Search

This paper examines the use of manifold learning in the context of electric power system transient stability analysis. Since wide-area monitoring systems (WAMSs) introduced a big data paradigm into the power system operation, manifold learning can be seen as a means of condensing these high-dimensional data into an appropriate low-dimensional representation (i.e., embedding) which preserves as much information as possible. In this paper, we consider several embedding methods (principal component analysis (PCA) and its variants, singular value decomposition, isomap and spectral embedding, locally linear embedding (LLE) and its variants, multidimensional scaling (MDS), and others) and apply them to the dataset derived from the IEEE New England 39-bus power system transient simulations. We found that PCA with a radial basis function kernel is well suited to this type of power system data (where features are instances of three-phase phasor values). We also found that the LLE (including its variants) did not produce a good embedding with this particular kind of data. Furthermore, we found that a support vector machine, trained on top of the embedding produced by several different methods was able to detect power system disturbances from WAMS data. [ABSTRACT FROM AUTHOR]

Power systems are becoming more and more complicated. Traditional simulation tools such as transient stability programs and electromagnetic transients (EMT) programs are unable to meet the accuracy or efficiency requirements. This paper proposes a shifted frequency‐based EMT (SFEMT) simulation in the symmetrical component‐domain (abbreviated as SCSFEMT simulation) for the three‐phase transmission system. The sequence‐decoupled SCSFEMT modeling for the power system components is first presented based on the symmetrical component transformation. Then, the solution procedure of the presented SCSFEMT simulation algorithm is elaborated in detail based on the EMTP‐type solution and multi‐sequence Thevenin equivalence (MSTE). With the MSTE, the three sequence networks can be decoupled during the whole simulation. Thus, the dimension of the system is greatly reduced. Last, the accuracy and efficiency of the SCSFEMT simulation are validated on the 10‐machine 39‐bus New England system by comparing it with traditional EMT and SFEMT simulation. Test results show that the SCSFEMT simulation algorithm is much more efficient than traditional SFEMT simulation. [ABSTRACT FROM AUTHOR]

In this work we present a novel technique, based on a trust-region optimization algorithm and second-order trajectory sensitivities, to compute the extreme trajectories of power system dynamic simulations given a bounded set that represents parametric uncertainty. We show how this method, while remaining computationally efficient compared with sampling-based techniques, overcomes the limitations of previous sensitivity-based techniques to approximate the bounds of the trajectories when the local approximation loses validity because of the nonlinearity. We present several numerical experiments that showcase the accuracy and scalability of the technique, including a demonstration on the IEEE New England test system. [ABSTRACT FROM AUTHOR]

This paper presents a fault detection and identification system for power systems using an artificial neural network approach while discussing its advantages and disadvantages. The initial data for the proposed technique are a set of simulated post-fault bus voltages and currents obtained at a sampling rate which emulates a complete phasor measurement unit (PMU)-based wide area measurement system (WAMS). Several types of faults are considered, such as short circuits and line and load contingencies. All fault and steady-state simulations have been performed on MATLAB using the Power System Toolbox. The artificial neural network was designed using an architecture proper for pattern recognition with supervised learning. As a result, satisfactory predictions within short time periods are obtained. The test system used in all simulations is the IEEE 39-Bus New England Power System, which has 10 generation units, 21 loads, and three distinct areas alongside transient and sub transient models, with PMUs distributed over up to 14 buses. Future works are also discussed in this paper, showing the possibilities for feature engineering in this type of problem, as well as the application of other machine learning and data analytics techniques for PMU-based WAMS databases. [ABSTRACT FROM AUTHOR]

This paper proposes a data-driven cooperative method for load frequency control (LFC) of the multi-area power system based on multi-agent deep reinforcement learning (MA-DRL) in continuous action domain. The proposed method can nonlinearly and adaptively derive the optimal coordinated control strategies for multiple LFC controllers through centralized learning and decentralized implementation. The centralized learning is achieved by MA-DRL based on a global action-value function to quantify overall LFC performance of the power system. To solve the MA-DRL problem, multi-agent deep deterministic policy gradient (DDPG) is derived to adjust control agents’ parameters considering the nonlinear generator behaviors. For implementation, each individual controller only needs local information in its control area to deliver optimal control signals. Numerical simulations on a three-area power system and the fully-modeled New-England 39-bus system demonstrate that the proposed method can effectively minimize control errors against stochastic frequency variations caused by load and renewable power fluctuations. [ABSTRACT FROM AUTHOR]

Summary: Disastrous effects resulting from power system security issues have been pointed out in various blackout reports. In these reports, setting of the third zone reach being large was found to be a major reason. In addition to a fault, the apparent impedance measured by the relay can also enter the third‐zone setting for different stressed events, such as load encroachment, power swing, and voltage instability, and thus be misinterpreted as a three‐phase fault, leading to relay maloperation. To improve the functionality of the relay under such dire situations, a local end information‐based technique is proposed. The scheme uses the Teager energy‐based approach for developing an index criterion. As per the proposed method, after the entry of the impedance into the relay zone‐3 characteristic, the index is checked. If both the impedance and the index cross their respective thresholds, the disturbance event will be detected as a fault. Otherwise, it will be a no‐fault condition and undesired relay operation avoided. Reliability of the proposed technique is tested for various power system events by simulation on the New England 39‐bus, 10 machine test system. [ABSTRACT FROM AUTHOR]