提升电力系统中分布式能源预测的联邦学习精度与收敛速度。
Improving accuracy and convergence of federated learning edge computing methods for generalized DER forecasting applications in power grid
- 采用分层与迭代聚类改进非独立同分布数据下的性能
- 针对时序数据设计更合适的全局模型，加快收敛
- 融合电力系统知识，构建可泛化至多种能源的框架
本研究旨在开发更准确、收敛更快且通信开销更低的联邦学习（FL）方法，专门用于现代低碳电网中分布式能源资源（DER）的预测，包括可再生能源、储能和负荷。通过（i）利用近期发展的联邦学习扩展技术，如分层与迭代聚类，以应对非独立同分布（non-IID）数据问题；（ii）试验适用于时序数据的不同类型联邦全局模型；（iii）融入电力系统领域知识，构建更具通用性的联邦学习框架与架构，使其不仅适用于负荷预测，还能推广到多种类型的分布式能源资源，并支持异构客户端。该方法致力于提升预测准确性与系统效率。
原文摘要 · Abstract (English)
This proposal aims to develop more accurate federated learning (FL) methods with faster convergence properties and lower communication requirements, specifically for forecasting distributed energy resources (DER) such as renewables, energy storage, and loads in modern, low-carbon power grids. This will be achieved by (i) leveraging recently developed extensions of FL such as hierarchical and iterative clustering to improve performance with non-IID data, (ii) experimenting with different types of FL global models well-suited to time-series data, and (iii) incorporating domain-specific knowledge from power systems to build more general FL frameworks and architectures that can be applied to diverse types of DERs beyond just load forecasting, and with heterogeneous clients.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。