Two-stage WECC Composite Load Modeling: A Double Deep Q-Learning Networks Approach

TL;DR

This paper introduces a novel two-stage deep reinforcement learning framework to efficiently identify and calibrate the complex parameters of the WECC composite load model, improving accuracy in power system stability analysis.

Contribution

It presents a systematic, data-driven approach using double deep Q-learning to decompose and calibrate the complex WECC CLM without explicit model details.

Findings

Effective load composition determination via DDQN

Parameter selection closely matches true transient responses

Framework verified on IEEE 39-bus system

Abstract

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.