Effective detection of electricity theft is essential to maintain power system reliability. With the development of smart grids, traditional electricity theft detection technologies have become ineffective to deal with the increasingly complex data on the users’ side. To improve the auditing efficiency of grid enterprises, a new electricity theft detection method based on improved synthetic minority oversampling technique (SMOTE) and improve random forest (RF) method is proposed in this paper. The data of normal and electricity theft users were classified as positive data (PD) and negative data (ND), respectively. In practice, the number of ND was far less than PD, which made the dataset composed of these two types of data become unbalanced. An improved SOMTE based on K-means clustering algorithm (K-SMOTE) was firstly presented to balance the dataset. The cluster center of ND was determined by K-means method. Then, the ND were interpolated by SMOTE on the basis of the cluster center to balance the entire data. Finally, the RF classifier was trained with the balanced dataset, and the optimal number of decision trees in RF was decided according to the convergence of out-of-bag data error (OOB error). Electricity theft behaviors on the user side were detected by the trained RF classifier.

In this work, spherical flower-shaped composite carbonyl iron powder@MnO2 (CIP@MnO2) with CIP as the core and ultrathin MnO2 nanosheets as the shell was successfully prepared by a simple redox reaction to improve oxidation resistance and electromagnetic wave absorption properties. The microwave-absorbing properties of CIP@MnO2 composites with different filling ratios (mass fractions of 20%, 40%, and 60% after mixing with paraffin) were tested and analyzed. The experimental results show that compared with pure CIP, the CIP@MnO2 composites have smaller minimum reflection loss and a wider effective absorption bandwidth than CIP (RL < −20 dB). The sample filled with 40 wt% has the best comprehensive performance, the minimum reflection loss is −63.87 dB at 6.32 GHz, and the effective absorption bandwidth (RL < −20 dB) reaches 7.28 GHz in the range of 5.92 GHz–9.28 GHz and 11.2 GHz–15.12 GHz, which covers most C and X bands. Such excellent microwave absorption performance of the spherical flower-like CIP@MnO2 composites is attributed to the combined effect of multiple beneficial components and the electromagnetic attenuation ability generated by the special spherical flower-like structure. Furthermore, this spherical flower-like core–shell shape aids in the creation of discontinuous networks, which improve microwave incidence dispersion, polarize more interfacial charges, and allow electromagnetic wave absorption. In theory, this research could lead to a simple and efficient process for producing spherical flower-shaped CIP@MnO2 composites with high absorption, a wide band, and oxidation resistance for a wide range of applications.

Owing to its modular construction, ability for bi-directional power flow and suitability for AC/DC grids, solid-state transformer (SST) is expected to be the backbone of the future smart grids. One of the main drawbacks of SST is the generation of negative-sequence current component at its input stage under unbalanced distribution system which causes adverse impacts on the power quality of the electricity grids. This paper is aimed at proposing a novel unbalance compensation method based on reduced order generalized integrator to suppress the negative-sequence current. Unlike the conventional sequence compensation method that is based on dual synchronous reference frames, the new proposed method does not involve complex calculation of the command current and sequence decomposition. As such, the response speed of the compensation controller is significantly improved. Additionally, the proposed method is easy to implement when compared with the current conventional compensation technique as there is no need to inject sequence components into the grid. A simulation model of three-module cascaded SST with threephase star connection is established in Matlab/Simulink. Several case studies are carried out under different operating conditions. Simulation results validate the feasibility of the proposed method. INDEX TERMS Solid-state transformer, negative-sequence current suppression, reduced order generalized integrator, three-phase unbalance compensation.

No abstract

In this paper, a fuzzy neural network controller for regulating demand-side thermostatically controlled loads (TCLs) is designed with the aim of stabilizing the frequency of the smart grid. Specifically, the balance between power supply and demand is achieved by tracking the automatic generation control (AGC) signal in an electric power system. The particle swarm optimization (PSO) and error back propagation (BP) algorithms are used to optimize the control parameters and consequently reduce the tracking errors. The fuzzy neural network can be applied to solve load control problems in power systems, since its self-learning and associative storage functions can deal with the highly nonlinear relationship between input and output. Simulation results show the advantage of the fuzzy neural network control scheme in terms of frequency regulation error and consumer comfort.