Day-Ahead Optimal Dispatch Strategy for Active Distribution Network Based on Improved Deep Reinforcement Learning
Open Access
- 9 June 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10 (01628828) , 9357-9370
Abstract
Object detection is a fundamental computer vision task that simultaneously predicts the category and localization of the targets of interest. Recently one-stage (also termed “dense”) detectors have gained much attention over two-stage ones due to their simple pipeline and friendly application to end devices. Dense object detectors basically formulate object detection as dense classification and localization (i.e., bounding box regression). The classification is usually optimized by Focal Loss and the box location is commonly learned under Dirac delta distribution. A recent trend for dense detectors is to introduce an individual prediction branch to estimate the quality of localization, which facilitates the classification to improve detection performance. This paper delves into the representations of the above three fundamental elements: quality estimation, classification and localization. Three problems are discovered in existing practices, including (1) the inconsistent usage of the quality estimation and classification between training and inference, (2) the inflexible Dirac delta distribution for localization, and (3) the deficient and implicit guidance for accurate quality estimation. To address these problems, we design new representations for these elements. Specifically, we merge the quality estimation into the class prediction vector to form a joint representation, use a vector to represent arbitrary distribution of box locations, and extract discriminant feature descriptors from the distribution vector for more reliable quality estimation. The improved representations eliminate the inconsistency risk and accurately depict the flexible distribution in real data, but contain continuous labels, which is beyond the scope of Focal Loss. We then propose Generalized Focal Loss (GFocal) that generalizes Focal Loss from its discrete form to the continuous version for successful optimization. Extensive experiments demonstrate the effectiveness of our method, without sacrificing the efficiency both in training and inference. Based on GFocal, we construct a considerably fast and lightweight detector termed NanoDet under mobile settings, which is 1.8 AP higher, 2x faster and 6x smaller than scaled YoloV4-Tiny.Keywords
Funding Information
- National Natural Science Foundation of China (51477091)
This publication has 20 references indexed in Scilit:
- Data-Driven Power Flow Linearization: A Regression ApproachIEEE Transactions on Smart Grid, 2018
- Multistage Adaptive Robust Optimization for the Unit Commitment ProblemOperations Research, 2016
- An Integrated Multiperiod OPF Model With Demand Response and Renewable Generation UncertaintyIEEE Transactions on Smart Grid, 2015
- A Multi Time-Scale and Multi Energy-Type Coordinated Microgrid Scheduling Solution—Part I: Model and MethodologyIEEE Transactions on Power Systems, 2014
- Stochastic Optimization for Unit Commitment—A ReviewIEEE Transactions on Power Systems, 2014
- Robust unit commitment problem with demand response and wind energy2012
- Robust Unit Commitment With Wind Power and Pumped Storage HydroIEEE Transactions on Power Systems, 2011
- Multistage Stochastic Programs2011
- Stochastic Security-Constrained Unit CommitmentIEEE Transactions on Power Systems, 2007
- A stochastic model for the unit commitment problemIEEE Transactions on Power Systems, 1996