Search Results for author: Di Shi

Found 10 papers, 0 papers with code

Rethink AI-based Power Grid Control: Diving Into Algorithm Design

no code implementations23 Dec 2020 Xiren Zhou, Siqi Wang, Ruisheng Diao, Desong Bian, Jiahui Duan, Di Shi

Recently, deep reinforcement learning (DRL)-based approach has shown promisein solving complex decision and control problems in power engineering domain. In this paper, we present an in-depth analysis of DRL-based voltage control fromaspects of algorithm selection, state space representation, and reward engineering. To resolve observed issues, we propose a novel imitation learning-based approachto directly map power grid operating points to effective actions without any interimreinforcement learning process.

Imitation Learning

On Training Effective Reinforcement Learning Agents for Real-time Power Grid Operation and Control

no code implementations11 Dec 2020 Ruisheng Diao, Di Shi, Bei Zhang, Siqi Wang, Haifeng Li, Chunlei Xu, Tu Lan, Desong Bian, Jiajun Duan

Deriving fast and effectively coordinated control actions remains a grand challenge affecting the secure and economic operation of today's large-scale power grid.

Optimization and Control Systems and Control Systems and Control

Evaluating Load Models and Their Impacts on Power Transfer Limits

no code implementations7 Aug 2020 Xinan Wang, Yishen Wang, Di Shi, Jianhui Wang, Siqi Wang, Ruisheng Diao, Zhiwei Wang

Since the load dynamics have substantial impacts on power system transient stability, load models are one critical factor that affects the power transfer limits.

Q-Learning

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

no code implementations8 Nov 2019 Xinan Wang, Yishen Wang, Di Shi, Jianhui Wang, Zhiwei Wang

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.

Q-Learning

Autonomous Voltage Control for Grid Operation Using Deep Reinforcement Learning

no code implementations24 Apr 2019 Ruisheng Diao, Zhiwei Wang, Di Shi, Qianyun Chang, Jiajun Duan, Xiaohu Zhang

Modern power grids are experiencing grand challenges caused by the stochastic and dynamic nature of growing renewable energy and demand response.

Short-term Load Forecasting at Different Aggregation Levels with Predictability Analysis

no code implementations26 Mar 2019 Yayu Peng, Yishen Wang, Xiao Lu, Haifeng Li, Di Shi, Zhiwei Wang, Jie Li

Short-term load forecasting (STLF) is essential for the reliable and economic operation of power systems.

Load Forecasting

Probabilistic Load Forecasting via Point Forecast Feature Integration

no code implementations26 Mar 2019 Qicheng Chang, Yishen Wang, Xiao Lu, Di Shi, Haifeng Li, Jiajun Duan, Zhiwei Wang

In the first stage, all related features are utilized to train a point forecast model and also obtain the feature importance.

Feature Importance Load Forecasting

Submodular Load Clustering with Robust Principal Component Analysis

no code implementations20 Feb 2019 Yishen Wang, Xiao Lu, Yiran Xu, Di Shi, Zhehan Yi, Jiajun Duan, Zhiwei Wang

Traditional load analysis is facing challenges with the new electricity usage patterns due to demand response as well as increasing deployment of distributed generations, including photovoltaics (PV), electric vehicles (EV), and energy storage systems (ESS).

Load Forecasting

A Neural-Network-Based Optimal Control of Ultra-Capacitors with System Uncertainties

no code implementations29 Nov 2018 Jiajun Duan, Zhehan Yi, Di Shi, Hao Xu, Zhiwei Wang

Conventional control strategies usually produce large disturbances to buses during charging and discharging (C&D) processes of UCs, which significantly degrades the power quality and system performance, especially under fast C&D modes.

A Rprop-Neural-Network-Based PV Maximum Power Point Tracking Algorithm with Short-Circuit Current Limitation

no code implementations29 Nov 2018 Yao Cui, Zhehan Yi, Jiajun Duan, Di Shi, Zhiwei Wang

This paper proposes a resilient-backpropagation-neural-network-(Rprop-NN) based algorithm for Photovoltaic (PV) maximum power point tracking (MPPT).

Cannot find the paper you are looking for? You can Submit a new open access paper.