用音乐框架解决电动车充电数据的三大问题，让分析结果更可信。
The Note-Chord-Voice Framework: Structured Source Separation and Causal Inference for EV Charging Data
- 分阶段处理：清洗、模式发现、源分离、因果推断各司其职，可验证
- 在江门数据集上，模型拟合度达R²=0.9921，识别出两个价格敏感群体
- 能区分稳定与临时价格响应者，适合政策制定者优化充电补贴
真实世界电动车充电数据存在三大互锁缺陷：硬件碎片化（网络超时和计费重置导致会话分裂）、物理矛盾（独立能量/时长模型产生不可能状态，如7kW充电器10分钟充50kWh）、 collider 偏倚（基于治疗后结果聚类打开反向路径，影响价格弹性判断）。本文提出音乐启发的Note-Chord-Voice框架，将数据清洗（修复和弦）、结构模式发现（和声和弦）、描述性源分离（非负矩阵分解，NMF 音色）、因果推断划分为可验证阶段。核心创新包括：(i) 虚假检验门（A1-A5, G3, G10）用于建模前测试数据适用性；(ii) Gamma初始化的NMF结合输入重缩放，提升来自季节趋势分解（STL）的收敛稳定性；(iii) 基于标签的优惠券分级（A/B/C/D），隔离准随机干预与夜间混杂因素及定向促销；(iv) 分音色分别进行普通最小二乘法（OLS）以避免单纯形共线性；(v) Foote新颖度曲线用于结构区间检测。应用于江门数据集（495,707条会话，20个站点，2024年7月至2025年3月），所有核心公理通过，仅G3（无强168小时周期）例外。NMF达到R²=0.9921；物理约束的时长模型整体拟合度为R²=0.5409。两个音色对价格敏感（β = -11 至 -14 分钟，p<0.001），其中一个是稳定的（音色3，β=-14.16），另一个是干预驱动的（音色1，β=-11.10）；仅稳定音色支持因果结论。反事实模拟显示，针对价格敏感音色投放折扣可回收52.8%折扣支出（约每年0.85百万人民币）；仅限单一稳定价格敏感音色则给出更保守估计。
原文摘要 · Abstract (English)
Real-world EV charging data exhibit three interlocking pathologies: hardware fragmentation (network timeouts and billing resets split sessions), physical violations (independent energy/duration models produce impossible states like 50 kWh in 10 min on a 7 kW charger), and collider bias (clustering on post-treatment outcomes opens backdoor paths for price elasticity). We propose the Note-Chord-Voice framework, a music-inspired, axiom-driven pipeline that separates data cleaning (Repair Chords), structural pattern discovery (Harmonic Chords), descriptive source separation (NMF Voices), and causal inference into distinct, falsifiable stages. Key innovations: (i) falsification gates (A1-A5, G3, G10) that test data suitability before modeling; (ii) Gamma-initialized NMF with input rescaling for convergence stability from STL decomposition; (iii) tag-based coupon grading (A/B/C/D) to isolate quasi-random treatment from night-time confounders and targeted promotions; (iv) separate per-voice OLS to avoid simplex collinearity; (v) Foote novelty curves for structural regime detection. Applied to the Jiangmen dataset (495,707 sessions, 20 stations, from July 2024 to March 2025), all core axioms pass except G3 (no strong 168 h cycle). NMF achieves R^2=0.9921; the physically constrained duration model yields aggregate R^2=0.5409. Two voices are price-sensitive (beta = -11 to -14 min, p<0.001), of which one is stable (Voice 3, beta=-14.16) and one treatment-driven (Voice 1, beta=-11.10); only the stable voice supports causal claims. Counterfactual simulation shows targeting discounts to price-sensitive voices recovers 52.8% of discount expenditures (~0.85M CNY/year); restricting to the single stable price-sensitive voice yields a more conservative estimate.
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。