Search

This paper develops a hierarchical deep learning machine (HDLM) to efficiently achieve both quantitative and qualitative online transient stability prediction (TSP). For the sake of improving its online efficiency, multiple generators’ fault-on trajectories as well as the two closest data-points in pre-/post-fault stages are acquired by PMUs to form its raw inputs. An anti-noise graphical transient characterization technique is tactfully designed to transform multiplex trajectories into 2-D images, within which system-wide transients are concisely described. Then, following the divide-and-conquer philosophy, the HDLM trains a two-level convolutional neural network (CNN) based regression model. With stability margin regressions hierarchically refined, it manages to perform reliable and adaptive online TSP almost immediately after fault clearance. Test results on the IEEE 39-bus test system and the real-world Guangdong Power Grid in South China demonstrate the HDLM's superior performances on both stability status and stability margin predictions. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) is the basis of power system planning and operation. With regard to the fast-growing load in China, a novel two-stage hybrid forecasting method is proposed in this paper. In the first stage, daily load is forecasted by time-series methods; in the second stage, the deviation caused by time-series methods is forecasted considering the impact of relative factors, and then is added to the result of the first stage. Different from other conventional methods, this paper does an in-depth analysis on the impact of relative factors on the deviation between actual load and the forecasting result of traditional time-series methods. On the basis of this analysis, an adaptive algorithm is proposed to perform the second stage which can be used to choose the most appropriate algorithm among linear regression, quadratic programming, and support vector machine (SVM) according to the characteristic of historical data. These ideas make the forecasting procedure more accurate, adaptive, and effective, comparing with SVM and other prevalent methods. The effectiveness has been demonstrated by the experiments and practical application in China. [ABSTRACT FROM PUBLISHER]

A quasi-continuous high magnetic field is a special kind of pulsed magnetic field with a flat-top field longer than 100 ms. This paper proposes a hybrid power supply that consists of a capacitor power supply and a generator-rectifier power supply. A dual-coil magnet is powered to generate a 65 T/100 ms quasicontinuous high magnetic field with a ripple less than 500 ppm at the Wuhan National High Magnetic Field Center, Wuhan, China. A protection circuit consists of an R-C branch and a diode array is discussed for the worst short-circuit fault, which occurs between the first turns of inner coil and outer coil. This type of faultwill produce oscillation voltage with a high peak value and high frequency on the rectifiers. A self-adaptive PI controller with the coefficients corrected by a back propagation neural network is adopted to reduce the ripple of a flat-top. [ABSTRACT FROM AUTHOR]

During the last decade, neural networks have emerged as one of the most powerful and accurate nonlinear models for load forecasting. However, using neural networks requires users to have in-depth knowledge to determine the model structure and parameters, which limits their wide application. To overcome this weakness, this paper proposes an integrated approach which combines a self-organizing fuzzy neural network (SOFNN) learning method with a bilevel optimization method. SOFNNs can automatically determine both the model structure and parameters, while the bilevel optimization method automatically selects the best pre-training parameters to ensure that the best fuzzy neural networks be identified. Therefore, the proposed approach is able to automatically identify the best fuzzy neural network for a given forecasting task and is much easier to use in practice. The proposed approach is tested on real-load data from the Southern Power Network of Hebei Province, China, and on the EUNITE competition data. Results show the proposed approach improves existing load forecasting models. [ABSTRACT FROM AUTHOR]

In this work, firstly we propose an artificial neural network (ANN) based channel modeling and simulation framework to playback a measurement channel to overcome the shortcomings of traditional geometry based stochastic modelling (GBSM) and simulation approach which is unable to predict a time or position-varying channel to match with real environment. Secondly, we implement the framework based on channel measurements performed at 28 GHz in a large waiting hall at Qingdao high-speed railway station, China. Thirdly, we validate the proposed framework by comparisons of the large scale channel parameters (LSCPs) and small scale channel parameters (SSCPs) extracted from the measured, ANN and GBSM simulation channels. The results show that the ANN-based framework can playback the measured channels accurately, while GBSM-based simulated channels have large deviations. This work offers a solution to playback the measured channels accurately to be used in 5G and beyond radio system research and engineering applications, while it’s also able to be applied in future channel predictions in case of large amount of measured data available. [ABSTRACT FROM AUTHOR]

Electricity theft behaviors have caused great harm to the economic benefits of power companies and the secure operation of power systems, thus electricity theft detection is paid much attention in the actual power supply management. In this work, a two-step electricity theft detection strategy is proposed to identify electricity theft users and predict potentially stolen electricity (PSE) for maximizing economic return. In the first step, a neural network model called convolutional autoencoder (CAE) is proposed for electricity theft identification, and the convolutional layer is adopted in CAE to extract and identify the abnormalities of electricity theft users against the uniformity and periodicity of normal power consumption features. In the second step, the PSE of each identified electricity theft user is predicted by the improved regression algorithm named Tr-XGBoost, which combines the extreme gradient boosting (XGBoost) algorithm and transfer adaptive boosting (TrAdaBoost) training strategy. The propsoed Tr-XGBoost could learn the relationship between the extracted electricity features and the PSE of each electricity theft user, and then the predicted PSE can be used to determine the list of electricity theft users to be inspected for maximizing economic return. Case studies on both the IEEE 33-bus test system and a low-voltage distribution system of a province in China show that the proposed two-step electricity theft detection strategy can improve the accuracy of electricity theft identification, and obtain a larger economic return because of a more accurate result of PSE prediction than other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) sensors, such as Advanced Land Observing Satellite-2 (ALOS-2) and Sentinel-1, provide significant opportunities for soil moisture content (SMC) retrieval with relatively high spatial resolutions (10~30 m). In this work, an artificial neural network (ANN) SMC retrieval algorithm combined with the water cloud model, the advanced integral equation model, and the Oh model database was proposed. The SAR copolarization backscatter, the local incidence angle (LIA), and the normalized difference vegetation index were used in input vectors for the ANN algorithm for the retrieval and mapping of the ALOS-2 and Sentinel-1 SMC at a 30-m resolution. The results of the comparison between the SMC retrievals and the measured SMC show that Sentinel-1 and ALOS-2 SMC retrievals with high accuracy correspond to low-vegetation areas (crop, grass, and shrub), with a root mean square error (RMSE) of 0.021 and 0.033 cm3/cm3, respectively. ALOS-2 SMC retrievals provide higher accuracy (RMSE = 0.076 cm3/cm3) than Sentinel-1 SMC retrievals at high vegetation (e.g., forest). However, it remains challenging for soil moisture retrieval in forest land. The C-band and L-band SMC retrievals have higher RMSE (up to 0.047 cm3/cm3) at low incidence angle (<20°) and high incidence angle (>50°). In addition, by considering the impact of rainfall on the SMC, it appears that the Sentinel-1 and ALOS-2 SMC have a good response to the rainfall events. Finally, the results of the comparison between the SMC retrievals and the Soil Moisture Active Passive (SMAP) L2 SMC product show that the correlation coefficients between Sentinel-1, ALOS-2, and SMAP are higher in September when the vegetation is drying than in July when the vegetation is growing. [ABSTRACT FROM AUTHOR]

Tropical cyclone (TC) intensity estimation is an important task in meteorological research. Meanwhile, TC intensity estimation performance can be improved by developing advanced machine learning techniques using the newly emerged high-quality multispectral images (MSIs) acquired by FY-4 meteorological satellite of China. To this end, this article proposes a novel model, tensor-based convolutional neural network (TCNN). Not only being a deep network entirely formulated in tensor algebra, but TCNN also establishes the mathematical connections between tensor decomposition and CNN operations with tensor contraction. Moreover, TCNN adopts a multitask structure, which consists of a classification network for intensity categorization and a regression network for wind speed estimation. It allows the regression network to leverage the outcome of the classification network, thus ensuring intensity estimation accuracy. In addition, two alternative TCNN models, coupled TCNN (C-TCNN) and Tucker TCNN (T-TCNN), are designed to automatically deal with invalid band data in the FY-4 MSIs, which has been a practical issue with the data. Experimental results prove that the proposed network is accurate and functional. They also demonstrate the advantages of TCNN over other TC intensity estimation methods, showing that C-TCNN and T-TCNN outperform several classic models and the state-of-the-art models based on CNN. [ABSTRACT FROM AUTHOR]