Distributed Energy Trading Supported by Data Analytics

由于大多数温室气体排放与能源生产和使用有关，增加绿色可再生资源是应对气候变化的核心。因此，各国正在制定激进的目标：例如，加拿大的目标是到2030年可再生能源的比例达到90%，丹麦的目标是70%。同时，预计2027年全球能源市场规模将超过5000亿。分布式能源系统已被认为是实现可持续发展的一种方式；然而，太阳能或风能等可再生能源发电的巨大波动性使其集成具有挑战性。分布式能源交易可以帮助平衡供需，同时促进可再生能源发电。基于区块链的解决方案已经被提出，但它们仍然面临着交易吞吐量和透明度下的隐私等挑战。此外，这些技术通常不会利用数据分析带来更好的决策。因此，本项目将设计和开发一个在数据分析支持下的最先进的智能电网对等交易的分布式能源交易系统。这将提高交易决策的质量，促进可再生能源的扩张，并有助于环境的可持续性。这两个主要组成部分是分布式交易平台，用于实现消费者、生产商和生产者之间的交易，以及负荷/发电分析，用于通过数据驱动的决策促进智能交易。该项目将帮助伦敦水电为其客户提供新服务，改进需求响应计划，并促进可再生能源。此外，该项目将帮助加拿大实现其积极的能源目标，并在减少碳足迹和可持续发展方面带来环境效益。能源系统、机器学习和人工智能方面的培训将增强加拿大在这些快速增长领域的优势。

As the majority of greenhouse gas emissions are linked to energy production and use, increasing green renewable resources is at the core of combating climate change. Thus, nations are setting aggressive targets: for example, Canada aims for 90% and Denmark for 70 % renewables by 2030. At the same time, the global energy market is expected to exceed 500 billion in 2027. Distributed energy systems have been recognized as a way of achieving sustainability; however, the immense volatility of renewable energy generation such as solar or wind makes their integration challenging. Distributed energy trading can assist with balancing supply and demand while promoting renewable generation. Blockchain-based solutions have been proposed, but they still face challenges such as transaction throughput and privacy in presence of transparency. Moreover, these techniques typically do not take advantage of data analytics to bring better decisions.Consequently, this project will design and develop a state-of-the-art distributed energy trading system for peer-to-peer transactions in Smart Grid supported by data analytics. This will improve the quality of trading decisions, facilitate the expansion of renewables, and contribute to environmental sustainability. The two main components are Distributed Trading Platform for enabling transactions between consumers, producers, and prosumers, and Load/Generation analytics for facilitating smart trading through data-driven decisions.This project will help London Hydro to provide new services to its customers, improve demand-response programs, and promote renewables. Moreover, this project will help Canada to reach its aggressive energy targets and deliver environmental benefits in terms of reduced carbon footprint and sustainability. Training in energy systems, machine learning, and artificial intelligence will build Canada's strengths in these fast-growing fields.