• Energy Research

With the increasing complexity of modern power systems, conventional dynamic load modeling with ZIP and induction motors (ZIP + IM) is no longer adequate to address the current load characteristic transitions. In recent years, the WECC composite load model (WECC CLM) has shown to effectively capture the dynamic load responses over traditional load models in various stability studies and contingency analyses. However, a detailed WECC CLM model typically has a high degree of complexity, with over one hundred parameters, and no systematic approach to identifying and calibrating these parameters. Enabled by the wide deployment of PMUs and advanced deep learning algorithms, proposed here is a double deep Q-learning network (DDQN)-based, two-stage load modeling framework for the WECC CLM. This two-stage method decomposes the complicated WECC CLM for more efficient identification and does not require explicit model details. In the first stage, the DDQN agent determines an accurate load composition. In the second stage, the parameters of the WECC CLM are selected from a group of Monte-Carlo simulations. The set of selected load parameters is expected to best approximate the true transient responses. The proposed framework is verified using an IEEE 39-bus test system on commercial simulation platforms. To appear in IEEE Transactions on Smart Grid

Stochastic programming methods have been proven to deal effectively with the uncertainty and variability of renewable generation resources. However, the quality of the solution that they provide (as measured by cost and reliability metrics) depends on the accuracy and the number of scenarios used to model this uncertainty and variability. Scenario reduction techniques are used to manage the computational burden by selecting representative scenarios. The common drawback of existing scenario reduction techniques is that the number of representative scenarios is a user-defined parameter. We propose a scenario reduction algorithm based on submodular function optimization to endogenously optimize the number of scenarios as well as rank these scenarios. This algorithm is compared, both qualitatively and quantitatively, with the state-of-the-art fast forward selection algorithm.

Energy Disaggregation at substations (EDS) is challenging because measurements are mostly aggregated over multiple types of loads, and the existence of some loads such as behind-the-meter solar is unknown to the operator. This paper for the first time addresses this so-called “partial labels” issue in energy disaggregation and develops a model-free EDS method to separate individual loads, including BTM solar, from the total energy consumption in real-time. Our approach learns the patterns of all loads offline from recorded historical datasets with partial labels. Compared with conventional model-free methods that require either pure measurements of each load for training or full labels of each training sample, our method can extract load patterns from partially labeled aggregated data and thus, is more applicable to practical scenarios and alleviates the annotation burden for the operator. Specifically, we propose to solve a new dictionary learning problem, where column-sparsity and incoherence regularization terms are added to identify unlabeled loads and learn distinctive patterns of each load. In real-time disaggregation, our approach solves an improved sparse decomposition problem where one decomposes the aggregated measurements as a linear combination of some representative recorded measurements with known disaggregation learned in the offline stage. Numerical experiments are reported to validate our method.

Growing model complexities in load modeling have created high dimensionality in parameter estimations, and thereby substantially increasing associated computational costs. In this paper, a tensor-based method is proposed for identifying composite load modeling (CLM) parameters and for conducting a global sensitivity analysis. Tensor format and Fokker-Planck equations are used to estimate the power output response of CLM in the context of simultaneously varying parameters under their full parameter distribution ranges. The proposed tensor structured is shown as effective for tackling high-dimensional parameter estimation and for improving computational performances in load modeling through global sensitivity analysis. Submitted to IEEE Power Engineering Letters

As the cost of battery energy storage continues to decline, we are likely to see the emergence of merchant energy storage operators. These entities will seek to maximize their operating profits through strategic bidding in the day-ahead electricity market. One important parameter in any storage bidding strategy is the state-of-charge at the end of the trading day. Because this final state-of-charge is the initial state-of-charge for the next trading day, it has a strong impact on the profitability of storage for this next day. This paper proposes a look-ahead technique to optimize a merchant energy storage operator's bidding strategy considering both the day-ahead and the following day. Taking into account the discounted profit opportunities that could be achieved during the following day allows us to optimize the state-of-charge at the end of the first day. We formulate this problem as a bilevel optimization. The lower-level problem clears a ramp-constrained multiperiod market and passes the results to the upper-level problem that optimizes the storage bids. Linearization techniques and Karush–Kuhn–Tucker conditions are used to transform the original problem into an equivalent single-level mixed-integer linear program. Numerical results obtained with the IEEE Reliability Test System demonstrate the benefits of the proposed look-ahead bidding strategy and the importance of considering ramping and network constraints.

Fast and accurate load parameter identification has a large impact on power systems operation and stability analysis. This article proposes a novel Imitation and Transfer Q-learning (ITQ)-based method to identify parameters of composite constant impedance-current-power (ZIP) and induction motor (IM) load models. Firstly, an imitation learning process is introduced to improve the exploitation and exploration processes. Then, a transfer learning method is employed to overcome the challenge of time-consuming optimization when dealing with new identification tasks. An associative memory is designed to realize dimension reduction, knowledge learning and transfer between different identification tasks. Agents can exploit the optimal knowledge from source tasks to accelerate the search rate in new tasks and improve solution accuracy. A greedy action selection rule is adopted for agents to balance the global and local search. The performance of the proposed ITQ approach has been validated on a 68-bus test system. Simulation results in multi-test cases verify that the proposed method is robust and can estimate load parameters accurately. Comparisons with other methods show that the proposed method has superior convergence rate and stability.