Disruptive platform to accelerate renewable energy with machine learning and grid data analytics

需要迅速增加对可再生能源技术的投资，以满足世界未来的能源供应，同时减少相关的温室气体排放。气候变化委员会估计，可再生能源装机容量需要翻两番才能实现净零。然而，可再生能源项目是资本密集型的，成本和回报取决于大量因素，如位置和可再生资源。可再生能源（太阳能/风能/储能）项目成功互联的一个主要障碍是缺乏关于电网网络/条件的信息，以及资本和运营成本的不可预测性。这意味着投资者必须估计项目的连接成本，这是有风险和不准确的，并导致重大的投资不确定性。为了应对这一挑战，Enian与爱丁堡大学的学者合作开发了一个可再生能源交易管理和协作平台，该平台有助于简化项目资格，并使用专有算法预测可再生能源项目成本（LCOE，年度能源产出，技术，经济指标）。虽然证明是有用的，但为了满足明确的行业需求并克服主要的投资障碍，技术的先进性至关重要。拟议项目将在这一早期成果的基础上，开发能够以数字方式捕获、计算和可视化电网数据的能力，以便使用机器增强的自动化流程为单个互连点/集成网络生成成本预测模型，从而提供第一个数据驱动的可再生能源分析平台，使并网太阳能光伏、风能和储能的运营成本能够快速准确地确定，为改进和降低可再生能源规划和投资风险提供独特的可扩展解决方案。已经对早期可行性进行了调查，该项目将概念推进到TRL 5。影响包括改善、降低风险和加速决策，从而增加投资（支持的可再生能源项目增加约30%）;在项目尽职调查中节省宝贵的时间和成本（20周，每家公司每年50万英镑）;由于更多的可再生能源项目获得投资，5年内节省了100万吨二氧化碳当量。更广泛地适用于其他电力（垃圾发电、水电）、商业地产/土地、废物管理/回收、电气化运输（电动汽车充电网络）。该项目将为主要申请人Enian带来显著的出口导向型增长，可观的投资回报率，增加就业机会和进一步的研发投资机会。项目合作伙伴爱丁堡大学将获得关键的商业知识，应用于未来的研发。

Investment in renewable technologies will need to rapidly increase in order to meet the world's future energy supply while reducing the associated greenhouse gas emissions. The Committee on Climate Change estimates that the installed renewable energy (RE) capacity needs to be quadrupled to achieve net zero. However, renewable energy projects are capital intensive and the costs and returns depend on a large number of factors such as location and renewable resource. A major barrier to successful interconnection of renewable energy (solar/wind/storage) projects is the lack of information on the grid network/conditions and unpredictability of capital and operational costs. This means investors must estimate the connection cost of projects which is risky and inaccurate and leads to major investment uncertainty.To address this challenge, Enian, in collaboration with academics from the University of Edinburgh, have developed a RE Deal Management and Collaboration Platform which helps streamline project qualification and uses proprietary algorithms to predict RE project costs (LCOE, annual energy output, technical, economic metrics). Although proving useful, to meet expressed industry demand and overcome major investment barriers, it is critical that that the technology is advanced. The proposed project will build on this early achievement to develop the capability to enable power grid data to be digitally captured, calculated and visualised to produce cost prediction models for single interconnection points/integrated networks using machine-enhanced automated processes, thus providing the first data-driven RE analytics platform that enables operational costs of grid-connected solar PV, wind and storage to be rapidly and accurately determined, offering a unique scalable solution for improved and de-risked RE planning and investment. Early feasibility has been investigated, this project advancing the concept to TRL5\.Impacts include improved, de-risked, and accelerated decision making leading to increased investments (~30% more RE projects supported); valuable time and cost savings in project due diligence (20 weeks, £500k per year per company); \>1M tonnes CO2e saved over 5 years due to more RE projects gaining investment. Wider applicability to other power (waste-to-energy, hydro), commercial property/land, waste management/recycling, electrified transport (EV charging networks). The project will deliver significant export led growth for lead applicant Enian, a substantial ROI, increased employment and further opportunity for R&D investment. Project partner the University of Edinburgh will gain crucial commercial knowledge to be applied to future R&D.