Structural statistical learning of heterogeneous preferences for smart energy choices with a case study on coordinated electric vehicle charging

智能能源选择异构偏好的结构统计学习以及协调电动汽车充电的案例研究

• 批准号: 2342215
• 负责人: Ricardo Daziano
• 金额: $ 39.04万
• 依托单位: Cornell University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-03-15 至 2027-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2342215&HistoricalAwards=false
• 关键词: Structural; statistical; learning; heterogeneous; preferences

This project is developing user-friendly tools to guide optimal choices about clean energy, especially regarding charging electric vehicles (EVs). Efforts focus on creating simple and efficient computer algorithms capable of learning from real-world data to suggest ideal charging times and conditions for EVs. The significance lies in users adapting to increasingly complex energy environments, adopting more sustainable options and behaviors, and gaining more control over energy use. The project centers on EVs as integral to reducing carbon emissions from transportation. Despite significant advancements in battery and charging technologies, there are many challenges in planning how EVs are charged, and the situation is poised to worsen with the expected increasing penetration of electrified transportation. The aim is to ensure these tools will be accessible to all EV users, focusing not only on making charging recommendations that promote the use of renewable energy but also on considering individual preferences and potential benefits to the entire energy system. The ultimate objective is to simplify decision-making, making it easier for users to manage energy consumption in optimal ways without feeling overwhelmed. Advanced statistical techniques are employed, utilizing highly efficient computer algorithms that will ensure speed, flexibility, interpretability, and real-world policy relevance. The proposed system adapts and learns charging preferences in real-time, providing energy management recommendations in the context of coordinated EV charging while considering factors such as electricity demand, pricing, and grid stability. The methodical modular Markov chain fast and scalable sampler of the proposed incentive-compatible recommender system is designed by integrating: an expansion of Ultimate Pólya-Gamma data augmentation for multi-index choice models to create conjugacy where it does not exist, amortized and non-factorized variational inference for efficiency, Choquet aggregation for complex nonparametric tradeoffs across service features (relaxing linear compensatory behavior), Bayes endogeneity controls, Bayesian optimization for tuning hyperparameters and for integration with a system equilibrium algorithm, and flexible semiparametric representation of heterogeneity in preferences and motives between and within strategic agents. The research team implements the project through an actual residential program for coordinated scheduling of electric-vehicle charging, such as avoiding in-force price endogeneity and constraints via self-selection price discrimination through discrete targeted bundles. In simpler terms, a helpful guide is created for individuals driving electric vehicles, suggesting ideal charging times and needs based on their preferences and driving patterns. Smart technology is employed to gather information, enabling the provision of personalized suggestions to users. The impact of the project extends beyond individual assistance, contributing to the overall sustainability of energy systems and providing valuable tools for energy-related organizations, utilities, and policymakers.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该项目正在开发用户友好的工具，以指导关于清洁能源的最佳选择，特别是关于充电电动汽车(EVS)。努力的重点是创造简单而高效的计算机算法，能够从真实世界的数据中学习，为电动汽车提供理想的充电时间和条件。其意义在于用户适应日益复杂的能源环境，采用更可持续的选择和行为，并获得对能源使用的更多控制。该项目以电动汽车为中心，将其作为减少交通运输碳排放的不可或缺的一部分。尽管电池和充电技术取得了重大进步，但在规划电动汽车充电方式方面仍存在许多挑战，随着电动交通的预期普及率不断提高，情况可能会变得更糟。其目的是确保所有电动汽车用户都可以使用这些工具，不仅专注于提出促进使用可再生能源的充电建议，而且还考虑到个人偏好和对整个能源系统的潜在好处。最终目标是简化决策，使用户更容易以最佳方式管理能源消耗，而不会感到不知所措。采用先进的统计技术，利用高效的计算机算法，确保速度、灵活性、可解释性和现实世界的政策相关性。该系统实时适应和学习充电偏好，在考虑电力需求、定价和电网稳定性等因素的同时，在协调电动汽车充电的背景下提供能源管理建议。提出的激励相容推荐系统的方法论模块化马尔可夫链快速和可扩展采样器的设计是通过集成：对多指标选择模型的终极Pólya-Gamma数据增强进行扩展以在不存在的情况下创建共轭、用于效率的分期和非因式变分推理、用于服务特征之间的复杂非参数权衡(放松线性补偿行为)的Choket聚集、贝叶斯内生性控制、用于调整超参数的贝叶斯优化以及用于与系统均衡算法集成的贝叶斯优化以及策略代理之间和策略代理内部偏好和动机的异质性的灵活半参数表示。研究团队通过一个用于电动汽车充电协调调度的实际住宅项目来实施该项目，例如通过离散的目标捆绑避免有效的价格内生性和通过自我选择的价格歧视而产生的约束。简而言之，为驾驶电动汽车的个人创建了一个有用的指南，根据他们的偏好和驾驶模式建议理想的充电时间和需求。智能技术被用于收集信息，从而能够向用户提供个性化的建议。该项目的影响超越了个人援助，有助于能源系统的整体可持续性，并为能源相关组织、公用事业公司和政策制定者提供了宝贵的工具。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。