arXiv subjects

Zhijian Jin

Publications and source records attributed to Zhijian Jin.

8 recordsLinked to original sources

arXiv2025

Marginalize, Rather than Impute: Probabilistic Wind Power Forecasting with Incomplete Data

Machine learning methods are widely and successfully used for probabilistic wind power forecasting, yet the pervasive issue of missing values (e.g., due to sensor faults or communication outages) has received limited attention. The prevailing practice is impute-then-predict, but conditioning on point imputations biases parameter estimates and fails to propagate uncertainty from missing features. Our approach treats missing features and forecast targets uniformly: we learn a joint generative model of features and targets from incomplete data and, at operational deployment, condition on the observed features and marginalize the unobserved ones to produce forecasts. This imputation-free procedure avoids error introduced by imputation and preserves uncertainty aroused from missing features. In experiments, it improves forecast quality in terms of continuous ranked probability score relative to impute-then-predict baselines while incurring substantially lower computational cost than common alternatives.

cs.LG↗

arXiv2022

Wind energy forecasting with missing values within a fully conditional specification framework

Wind power forecasting is essential to power system operation and electricity markets. As abundant data became available thanks to the deployment of measurement infrastructures and the democratization of meteorological modelling, extensive data-driven approaches have been developed within both point and probabilistic forecasting frameworks. These models usually assume that the dataset at hand is complete and overlook missing value issues that often occur in practice. In contrast to that common approach, we rigorously consider here the wind power forecasting problem in the presence of missing values, by jointly accommodating imputation and forecasting tasks. Our approach allows inferring the joint distribution of input features and target variables at the model estimation stage based on incomplete observations only. We place emphasis on a fully conditional specification method owing to its desirable properties, e.g., being assumption-free when it comes to these joint distributions. Then, at the operational forecasting stage, with available features at hand, one can issue forecasts by implicitly imputing all missing entries. The approach is applicable to both point and probabilistic forecasting, while yielding competitive forecast quality within both simulation and real-world case studies. It confirms that by using a powerful universal imputation method like fully conditional specification, the proposed approach is superior to the common approach, especially in the context of probabilistic forecasting.

stat.AP↗

arXiv2022

Continuous and Distribution-free Probabilistic Wind Power Forecasting: A Conditional Normalizing Flow Approach

We present a data-driven approach for probabilistic wind power forecasting based on conditional normalizing flow (CNF). In contrast with the existing, this approach is distribution-free (as for non-parametric and quantile-based approaches) and can directly yield continuous probability densities, hence avoiding quantile crossing. It relies on a base distribution and a set of bijective mappings. Both the shape parameters of the base distribution and the bijective mappings are approximated with neural networks. Spline-based conditional normalizing flow is considered owing to its non-affine characteristics. Over the training phase, the model sequentially maps input examples onto samples of base distribution, given the conditional contexts, where parameters are estimated through maximum likelihood. To issue probabilistic forecasts, one eventually maps samples of the base distribution into samples of a desired distribution. Case studies based on open datasets validate the effectiveness of the proposed model, and allows us to discuss its advantages and caveats with respect to the state of the art.

eess.SY↗

arXiv2021

Algebraic Analysis of Electric Load and Electricity Pricing

This paper presents a perspective of functional analysis to analyze electric load and electricity pricing in the $L_2$ space and its isomorphic vector space, which also yields the general algebraic model of load and pricing associated with time course. It clarifies law of interaction between payment and load associated with time course and necessity of pricing to sufficiently convey information on how load results in supply cost. It describes classic paradigm of modeling in a general algebraic form and formally proves the ineffectiveness of classic integral-based pricing in modeling. It consequently introduces to: describe electricity supply cost by a mapping defined on an isomorphic space of the original space of load constituted by orthonormal basis that quantifies the dynamism of load, named the space of dynamism; a pricing model defined on the space of dynamism that sufficiently conveys the information; a further derived computational model of pricing based on the Fourier series; simple examples to demonstrate use of the proposed pricing and its effectiveness in distinguishing loads and reflecting supply cost associated with time course, which theoretically completes the incentive to reshape loads.

math.OC↗

arXiv2020

Behaviour Prediction of Closed-loop HTS coils in Non-Uniform AC fields

Field decay rate is the key characteristic of the superconducting magnets based on closed-loop coils. However, in Maglev trains or rotating machines, closed-loop magnets work in external AC fields and will exhibit an evidently accelerated field decay resulting from dynamic resistances, which are usually much larger than joint resistance. Nevertheless, there has not been a numerical model capable of systematically studying this behaviour, which is the main topic of this work. The field decay curves of a closed-loop high-temperature-superconducting (HTS) coil in various AC fields are simulated based on H-formulation. A non-uniform external field generated by armature coils is considered. Reasonable consistence is found between experimental and simulation results. In our numerical model, the impact of current relaxation, which is a historical challenge, is analysed and subsequently eliminated with acceptable precision. Our simulation results suggest that most proportion of the field decay rate is from the innermost and outermost turns. Based on this observation, a magnetic shielding pattern is designed to reduce the field decay rate efficiently. This work has provided magnet designers an effective method to predict the field decay rate of closed-loop HTS coils in external AC fields, and explore various shielding designs.

physics.app-ph↗

arXiv2020

Dimensional Pricing Based on Dynamism of Load

Electricity supply is not simply a matter of quantity, but a time lasting service that matches with a wave-like load curve. It logically deserves a pricing based on the curve per se rather than simply integral of load. This paper introduces to price electricity consumption based on dynamism of load, which is an equivalent characterization of load. Orthonormal basis with definable and distinguishable periodicity that can linearly express load curves constitutes a space to capture the dynamism, where coefficients of the basis quantify the dynamism in multiple dimensions. A price function is proposed to map the coefficients to a numerical charge. A pricing model on the space specialized by the Fourier series is derived for the simplest one-source-one-subscriber system and generalized to a single-bus system with multiple sources and multiple subscribers. Examples will demonstrate the use of the proposed pricing and its effectiveness in reflecting the cost of generation to cope with load dynamism and guaranteeing fairness.

eess.SY↗

arXiv2018

An Accurate and Real-time Self-blast Glass Insulator Location Method Based On Faster R-CNN and U-net with Aerial Images

The location of broken insulators in aerial images is a challenging task. This paper, focusing on the self-blast glass insulator, proposes a deep learning solution. We address the broken insulators location problem as a low signal-noise-ratio image location framework with two modules: 1) object detection based on Fast R-CNN, and 2) classification of pixels based on U-net. A diverse aerial image set of some grid in China is tested to validated the proposed approach. Furthermore, a comparison is made among different methods and the result shows that our approach is accurate and real-time.

cs.CV↗

arXiv2015

A Random Matrix Theoretical Approach to Early Event Detection in Smart Grid

Power systems are developing very fast nowadays, both in size and in complexity; this situation is a challenge for Early Event Detection (EED). This paper proposes a data- driven unsupervised learning method to handle this challenge. Specifically, the random matrix theories (RMTs) are introduced as the statistical foundations for random matrix models (RMMs); based on the RMMs, linear eigenvalue statistics (LESs) are defined via the test functions as the system indicators. By comparing the values of the LES between the experimental and the theoretical ones, the anomaly detection is conducted. Furthermore, we develop 3D power-map to visualize the LES; it provides a robust auxiliary decision-making mechanism to the operators. In this sense, the proposed method conducts EED with a pure statistical procedure, requiring no knowledge of system topologies, unit operation/control models, etc. The LES, as a key ingredient during this procedure, is a high dimensional indictor derived directly from raw data. As an unsupervised learning indicator, the LES is much more sensitive than the low dimensional indictors obtained from supervised learning. With the statistical procedure, the proposed method is universal and fast; moreover, it is robust against traditional EED challenges (such as error accumulations, spurious correlations, and even bad data in core area). Case studies, with both simulated data and real ones, validate the proposed method. To manage large-scale distributed systems, data fusion is mentioned as another data processing ingredient.

stat.ME↗