This paper presents a rule‐based adaptive protection scheme using machine‐learning methodology for microgrids in extensive distribution automation (DA). The uncertain elements in a microgrid are first analysed quantitatively by Pearson correlation coefficients from data mining. Then, a so‐called hybrid artificial neural network and support vector machine (ANN‐SVM) model is proposed for state recognition in microgrids, which utilises the growing massive data streams in smart grids. Based on the state recognition in the algorithm, adaptive reconfigurations can be implemented with enhanced decision‐making to modify the protective settings and the network topology to ensure the reliability of the intelligent operation. The effectiveness of the proposed methods is demonstrated on a microgrid model in Aalborg, Denmark and an IEEE 9 bus model, respectively.

An optimal placement problem on Battery Energy Storage Systems (BESSs) integrating the optimization on BESS controller parameters is formulated for power system oscillation damping improvement in this paper. First, a BESS model is established based on the power output characteristics of its power converter interface considering the converter power limit, State of Charge (SOC) limit, and the time constant of converters. Then the objective function and constraints are introduced to establish a black-box mixed-integer optimization problem tackled by interfacing time-domain simulations with a Mixed-Integer Particle Swarm Optimization (PSO) algorithm. Finally, the proposed optimization procedure is tested on the New England 39-bus system and the Nordic test system. The optimal results are also verified by time-domain simulations. Finally, the applicability of the proposed method is investigated including: consideration of seasonal load change; minimum number of BESS units to be placed; improvement of the PSO efficiency and performance comparison of different controllers. Results demonstrate the effectiveness of the proposed approach for optimization of the battery energy storage placement.

Dynamic behaviors of distribution networks are of great importance for the power system analysis. Nowadays, due to the integration of the renewable energy generation, energy storage, plug-in electric vehicles, and distribution networks turn from passive systems to active ones. Hence, the dynamic behaviors of active distribution networks (ADNs) are much more complex than the traditional ones. The research interests how to establish an accurate model of ADNs in modern power systems are drawing a great deal of attention. In this paper, motivated by the similarities between power system differential algebraic equations and the forward calculation flows of recurrent neural networks (RNNs), a long short-term memory (LSTM) RNN-based equivalent model is proposed to accurately represent the ADNs. First, the adoption reasons of the proposed LSTM RNN-based equivalent model are explained, and its advantages are analyzed from the mathematical point of view. Then, the accuracy and generalization performance of the proposed model is evaluated using the IEEE 39-Bus New England system integrated with ADNs in the study cases. It reveals that the proposed LSTM RNN-based equivalent model has a generalization capability to capture the dynamic behaviors of ADNs with high accuracy.

The variation and uncertainty of renewable energy potentially impact power system stability. This article proposes an efficient uncertainty evaluation algorithm to evaluate the influence of renewable energy uncertainty on power system dynamic performance. This algorithm applies probabilistic collocation method (PCM), which greatly reduces the simulation burden without compromising the result accuracy, to approximate the dynamic simulation results. The proposed algorithm also considers the correlation among adjacent renewable generators by using the Copula function, which is suitable to model nonlinear correlations. Additionally, this article extends the utilization of PCM. The actual historical data of renewable generation productions can be utilized directly, and kernel density estimation (KDE) is used to capture the nonparametric distribution of renewable generation production. To improve the accuracy of the approximation results, the proposed method adopts K-means clustering technique to select the approximation samples of input variables. The proposed probabilistic dynamic simulation algorithm is compared with Monte Carlo simulations (MCS) with the probabilistic results on the IEEE 39-bus system with multiple renewable generators, and the accuracy and efficiency of the proposed algorithm are validated.

This paper presents a novel fast frequency and voltage regulation method for battery energy storage system (BESS) based on the amplitude-phase-locked-loop (APLL). In the proposed method, the primary frequency regulation and inertia emulating control are designed based on grid frequency deviation ( ${\Delta }f$ ) and its differential $(df/dt)$ signals detected by APLL, avoiding complicated and sensitive differential operation to get better dynamic support performance. Moreover, unlike the traditional voltage control only using grid voltage deviation ( ${\Delta }V$ ), the proposed method also uses the voltage differential control ( $dV/dt$ -control) to improve dynamic performance of traditional voltage control and behaviors of grid voltage based on the $dV/dt$ signal from APLL. Finally, simulations and experiments are implemented to validate the effectiveness of the proposed APLL-based BESS on improving the dynamic behaviors of grid frequency and voltage.

This paper proposes an online steady-state voltage stability assessment scheme to evaluate the proximity to voltage collapse at each bus of a load area. Using a non-iterative holomorphic embedding method (HEM) with a proposed physical germ solution, an accurate loading limit at each load bus can be calculated based on online state estimation on the entire load area and a measurement-based equivalent for the external system. The HEM employs a power series to calculate an accurate Power-Voltage (P-V) curve at each load bus and accordingly evaluates the voltage stability margin considering load variations in the next period. An adaptive two-stage Pade approximants (PA) method is proposed to improve the convergence of the power series for accurate determination of the nose point on the P-V curve with moderate computational burden. The proposed method is illustrated in detail on a 4-bus test system and then demonstrated on a load area of the Northeast Power Coordinating Council (NPCC) 48-generator, 140-bus power system.