Search Results for author: Yufan Zhang

Found 11 papers, 5 papers with code

Deriving Loss Function for Value-oriented Renewable Energy Forecasting

no code implementations1 Oct 2023 Yufan Zhang, Honglin Wen, Yuexin Bian, Yuanyuan Shi

By integrating it into the upper-level objective for minimizing expected operation cost, we convert the bilevel problem to a single-level one and derive the loss function for training the model.

Fast Constraint Screening for Multi-Interval Unit Commitment

no code implementations12 Sep 2023 Xuan He, Jiayu Tian, Yufan Zhang, Honglin Wen, Yize Chen

Extensive simulations on both specific load samples and load regions validate the proposed technique can screen out more than 80% constraints while preserving the feasibility of multi-interval UC problem.

Value-oriented Renewable Energy Forecasting for Coordinated Energy Dispatch Problems at Two Stages

no code implementations2 Sep 2023 Yufan Zhang, Mengshuo Jia, Honglin Wen, Yuanyuan Shi

To this end, we formulate the forecast model parameter estimation as a bilevel program at the training phase, where the lower level solves the day-ahead and real-time energy dispatch problems, with the forecasts as parameters; the optimal solutions of the lower level are then returned to the upper level, which optimizes the model parameters given the contextual information and minimizes the expected operation cost of the two stages.

LF-PGVIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras using Points and Geodesic Segments

1 code implementation11 Jun 2023 Ze Wang, Kailun Yang, Hao Shi, Yufan Zhang, Zhijie Xu, Fei Gao, Kaiwei Wang

The purpose of our research is to unleash the potential of point-line odometry with large-FoV omnidirectional cameras, even for cameras with negative-plane FoV.

Line Detection

Optimal Vehicle Charging in Bilevel Power-Traffic Networks via Charging Demand Function

no code implementations22 Apr 2023 Yufan Zhang, Sujit Dey, Yuanyuan Shi

Specifically, the power network determines the charging price at various locations, while EVs on the traffic network optimize the charging power given the price, acting as price-takers.

Decision Making

Blockchain Network Analysis: A Comparative Study of Decentralized Banks

1 code implementation11 Dec 2022 Yufan Zhang, Zichao Chen, Yutong Sun, Yulin Liu, Luyao Zhang

We apply core-periphery network features analysis using the transaction data from four decentralized banks, Liquity, Aave, MakerDao, and Compound.

Enabling Fast Unit Commitment Constraint Screening via Learning Cost Model

1 code implementation1 Dec 2022 Xuan He, Honglin Wen, Yufan Zhang, Yize Chen

Unit commitment (UC) are essential tools to transmission system operators for finding the most economical and feasible generation schedules and dispatch signals.

Targeted Demand Response: Formulation, LMP Implications, and Fast Algorithms

no code implementations27 Nov 2022 Yufan Zhang, Honglin Wen, Tao Feng, Yize Chen

Numerical studies demonstrate compared with the benchmarking strategy, the proposed approach can reduce the price to the reference point with less efforts in demand reduction.

Benchmarking

A Contextual Bandit Approach for Value-oriented Prediction Interval Forecasting

no code implementations9 Oct 2022 Yufan Zhang, Honglin Wen, Qiuwei Wu

The numerical study regarding a two-timescale operation of a virtual power plant verifies the superiority of the proposed approach in terms of operational value.

Optimal Adaptive Prediction Intervals for Electricity Load Forecasting in Distribution Systems via Reinforcement Learning

1 code implementation18 May 2022 Yufan Zhang, Honglin Wen, Qiuwei Wu, Qian Ai

Case studies on both load and net load demonstrate that the proposed method can better adapt to data distribution compared with online central PIs method.

Load Forecasting Prediction Intervals +1

DELTA: Dynamically Optimizing GPU Memory beyond Tensor Recomputation

1 code implementation30 Mar 2022 Yu Tang, Chenyu Wang, Yufan Zhang, Yuliang Liu, Xingcheng Zhang, Linbo Qiao, Zhiquan Lai, Dongsheng Li

To the best of our knowledge, we are the first to make a reasonable dynamic runtime scheduler on the combination of tensor swapping and tensor recomputation without user oversight.

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