用锚定集成LSTM实现精准且可信的电动车能耗预测。
Bayesian Uncertainty Quantification with Anchored Ensembles for Robust EV Power Consumption Prediction
- 采用锚定集成LSTM与t分布似然，同时捕捉模型和数据不确定性。
- 测试误差RMSE为3.36±1.10，预测区间覆盖率接近理论值。
- 无需蒙特卡洛采样，单次前向传播即可完成推理，适合实时部署。
准确的电动车能耗估计是续航预测与能源管理的基础，但实际应用既需点估计精度，也需可信赖的不确定性量化。本文提出一种锚定集成长短期记忆网络（LSTM），结合学生t分布似然，联合建模认知不确定性（模型）与随机不确定性（数据）。锚定通过高斯权重先验（最大后验训练）实现后验式多样性，无需测试时采样；t分布头提供重尾鲁棒性与闭式预测区间。基于车辆运动时序数据（如速度、电机转速），模型在测试集上达到RMSE 3.36±1.10、MAE 2.21±0.89、R²=0.93±0.02，解释方差0.93±0.02，且不确定性带校准良好，覆盖率接近名义水平。相比竞争基线（t分布蒙特卡洛丢弃；带/不带锚定的分位数回归），本方法在相同覆盖下产生更紧致的区间，且对数评分更优。关键优势在于：每成员仅需一次确定性前向传播（或加权平均坍缩），彻底消除蒙特卡洛延迟，适用于实时系统。结果是一个紧凑、理论严谨的估计算子，兼顾准确性、校准性与系统效率，支持生产级电动车能量管理中的可靠续航估计与决策。
原文摘要 · Abstract (English)
Accurate EV power estimation underpins range prediction and energy management, yet practitioners need both point accuracy and trustworthy uncertainty. We propose an anchored-ensemble Long Short-Term Memory (LSTM) with a Student-t likelihood that jointly captures epistemic (model) and aleatoric (data) uncertainty. Anchoring imposes a Gaussian weight prior (MAP training), yielding posterior-like diversity without test-time sampling, while the t-head provides heavy-tailed robustness and closed-form prediction intervals. Using vehicle-kinematic time series (e.g., speed, motor RPM), our model attains strong accuracy: RMSE 3.36 +/- 1.10, MAE 2.21 +/- 0.89, R-squared = 0.93 +/- 0.02, explained variance 0.93 +/- 0.02, and delivers well-calibrated uncertainty bands with near-nominal coverage. Against competitive baselines (Student-t MC dropout; quantile regression with/without anchoring), our method matches or improves log-scores while producing sharper intervals at the same coverage. Crucially for real-time deployment, inference is a single deterministic pass per ensemble member (or a weight-averaged collapse), eliminating Monte Carlo latency. The result is a compact, theoretically grounded estimator that couples accuracy, calibration, and systems efficiency, enabling reliable range estimation and decision-making for production EV energy management.
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。