This paper introduces a new scheme for suburban renewable energies, hydrogen plant, and logistics (SRE-HP-LC) integration scheme and dispatching. The objective of the proposed SRE-HP-LC integration scheme aims at coordinating the operation of renewable energies, hydrogen production and storage and logistic transportation. In order to take advantages of various energy conversion techniques to enhance the energy utilization rate and improves the financial revenue of the integration scheme, a completed dispatching and operating scheme for the proposed SRE-HP-LC integration scheme is introduced in the scheme stage. A multiple-demand-response objective function is developed in the operation stage to coordinate the hydrogen energy usage in the SRE-HP-LC integration scheme. The proposed SRE-HP-LC integration scheme considers the uncertainties of renewable energy output and truck demand so that it improves the revenue of every component in the integration scheme. Case studies on a general integration system verify the effectiveness and economic value of the proposed SRE-HP-LC integration scheme.

The Single-phase-to-ground fault (SPGF) affects reliability and security of distribution system greatly. Accurate online recognition of fault causes can help improve the efficiency of weak components finding and maintenance. In this paper, various symptom features of the SPGF by typical causes are analyzed and a fuzzy inference system (FIS) for fault cause recognition is established for overhead lines in non-solidly earthed distribution networks. Based on the survey of fault causes in a certain city in China, artificial grounding experiments are designed for six typical fault causes, including arrester breakdown, insulator flashover, line-to-crossbar discharge, line fallen on wet mud, line fallen on wet sand, and line fallen into pond for waveform data collection. Through multiple time-frequency analysis on waveform data of various causes, five features are extracted and the statistical results are obtained, including self-recoverability, zero current time, transition time, degree of distortion, and randomness. Based on above, a FIS for cause recognition for SPGFs is established. The experimental results and the comparison with BPNN model show that the proposed method has good performance and feasibility.

In nonsolidly earthed distribution networks, single-phase-to-ground faults (SPGFs) significantly threaten the safety of people and equipment. Although selection and location techniques for the existing fault lines have made remarkable contributions in reducing the damage due to SPGFs, a certain amount of power loss still exists in the SPGF owing to its low efficiency in detection and maintenance. Multiple-dimensional classification of the SPGF May help reveal the nature of the fault from different perspectives; therefore, in this article, a multilabel classification model for recognizing the types of SPGF is proposed. In the proposed model, the SPGF is classified considering five dimensions, namely time-domain continuity, time-domain stability, volt-ampere characteristics of transition impedance, transition impedance size, and fault point medium. Subsequently, the corresponding features are determined. In addition, a multilabel classification model of the SPGF is constructed with an 8-D feature space and a 14-label fault-type space. Finally, a k-nearest neighbors Bayesian method is designed to solve the multilabel classification problem. The feasibility and advantages of the proposed model and methods are verified using field data and through comparison with the KNN method.

Online monitoring of gases dissolved in transformer oil is widely applied. Improving the performance of dissolved gas analysis (DGA)‐based fault diagnosis methods by exploring new features of time‐series data has become an appealing topic. In this study, a new type of correlation features between characteristic gases was extracted from time‐series data based on the maximal information coefficient (MIC), and a fuzzy inference system was established. After the introduction of the principle of the MIC and a method for calculating the MIC‐based correlation features, the dominant symptom features that can be used to classify fault types were extracted through the receiver operating characteristic curve. Then, fuzzy rules were learnt, and a fuzzy inference system was designed. In addition, to improve the feasibility of the method, the Newton interpolation method was used for adaptation to the existing sampling cycle. The diagnostic results of the test data show that the proposed method has excellent performance and outperforms some prevailing traditional rule‐based methods as well as some artificial intelligent methods. The results also show that by exploring new correlation features from time‐series data based on the MIC, the performance of DGA‐based methods can be improved.

In this paper, a model is proposed for the optimal operation of multi-energy microgrids (MEMGs) in the presence of solar photovoltaics (PV), heterogeneous energy storage (HES) and integrated demand response (IDR), considering technical and economic ties among the resources. Uncertainty of solar power as well as the flexibility of electrical, cooling and heat load demand are taken into account. A p-efficient point method is applied to compute PV power at different confidence levels based on historical data. This method converts the uncertain PV energy from stochastic to deterministic to be included in the optimization model. The concept of demand response is extended and mathematically modeled using a linear function based on the quantized flexibility interval of multi-energy load demand. As a result, the overall model is formulated as a mixed-integer linear program, which can be effectively solved by the commercial solvers. The proposed model is implemented on two typical summer and winter days for various cases. Results of case studies show the important benefits for maximum PV utilization, energy efficiency and economic system operation. Moreover, the influence of the different confidence levels of PV power and effectiveness of IDR in the stochastic circumstances are addressed in the optimization-based operation.