• Energy Research

This article proposes a robust topology change-aware distribution system state estimation (DSSE) method based on a physics-informed graph neural network and Bayesian Probability Weighted Averaging (BPWA). A general state estimator is first built utilizing a graph attention network to learn the nonlinear mapping functions under different distribution network topologies. During this stage, the topology information is embedded in the neural network and the attention mechanism is employed to capture collaborative signals and discriminate the importance of neighboring buses. Then, the BPWA method allows assigning proper weights for the state estimation results under different topologies, which finally yields a single consensus solution via the sparse training samples under the new topology. The physics-informed mechanism enables the proposed method to embed the topology knowledge in the neural network while fully exploiting the value of historical data. Robustness to anomalous measurements is achieved through the embedding of physics knowledge. The application of the BPWA method further allows the proposed method to achieve faster adaptation to topology change and quantification of the estimation uncertainties by measurement errors. MATLAB and Python are used to carry out the comparative tests to evaluate the performance of the proposed method.

The training process of learning-based distribution system state estimation (DSSE) methods relies on accurate state variables, which typically contain unknown noise and outliers in practice. To this end, this paper proposes an adaptive noise-resistant graphical learning-based DSSE method considering the impact of inaccurate state variables. Specifically, two global-scanning graph jumping connection networks are first developed to capture the regression rules between measurements and state variables considering the structure constraints. To mitigate the negative impact caused by inaccurate labels, a collaborative learning framework is further developed, within which Gaussian mixture model-based discriminators are employed to adaptively select clean samples in each mini-batch. These allow the method to obtain robustness against noisy state labels in historical data, as well as anomalous measurements during online operations. Comparative tests show the superiority of the proposed method in tackling abnormal data in both the training and test phases.

This paper develops a robust physics-informed state estimation method for the distribution network with inaccurate topology information. An aggregated k-nearest neighbor graph is first derived as the feature graph according to the inaccurate topology and measurement features. Then, graph propagation and aggregation are performed by an adaptive multi-channel graph attention model on both the feature graph and the graph constructed based on the inaccurate given topology. To fuse the different graph embeddings, an attention module is further employed to adaptively assign importance weights for them. This allows the proposed method to achieve robustness against anomalous measurements even when the given topology information is inaccurate. Comparative results with state-of-the-art distribution system state estimation methods demonstrate the accuracy and robustness of the proposed method.

This paper proposes a novel multi-agent deep reinforcement learning (MADRL) approach for the energy management of multiple microgrids considering the robust voltage control under the missing measurements. Missing measurement control poses challenges to the MADRL. To address the problem, we propose a trajectory history information-utilized opponent modeling-based distributed MADRL to avoid the collapse of control caused by the loss of current time measurement. Simulation results demonstrate that, whether the measurements are complete or not, the proposed approach achieves the ideal results.

A probabilistic load forecasting method that can deal with sudden load pattern changes caused by abnormal events such as COVID-19 is proposed in this paper. The deep residual network (ResNet) is first applied to extract the load pattern for the normal period from historical data. When an abnormal event occurs, a Gaussian Process (GP) with a composite kernel is utilized to adapt to the changes on load pattern by estimating the forecasting residual of the ResNet. The designed kernel enables the proposed method to adapt rapidly to changes in the load pattern and effectively quantify the uncertainties caused by the abnormal event using a few training samples. Comparative tests with state-of-the-art point and probabilistic forecasting methods demonstrate the effectiveness of the proposed method.

This letter develops a novel multi-agent deep reinforcement learning (MADRL)-based local control method that can achieve coordinated scheduling of large-scale PV inverters using local information. This is achieved by the development of a system state inference-aided actor structure for each agent and implementation of random sequential updating within centralized-training-decentralized-execution framework. To enhance the coordination between agents utilizing local observation, a state latent inductive reasoning-based composite loss is further designed for the optimization of the inference models. Simulation tests on IEEE 123-node network demonstrate the superiority of the developed local control method when there is a large number of PV inverters.

Accurate multi-energy load forecasting plays an important role in the stable and secure operation of integrated energy systems (IESs). The strong randomness and complex coupling relationship among multiple energy loads bring huge challenges for the accurate forecasting of multi-energy load. In this context, this paper proposes a multi-task learning method-enabled probabilistic load forecasting method for the joint prediction of electric, cooling, and heating loads. Specifically, a complex neural network (ComNN) is developed to capture the coupling relationships between the multiple loads by taking aggregated multi-source information as input. The hard-parameter sharing mechanism is adopted to share information between tasks and reduce the risk of overfitting in multi-task learning. To balance the training of multiple loads, a geometric loss function (GLF) is designed for the optimization of the ComNN. It is further extended to a geometric quantile loss function to capture the uncertainties of multi-energy load. The ComNN allows the coupling information to be shared among the multiple tasks, which enhances the forecasting performance of the proposed method on each individual task. The designed geometric quantile loss function further enables the proposed method to dynamically balance the weights for different tasks during training and achieve effective quantification of the multi-energy load forecasting outcomes. Comparative tests with state-of-the-art forecasting methods using regional IES load data from Arizona State University's Tempe campus and Western China demonstrate the effectiveness of the proposed method in both deterministic and probabilistic multi-energy load forecasting.

This paper proposes a novel data-driven self-tuning additional sliding mode controller for power system transient voltage stability enhancement considering wind integration. We first develop a new additional fractional-order sliding mode controller (FOSMC) for the static var compensator (SVC). The tuning of FOSMC parameter settings is then reformulated as a Markov decision process (MDP) and solved by the deep reinforcement learning (DRL) algorithm. In addition, a data-driven estimation method is proposed for the identification of an equivalent transfer function that is further used to calculate reward during the training process, yielding the model-free training. After that, the well-trained agent allows us to tune the controller parameters considering system uncertainties and achieve robustness against various operating conditions. Comparative results with other state-of-art methods demonstrate that the proposed method can effectively suppress the chattering issue of the sliding mode controller and ensure transient voltage stability under different operating conditions.