With increase of practical power system complexity, power system online stability assessment and control is more and more important. Application of the traditional model-driven methods is always limited by contradiction between accuracy and efficiency, while data-driven methods demonstrate strong abilities for the online decision-making support with advancement of various data mining techniques. Instead of direct application of data-driven methods in the power system, this paper first discusses feasible integration approaches for the model-driven and data-driven methods based on the existing achievements, and then, proposes to integrate both methods for the power system online frequency stability assessment and control. The integrated method consists of frequency dynamics prediction and load shedding procedure. In frequency dynamics prediction procedure, integration of system frequency response (SFR) model and the extreme learning machine (ELM)-based learning model is applied, where basic physical causality is kept in the SFR model and ELM is used to fit and correct error of the SFR. The ELM also plays a part in load shedding prediction model construction by digging out mapping relationship from samples. Finally, the proposed prediction and control scheme for the frequency stability is verified by simulations on WSCC 9-bus, New England 39-bus, and NPCC 140-bus system. Results show that the reliability, time efficiency, and accuracy are enhanced with the proposed method.

Peer-to-peer (P2P) transactive energy trading has emerged as a promising paradigm towards maximizing the flexibility value of prosumers’ distributed energy resources (DERs). Despite reinforcement learning constitutes a well-suited model-free and data-driven methodological framework to optimize prosumers’ energy management decisions, its application to the large-scale coordinated management and P2P trading among multiple prosumers within an energy community is still challenging, due to the scalability, non-stationarity and privacy limitations of state-of-the-art multi-agent deep reinforcement learning (MADRL) approaches. This paper proposes a novel P2P transactive trading scheme based on the multi-actor-attention-critic (MAAC) algorithm, which addresses the above challenges individually. This method is complemented by a P2P trading platform that incentivizes prosumers to engage in local energy trading while also penalizes each prosumer’s addition to rebound peaks. Case studies involving a real-world, large-scale scenario with 300 residential prosumers demonstrate that the proposed method significantly outperforms the state-of-the-art MADRL methods in reducing the community’s cost and peak demand.

Wind power prediction is the key technology to the safe dispatch and stable operation of power system with large-scale integration of wind power. In this work, based on the historical data of wind power, wind speed and temperature, the autoregressive moving average (ARMA) prediction model and the support vector machine (SVM) prediction model are established, particle swarm optimization (PSO) algorithm is involved for parameter optimization of SVM model. Furthermore, a hybrid PSO-SVM-ARMA prediction model based on ARMA and PSO-SVM model is illustrated for wind power prediction, and the covariance minimization method and PSO are employed to find the optimal weights. Moreover, with the basis of clustering theory, time series are clustered to examine the effective dataset for wind power prediction, and a clustered hybrid PSO-SVM-ARMA (C-PSO-SVM-ARMA) wind power prediction model is prospectively proposed. In case study, different prediction models are carried out and the prediction performance is examined based on different evaluation indices, the C-PSO-SVM-ARMA model shows better performance for wind power prediction with computational efficiency and satisfying precision.

Local electricity markets (LEM) have recently attracted great interest as an effective solution to the challenging problem of distributed energy resources’ (DER) management. However, LEM designs combining the market functions of local energy trading and flexibility services (FS) provision to wider system operators have not attracted sufficient attention. In the context of addressing this research gap, this paper firstly provides a new model-based system-centric formulation for the coordination of such a LEM, which provides a theoretical optimality benchmark. Compared to previous formulations, it considers the time-coupling operating characteristics of flexible DERs, and optimizes the two market functions simultaneously. Furthermore, this paper explores for the very first time a model-free prosumer-centric coordination approach for such a LEM, in order to address the practical limitations of model-based system-centric approaches. This is achieved through a new multi-agent deep reinforcement learning method which combines the beneficial properties of the multi-actor-attention-critic and the prioritized experience replay approaches. Case studies on a real-world, large-scale setting validate that the proposed LEM design successfully encapsulates the economic benefits of both local energy trading and FS provision functions, and demonstrate that the proposed learning method outperforms previous methods.

Microgrids (MG) have recently attracted great interest as an effective solution to the challenging problem of distributed energy resources’ management in distribution networks. In this context, despite deep reinforcement learning (DRL) constitutes a well-suited model-free and data-driven methodological framework, its application to MG energy management is still challenging, driven by their limitations on environment status perception and constraint satisfaction. In this paper, the MG energy management problem is formalized as a Constrained Markov Decision Process, and is solved with the state-of-the-art interior-point policy optimization (IPO) method. In contrast to conventional DRL approaches, IPO facilitates efficient learning in multi-dimensional, continuous state and action spaces, while promising satisfaction of complex network constraints of the distribution network. The generalization capability of IPO is further enhanced through the extraction of spatial-temporal correlation features from original MG operating status, combining the strength of edge conditioned convolutional network and long short-term memory network. Case studies based on an IEEE 15-bus and 123-bus test feeders with real-world data demonstrate the superior performance of the proposed method in improving MG cost effectiveness, safeguarding the secure operation of the network and uncertainty adaptability, through performance benchmarking against model-based and DRL-based baseline methods. Finally, case studies also analyze the computational and scalability performance of proposed and baseline methods.

The real-time center of inertia frequency plays an important role in power system stability analysis and control. This letter proposes a robust approach to identify power system center of inertia frequency with consideration of system uncertainties and synchrophasor measurement quality. A model decoupling strategy is first presented by taking measured generator active power as the swing equation input, whereas remaining the bus frequency as output. This allows deriving the linear discrete-time state-space form, which will be used by the robust Kalman filter for generator rotor speed, angle, and inertia estimation. The robust Kalman filter is mandatory as the measured frequency can change abruptly due to impulsive noise or system sudden changes. Simulations carried out on the IEEE 39-bus system validate the effectiveness and robustness of the proposed approach in the presence of various sources of uncertainties.