The dangerous electricity consumption behaviors of enterprises may lead to energy-related safety incidents during the production process, like overloading. To address these risks, the government has increasingly relied on Internet of Things (IoT)-enabled monitoring systems to analyze electricity consumption curves in real-time. The essence of government monitoring electricity consumption behaviors is to conduct a comparative analysis of electricity consumption curves in combination with historical data. However, there are two difficulties in the working process: 1. Clustering based on time-series data is the core of electricity curve analysis, but existing methods are only suitable for clustering discrete data points. 2. It is prone to misjudge behaviors not existing in historical data, lacking of common feature capture for behaviors. Therefore, this paper proposes an IoT-integrated early warning method operated within a multi-layered IoT architecture (perception → network → edge → cloud). First of all, designing a time-series feature capture enhancement module based on Self-Organizing Mapping (SOM) and Hierarchical Clustering algorithm (HCA). The SOM is utilized to capture the features of the power consumption curves, and the capture effect is enhanced through reintegration by HCA. Secondly, constructing a multi-scale feature extraction ensemble fusion framework. Exploring the common features of electricity consumption behavior avoids the situation of misjudgment during the work process. Finally, through the practical application in the regional power grid of a certain area in China, the proposed method achieves an early warning accuracy of 97.99%, which is more than 20% higher than that of the current methods.

With the increasing uncertainty brought by renewable energy sources, it is crucial to price uncertainty and quantify the impact on operation costs. For certain types of uncertainty, such as those following jointly Gaussian distributions, the price of uncertainty has been defined. However, the definition of prices for uncertainties following more general parametric forms of distributions is not clear. To fill the gap, this article proposes a uniform price definition of uncertainties with general parametric distributions and a practical calculation method. First, the price definition for uncertainty is proposed based on the marginal pricing principle, which can be derived from the Lagrangian function of the chance-constrained optimal power flow (CCOPF) problem. Next, the scenario-based method is used to analytically transform CCOPF into a deterministic form. The prices of uncertainties in each scenario can be calculated from the Lagrangian function of the scenario-based model. Then, the relationship between the distribution parameters and the uncertainties in scenarios is revealed. We compute the prices of distribution parameters through the prices of uncertainties in multiple scenarios and their relationship. Finally, this article demonstrates the entire calculation procedure using the correlated non-Gaussian uncertainties as typical examples. The performance of proposed method is verified in the PJM 5-bus, IEEE 30-bus, and 118-bus test systems. It shows that the proposed method can accurately compute the price of uncertainty, ensuring nonnegative market surplus, and keeping the constraint violation probability within the tolerance.

Transfer learning (TL) is a crucial technique to improve the cross-system analysis ability of data-driven transient stability assessment (TSA) approaches. However, existing transfer learning methods for TSA in new scenarios generally depend on a larger number of target samples, and the computational performance is limited by the inconsistency of temporal features in the transfer process. To resolve this issue, this paper proposes a temporal transfer learning framework (TTLF) for TSA, which can effectively improve the performance of cross-system TSA with zero target samples. The TTLF is sequentially composed of two modules. The first module is referred to as source sample characterization (SSC), which aims to better characterize the distribution information of transient time-series curves. The second module is termed temporal distribution matching (TDM), which aims to maximize the interclass dispersion and minimize the intra-class scatter in each hidden layer at each time. What’s more, the framework can also be extended to the situation with a few cross-system samples, which can significantly improve the assessment performance. The simulation results demonstrate the efficiency and scalability of the proposed framework in several utility benchmark systems with different data-driven models.

Data-driven optimal power flow (OPF) approach has been a research focus in recent years. However, the current data-driven OPF approaches face the following difficulties: 1) the data-driven solutions may have large deviations and are not trustable, facing out-of-distribution (OOD) samples and 2) it is hard to judge whether the solutions of the data-driven approach can be trusted. To handle these problems, this article first improves the generalization ability of the data-driven OPF method by embedding the inherent pattern of the OPF solution into the data-driven learning process. As an optimization problem, the OPF solution has certain fixed patterns that are not influenced by the distribution of samples. For example, the load balance constraints should always be satisfied. This leads to an inherent requirement of output vectors, which can be utilized to guide the learning process of the data-driven OPF method. Second, an adaptability judging method based on the decoder neural network is proposed to determine whether the data-driven OPF approach can produce trustable solutions. By measuring the decoding error from latent features to input features, the adaptability of neural networks for input samples could be accurately judged. According to extensive results on various systems, the proposed method can improve the calculation accuracy of OOD data by an average of 30.19% compared with state-of-the-art methods. With the adaptability judgment method, the accuracy of the data-driven approach can achieve higher than 98% for OOD data, whereas the accuracy of other methods ranges from 34.08% to 94.50% on the same set of OOD test data.

Constructing virtual power plants (VPPs) based on cellular base stations (CBSs) can effectively enable the CBSs to participate in power system operations. Then, like VPPs constructed by other distributed resources, it is essential for CBSbased VPPs to conduct self-scheduling at the day-ahead stage. However, the operational flexibility of CBS-based VPPs has yet to be systematically investigated, so the dispatch potential cannot be fully explored. This paper proposes a self-scheduling framework based on the device-level modeling of CBS operational flexibility. Both the DC part and the AC part of CBSs are systematically studied. In the scheduling framework, the backup storage units at the DC part are arranged to utilize the spare capacity to conduct temporal arbitrage while guaranteeing the power supply reliability requirement; the cooling infrastructures at the AC part are dispatched with optimized schemes with temperature prerequisites. The synergy effect improves the scheduling of CBSbased VPPs and reduces operation costs. Case studies validate the proposed framework.

Pre-stack seismic inversion is an effective approach to obtain elastic parameters for reservoir characterization in seismic exploration. However, the difficulty in achieving reliable inversion results in pre-stack seismic inversion remains due to the strong nonlinearity of the problem and the ambiguity of solutions. Deep learning (DL) excels at mapping the complex nonlinear relationship, and thus various DL-based methods have been used in seismic inversion. To address challenges posed by the nonlinearity and ambiguity in seismic inversion, a novel DL-based pre-stack seismic inversion constrained by amplitude versus offset (AVO) attributes is proposed. In this approach, the multitask learning strategy is adopted to construct a deep neural network that allows for the simultaneous processing of multiple related tasks through information shared between tasks. Moreover, the theoretical seismic forward modeling is integrated with the neural network training, enabling semisupervised learning and utilizing unlabeled data. Additionally, To mitigate the ambiguity of solutions, AVO attributes including intercept P and gradient G are introduced as constraints in the neural network training process. Experimental analyses show that the proposed method can obtain superior inversion results on both synthetic and real examples. Compared with other DL-based methods, the mean squared error of the proposed method’s inversion results on examples drops by at least 30%. Besides, the proposed method can effectively improve spatial continuity and preserve more details laterally in the field data example.

The prediction of physical properties for porous medium plays an essential role in geological resource exploration and subsurface exploitation. Deterministic methods based on computational or numerical experiment provide an efficient way to estimate the physical properties of porous medium. However, uncertainty and randomness are common characteristics in the geological system. The variability of physical property in porous medium cannot be explicitly explained by a limited number of models. In this article, we propose an interval estimator-based Bayesian evidential learning (IE-BEL) framework to quantify the uncertainty while predicting physical properties of porous medium at the same time. First, we utilize a stochastic simulation to generate a number of high-quality 3-D models. Second, the morphological characteristics and physical properties are numerically computed as the training data. Third, a combination of machine learning techniques, including eXtreme gradient boosting (XGBoost) and model agnostic prediction interval estimator (MAPIE), is employed to obtain reliable interval predictions with uncertainty quantification. Fourth, a model calibration process is conducted to regulate the physical property predictions. We validate the proposed method by three practical examples, including both artificial and natural porous materials. Compared with the previous method, the IE-BEL framework shows competitive performance in predicting the physical properties of porous medium. The experiment result indicates that the proposed method can address the uncertainty quantification problem associated with physical properties prediction.

Probabilistic analysis tool is important to quantify the impacts of the uncertainties on power system operations. However, the repetitive calculations of power flow are time-consuming. To address this issue, data-driven approaches are proposed but they are not robust to the uncertain injections and varying topology. This article proposes a model-driven graph convolution neural network (MD-GCN) for power flow calculation with high-computational efficiency and good robustness to topology changes. Compared with the basic graph convolution neural network (GCN), the construction of MD-GCN considers the physical connection relationships among different nodes. This is achieved by embedding the linearized power flow model into the layer-wise propagation. Such a structure enhances the interpretability of the network forward propagation. To ensure that enough features are extracted in MD-GCN, a new input feature construction method with multiple neighborhood aggregations and a global pooling layer are developed. This allows us to integrate both global features and neighborhood features, yielding the complete features representation of the system-wide impacts on every single node. Numerical results on the IEEE 30-bus, 57-bus, 118-bus, and 1354-bus systems demonstrate that the proposed method achieves much better performance as compared to other approaches in the presence of uncertain power injections and system topology.

The seismic coherence attribute is one of the most typically used seismic discontinuity feature detection technologies, which is widely used in fault detection, channel boundary characterization, and other occasions. The eigen-structure-based coherence algorithm possesses the property of stability by using the eigenvalues of seismic data’s covariance matrix, but in the algorithm, only the eigenvalues are used to calculate the final coherence value, and the information contained in eigenvectors is ignored. Through analysis, it is found that the elements in the eigenvectors represent the energy differences of seismic traces. By directly measuring the difference of different elements in an eigenvector, the energy differences between different seismic records can be effectively measured. Since the seismic data on both sides of some discontinuous boundaries, such as channel boundaries, principally show amplitude differences, the coherence properties based on eigenvectors can better characterize them. Through theoretical analysis, model testing, and case application, this letter illustrates the reliability of the proposed algorithm.

Fracture networks are omnipresent in unconventional energy reservoirs. The inversion of fractures is of vital importance to oil and gas exploration and production. Most of the existing inversion methods are developed based on homogeneous media theory and rely on a solitary physical descriptor. For instance, one commonly employed single-property inversion approach is the determination of water saturation through the use of the media’s electrical conductivity. With the fast development of multiphysics geological survey, a joint inversion framework that is suitable for anisotropic fractured media is needed. In this article, we propose an electrical–elastic joint inversion method involving both electrical tensor and elastic tensor to invert the fracture characteristics (e.g., fracture shape, inclination angle, and porosity). We conduct numerical experiments with two-phase geometries containing idealized ellipsoidal fractures. The resistivity tensor and Young’s moduli of different directions are calculated and used to construct an anisotropy diagram and a joint inversion chart. The method is validated by comparing the predicted fracture geometry with the actual geometry of the fracture embedded in media. Both ideal homogeneous media and digital rock samples are used to test the inversion framework. A comparison between the single- and the joint-property inversion is also presented, and the joint-property inversion shows a higher accuracy in predicting fracture volume and tilting angle. This work indicates that the proposed electrical–elastic joint method can capture the anisotropy of the formation rock, and the multiphysics inversion framework exhibits the potential to recover fracture features with high fidelity.

In oil and gas exploration, formation water (or hydrocarbon) content estimation is essential for reservoir evaluation, development, and production. Archie’s law, which associates the formation resistivity and water saturation, has been widely adopted for reservoir assessment. However, the accuracy of the scalar-based Archie’s law falls when the formation exhibits strong heterogeneity (e.g., fractured shales), as the electrical anisotropy is neglected in the scalar model. In this letter, we propose a tensorial Archie’s law based on the effective resistivity tensor of the formation. We construct numerical experiments of idealized three-phase formation geometries that contain ellipsoidal inclusions. The resistivity tensor is calculated from the simulation results and used in the newly proposed Archie’s law to calculate the water saturation of the formation, and the model is validated by comparing the predicted saturation with the calculated value from the known geometries. The results show that the tensorial Archie’s law captures the anisotropy of the formation by including all tensor elements of the resistivity, thus improving the predictability.

For the direct current (dc) based scheduling model in market clearing procedure, there exists a clear mismatchbetween dc market solutions and alternating current (ac) feasible operation points. This mismatch is commonly covered by out-of-market corrections, which makes generators deviate from market solutions and consequently incur uplift payments. The enhanced coupling relationship of active power and reactive power makes this issue crucial. However, it has been seldom studied. This article presents the problem formulation of existing industrial practice to handle this mismatch. The physical properties of current practice are discussed in depth. The serious potential disadvantages incurred by current ad-hoc manners in ac feasibility restoration are analyzed and its influence on market results is demonstrated. Theoretical analysis shows that social welfare loss and price spikes will occur under certain circumstances, especially in on-peak load scenarios. To handle these issues, this article presents a modified ac feasibility restoration framework based on the linearized optimal power flow algorithm, which improves the rationality of the reactive power and voltage magnitudes to restore ac feasibility. A strategy to select the additional unit is proposed to avoid price spikes. The proposed method has the potential to reduce the overall operation costs. The effectiveness of the proposed method is verified in IEEE and Polish systems.

Probabilistic power flow (PPF) calculation is an important power system analysis tool considering the increasing uncertainties. However, existing calculation methods cannot simultaneously achieve high precision and fast calculation, which limits the practical application of the PPF. This article designs a specific architecture of the extreme learning machine (ELM) in a model-driven pattern to extract the power flow features and therefore accelerate the calculation of PPF. ELM is selected because of the unique characteristics of fast training and less intervention. The key challenge is that the learning capability of the ELM for extracting complex features is limited compared with deep neural networks. In this article, we use the physical properties of the power flow model to assist the learning process. To reduce the learning complexity of the power flow features, the feature decomposition and nonlinearity reduction method is proposed to extract the features of the power flow model. An enhanced ELM network architecture is designed. An optimization model for the hidden node parameters is established to improve the learning performance. Based on the proposed model-driven ELM architecture, a fast and accurate PPF calculation method is proposed. The simulations on the IEEE 57-bus and Polish 2383-bus systems demonstrate the effectiveness of the proposed method.

In smart grids, the power supply and demand are balanced through the electricity market to promote the maximization of social welfare. An important procedure in electricity market clearing is to sequentially solve the security-constrained economic dispatch (SCED) problem. However, the scale of the SCED problem with all N-1 constraints is huge. Directly optimizing such a problem is inefficient and not robust. With the development of smart grids, the frequency of market clearing is increasing, which presents new requirements for fast calculation of SCED. To solve this problem, we propose an intelligent prescreening method to identify the active constraints of SCED based on deep learning. We utilize stacked denoising autoencoders (SDAEs) to extract the nonlinear relationship between the system operating condition and the active constraint set of SCED. Especially, the input/output feature vectors and learning strategy are designed to improve the training efficiency and guarantee the learning accuracy of the deep neural network (DNN). Besides, a fast tuning strategy of neural network parameters based on transfer learning is proposed to handle new scenarios such as topology change. The computational efficiency of the SCED problem is significantly improved while the accuracy is not influenced. The IEEE 30-bus, IEEE 118-bus, and practical utility 661-bus systems are used to demonstrate the effectiveness of the proposed method.