree, obtaining a baseline charging state curve for a cell consistency assessment. This also solves the problem of sensor outputs being affected by random noise. To further detect and identify abnormal battery cells, the RPCA is used to extract outlier components. Based on the Average Deviation-3σ principle and by utilizing Gaussian distribution probability characteristics, battery cells are conducted to screen, and the serial numbers of the anomaly cells are obtained. Finally, the effectiveness and accuracy of this anomaly detection method for battery cells are compared and verified through different statistical distributions.

State Evaluation of Electrical Equipment in Substations Based on Data Mining

This paper explores the combination of a data mining-based state evaluation method for electrical equipment in substations, analyzing the effectiveness and accuracy. First, a Gaussian mixture model is applied to fit all raw data of electrical equipment. The Expectation Maximization algorithm summarizes the data distribution characteristics and identifies outliers. The a priori algorithm is then employed for data mining to derive frequent itemsets and association rules between equipment quality and measurement data. For new equipment samples, conditional probabilities of each feature are independently calculated and combined to classify and evaluate equipment quality. The results suggest that equipment reliability in smart substations can be inferred from historical and real-time operational data using improved association rule algorithms and Naive Bayes classifiers. Finally, the proposed method was applied to analyze statistical data from a 110 kV substation of a power supply company. The states prediction accuracy exceeded 95% when compared with actual equipment quality. The effectiveness evaluation metrics demonstrated that this method outperforms single-category algorithms in terms of accuracy and discrimination ability.

Model predictive control of switched nonlinear systems using online machine learning

This work introduces an online learning-based model predictive control (MPC) approach for the modeling and control of switched nonlinear systems with scheduled mode transitions. Initially, recurrent neural network (RNN) models are constructed offline, utilizing sufficient historical operational data to capture the nominal system dynamics for each mode. Subsequently, we employ real-time process data to develop online learning RNN models, aiming to approximate the dynamics of switched nonlinear systems in the presence of of bounded disturbances. In cases where the initial RNN model is unavailable for a specific switching mode due to very limited historical data, we use real-time data from closed-loop operations under a proportional–integral (PI) controller to build online learning RNN models. To evaluate the predictive performance of online learning RNNs, a theoretical analysis on their generalization error bound is developed using statistical machine learning theory. Additionally, considering the presence or absence of initial RNN models, two MPC schemes are developed. These schemes employ RNNs as prediction models to stabilize switched nonlinear systems, ensuring closed-loop stability by accounting for the generalization error bound derived for online learning RNNs. Finally, the effectiveness of the proposed MPC schemes is demonstrated through a nonlinear process example with two switching modes.

Machine Learning for Predictive Maintenance to Enhance Energy Efficiency in Industrial Operations

In the realm of industrial operations, optimizing energy usage is critical for both economic and environmental sustainability. Traditional approaches to maintenance often rely on fixed schedules or reactive responses to equipment failures, leading to inefficiencies and higher energy consumption. Predictive maintenance (PdM) offers a proactive solution by leveraging machine learning algorithms to predict equipment failures before they occur. This approach not only reduces downtime but also facilitates energy-efficient practices by enabling timely interventions and optimized operational strategies. This study explores the application of machine learning techniques for predictive maintenance in a manufacturing setting. Historical operational data, including equipment performance metrics and environmental conditions, are collected and preprocessed. Various machine learning models, such as support vector machines (SVM), random forests, and neural networks, are trained on this dataset to predict equipment failures and maintenance needs. Feature engineering and model selection processes are detailed to highlight the steps taken to enhance prediction accuracy and reliability. Through rigorous experimentation and validation, our approach demonstrates significant improvements in energy efficiency within industrial operations. By predicting maintenance needs in advance, downtime is minimized, and energy-intensive emergency repairs are avoided. Furthermore, the implementation of optimized maintenance schedules and operational strategies based on machine learning predictions leads to substantial reductions in overall energy consumption. Case studies and quantitative analyses underscore the efficacy of our methodology in enhancing both operational efficiency and energy sustainability in industrial settings.

Research on maintenance cycle prediction for energy equipment with limited and sensitive data

Failures in natural gas compressor units can lead to significant production incidents that impact energy security, making intelligent preventative maintenance of this equipment critically important. Given the limited and sensitive data from critical energy equipment like natural gas compressor units, this paper conducts preventative maintenance research based on domain adaptation and federated learning (DFPM), and proposes a novel maintenance cycle prediction framework. The feasibility of the proposed method was validated through historical operational data from field natural gas compressor units, providing a data-oriented reference for maintenance decision-making. Verification results demonstrate that the proposed multi-level adversarial domain adaptation method possesses superior feature representation capability, enhancing the preservation of the original degradation trend for time series data compared to traditional DA models. The novel federated adversarial strategy presented in this paper can effectively transfer source domain knowledge to the target domain, further enhancing the cross-unit predictive performance of the target domain model with limited samples. Additionally, this strategy with the chaotic multi-mode predictive model further improves the limitations of low parallelism and efficiency in traditional RNN-based prediction models while ensuring data security. This research provides a new perspective for the intelligent operation and maintenance of large energy equipment, which is of significance in practical engineering.

Data based digital twin for operational performance optimization in CFB boilers

The benchmarks of controllable variables for circulating fluidized bed (CFB) boilers with small capacity dependencies on operator experience result in boiler efficiency penalties, increased energy consumption, and performance degradation. This study proposes a digital twin (DT) for a CFB boiler based on data-driven methods to determine the benchmarks of controllable variables by mining historical operating data to save energy, with a coefficient, Cm, proposed for the online evaluation of boiler performance. A hybrid data-driven model integrating kernel density estimation and the K-means++ algorithm was proposed to optimize boiler performance for different coal types, with Cm set as the clustering objective to determine the benchmarks of controllable variables from an operator's perspective. In addition, a classification model adopting an extreme gradient boosting algorithm was presented to identify the coal type online. The proposed DT was applied to an on-duty 150 t/h CFB boiler. The results showed that the proposed DT could identify coal types online with an accuracy of no lower than 94.8 %. Moreover, after the industrial commission of DT, the boiler efficiency increased from 84.41 % to 85.96 % on average, the energy savings reached 151.01 GJ, while steam production increased 59,998 kg over three days, thus highlighting that the proposed benchmarks for controllable variables help enhance the performance of CFB boilers.

A hierarchical framework for minimising emissions in hybrid gas-renewable energy systems under forecast uncertainty

Developing and deploying renewables in existing energy systems are pivotal in Europe’s transition to net-zero emissions. In this transition, gas turbines (GTs) will be central for balancing purposes. However, a significant hurdle in minimising emissions of GTs operating in combination with intermittent renewables arises from the reliance on unreliable meteorological forecasts. Here, we propose a hierarchical framework for decoupling this operational problem into a balancing and emissions minimisation problem. Balancing is ensured with a high-level stochastic balancing filter (SBF) based on data-driven stochastic grey-box models for the uncertain intermittent renewable. The filter utilises probabilistic forecasting and less conservative chance constraints to compute safe bounds, within which a proposed low-level economic predictive controller further minimises emissions of the GTs during operations. As GTs exhibit semi-continuous operating regions, complementarity constraints are utilised to fully exploit each GT’s allowed operational range. The proposed method is validated in simulation for a gas-balanced hybrid renewable system with batteries, three GTs with varying capacities, and a wind farm. Using real historical operational wind data, our simulation shows that the proposed framework balances the energy demand and minimises emissions with up to 4.35% compared with other conventional control strategies in simulation by minimising the GT emissions directly with complementarity constraints in the low-level controller and indirectly with less conservative chance constraints in the high-level filter. The simulations show that the computational cost of the proposed framework is well within requirements for real-time applications. Thus, the proposed operational framework enables increased renewable share in hybrid energy systems with GTs and renewable energy and subsequently contributes to de-carbonising these types of isolated or grid-connected systems onshore and offshore.

Control-oriented dynamic modeling and GPC for single-tower double-circulation wet flue gas desulfurization system

In China, the current situation of large-scale grid integration of renewable energy generation and the government's introduction of capacity-based electricity pricing policies have compelled coal-fired power plants to gradually enhance their load adjustment capabilities and expand their load adjustment ranges. Simultaneously, the national environmental requirements for these plants have become increasingly stringent. However, the economic control of wet flue gas desulfurization (WFGD) systems is still far from meeting practical requirements. In this paper, starting from practical engineering applications and utilizing historical operational data, considering the actual system operation process, the impact of the absorption tower variable-frequency slurry circulation pump on the concentration of sulfur dioxide (SO2) in flue gas under different slurry pH values is investigated. This led to the establishment of a dynamic model for a single-tower double-circulation wet flue gas desulfurization (SD-WFGD) system. Recognizing the significant delay and inertia characteristics of pH value control in the SO2 absorption tank, a desulfurization system pH value desulfurization capacity-based optimization control scheme for the SD-WFGD system is proposed, termed as the Direct Sulfur Control (DSC) strategy. Based on the established dynamic model, a SD-WFGD system series control system is developed using a step generalized predictive control algorithm (GPC) combined with the DSC strategy. Validation results indicate that, compared to SGPC control schemes and traditional PID control schemes, this approach reduces fluctuations in slurry supply and outlet SO2 concentration, significantly enhancing the control performance of the SD-WFGD system. This ensures the safe, stable, economical, and flexible operation of the desulfurization system against the backdrop of flexible operation in coal-fired power plants.

A Comparative Analysis of Machine Learning Algorithms in Predicting the Performance of a Combined Radiant Floor and Fan Coil Cooling System

Machine learning algorithms have proven to be practical in a wide range of applications. Many studies have been conducted on the operational energy consumption and thermal comfort of radiant floor systems. This paper conducts a case study in a self-designed experimental setup that combines radiant floor and fan coil cooling (RFCFC) and develops a data monitoring system as a source of historical operational data. Seven machine learning algorithms (extreme learning machine (ELM), convolutional neural network (CNN), genetic algorithm-back propagation (GA-BP), radial basis function (RBF), random forest (RF), support vector machine (SVM), and long short-term memory (LSTM)) were employed to predict the behavior of the RFCFC system. Corresponding prediction models were then developed to evaluate operative temperature (Top) and energy consumption (Eh). The performance of the model was evaluated using five error metrics. The obtained results showed that the RF model had very high performance in predicting Top and Eh, with high correlation coefficients (>0.9915) and low error metrics. Compared with other models, it also demonstrated high accuracy in Eh prediction, yielding maximum reductions of 68.1, 82.4, and 43.2% in the mean absolute percentage error (MAPE), mean squared error (MSE), and mean absolute error (MAE), respectively. A sensitivity ranking algorithm analysis was also conducted. The obtained results demonstrated the importance of adjusting parameters, such as the radiant floor supply water temperature, to enhance the indoor comfort. This study provides a novel and effective method for evaluating the energy efficiency and thermal comfort of radiant cooling systems. It also provides insights for optimizing the efficiency and thermal comfort of RFCFC systems, and lays a theoretical foundation for future studies integrating machine learning algorithms in this field.

Real-time multi-risk assessment of large scale power system with high-penetration renewable energy

Abstract To accurately assess the impact of real-time uncertainty of high penetration renewable energy sources on the real-time operation of large-scale power systems, this study proposes an innovative method for real-time multi-risk assessment in power systems. Firstly, by utilizing an improved spectral clustering algorithm and mixture density network to analyze historical operational data, effective clustering of different renewable energy generation curves and accurate fitting of prediction errors were achieved. Next, random sampling was performed from the probability density curves of prediction errors to obtain real-time renewable energy outputs. At the same time, a non-sequential Monte Carlo method was used to incorporate interruptions for each component into the scenario simulation. Subsequently, a state assessment was conducted for each sampled scenario by minimizing load shedding and energy curtailment. On this basis, risk indices that comprehensively consider the real-time flexibility of the system and power supply-demand imbalances were established. Finally, validation in a test system verified the accuracy and speed of the proposed multi-risk assessment method.

Long-short term memory networks aided fault detection of power facilities

In recent years, long-short term memory (LSTM) networks have emerged as a promising tool for time-series analysis, offering the ability to capture temporal dependencies effectively, especially for the fault detection in power facilities which is crucial for maintaining operational integrity and ensuring continuous power supply. This paper presents a study on the utilization of LSTM networks for fault detection in power facilities, focusing on evaluating the detection accuracy as a performance metric. We propose a novel LSTM-based fault detection framework that utilizes historical operational data to identify abnormal patterns indicative of faults or anomalies. The framework is trained on labeled data to learn the normal operational behavior of the power facility, enabling it to detect deviations from expected patterns in practical data streams. To assess the effectiveness of the proposed approach, extensive experiments are conducted using real-world operational data from diverse power facilities. We systematically evaluate the detection accuracy of the LSTM-based fault detection system under various operating conditions, including different types of faults and levels of noise in the data. Comparative analyses are performed against traditional fault detection methods to demonstrate the superiority of the LSTM-based approach in terms of accuracy. Moreover, sensitivity analyses are conducted to investigate the impact of key parameters, such as network architecture and training data size, on the detection performance. The results illustrate the robustness and effectiveness of the proposed LSTM-based fault detection framework, highlighting its potential for enhancing the reliability and efficiency of power facility operations.