AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Data Sharing and Compression for Cooperative Networked Control

Jiangnan Cheng, Marco Pavone, Sachin Katti, Sandeep P. Chinchali, Ao Tang

NeurIPS 2021 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Co-design compressed forecasts with the controller's task objective instead of optimizing only prediction MSEMPC on IoT sensor data · IoT sensor datacontrol cost: within 5 % of the optimal cost; 15×Improved
Co-design compressed forecasts with the controller's task objective instead of optimizing only prediction MSEMPC on cell traffic data · Cell traffic datacontrol cost: within 5 % of the optimal cost; 15×Improved
Co-design compressed forecasts with the controller's task objective instead of optimizing only prediction MSEMPC on battery data · Battery datacontrol cost: within 5 % of the optimal cost; 96×Improved
Use task-agnostic MSE forecasting instead of task-aware co-designMPC on IoT, cell traffic, and battery data · IoT, cell traffic, and battery datacontrol cost at the same bottleneck size: at least 25% more control costHurt
Use task-agnostic MSE forecasting rather than task-aware co-designMPC on IoT sensor data · IoT sensor datadata transmitted to reach within 5% of optimal cost: 88 % less data with our approachHurt
Use task-agnostic MSE forecasting rather than task-aware co-designMPC on battery data · Battery datadata transmitted to reach within 5% of optimal cost: 82 % less data with our approachHurt
Use task-agnostic MSE forecasting rather than task-aware co-designMPC on cell traffic data · Cell traffic datacontrol cost relative to optimal: 100% more cost than the optimalHurt
Add prediction-error regularization to fully task-aware co-design (weighted approach) (ablation)Co-designed MPC forecaster · IoT, cell traffic, and battery dataforecasting error in the near futureImproved
Add prediction-error regularization to fully task-aware co-design (weighted approach) (ablation)Co-designed MPC forecaster · IoT, cell traffic, and battery databottleneck size needed for control performance: marginally larger representationHurt
Remove the prediction-error penalty (fully task-aware, λF = 0) (ablation)Co-designed MPC forecaster · IoT, cell traffic, and battery dataforecast qualityHurt
Use an LSTM forecaster instead of a feedforward forecaster, or vice versa (ablation)Co-designed forecaster · IoT, cell traffic, and battery dataperformanceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy