# End-to-End Demand Response Model Identification and Baseline Estimation with Deep Learning

arXiv: https://arxiv.org/abs/2109.00741 · HTML: https://mlsanity.com/paper/2109.00741/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 2 Sep 2021.

## Builds on (most cited first, 10 of 10)

- [OptNet: Differentiable Optimization as a Layer in Neural Networks](https://mlsanity.com/paper/1703.00443/) (2017)
- [On the Differentiability of the Solution to Convex Optimization Problems](https://mlsanity.com/paper/1804.05098/) (2018)
- [A Time-Series Distribution Test System Based on Real Utility Data](https://mlsanity.com/paper/1906.04078/) (2019)
- [Forecasting the Price-Response of a Pool of Buildings via Homothetic Inverse Optimization](https://mlsanity.com/paper/2004.09819/) (2020)
- [Three-Party Energy Management With Distributed Energy Resources in Smart Grid](https://mlsanity.com/paper/1406.5794/) (2014)
- [A Contract Design Approach for Phantom Demand Response](https://mlsanity.com/paper/1611.09788/) (2016)
- [A Hierarchical Approach to Multi-Energy Demand Response: From Electricity to Multi-Energy Applications](https://mlsanity.com/paper/2005.02339/) (2020)
- [A Sparse Linear Model and Significance Test for Individual Consumption Prediction](https://mlsanity.com/paper/1511.01853/) (2015)
- [Demand Response in the Smart Grid: the Impact of Consumers Temporal Preferences](https://mlsanity.com/paper/1711.11304/) (2017)
- [A Lagrangian Policy for Optimal Energy Storage Control](https://mlsanity.com/paper/1901.09507/) (2019)

## Built on by (most cited first, 3 of 3)

- [A Hybrid PCA-PR-Seq2Seq-Adam-LSTM Framework for Time-Series Power Outage Prediction](https://mlsanity.com/paper/2509.16743/) (2025)
- [Laxity-Aware Scalable Reinforcement Learning for HVAC Control](https://mlsanity.com/paper/2306.16619/) (2023)
- [Reliable Grid Forecasting: State Space Models for Safety-Critical Energy Systems](https://mlsanity.com/paper/2601.01410/) (2026)

## Abstract (arXiv)

This paper proposes a novel end-to-end deep learning framework that simultaneously identifies demand baselines and the incentive-based agent demand response model, from the net demand measurements and incentive signals. This learning framework is modularized as two modules: 1) the decision making process of a demand response participant is represented as a differentiable optimization layer, which takes the incentive signal as input and predicts user's response; 2) the baseline demand forecast is represented as a standard neural network model, which takes relevant features and predicts user's baseline demand. These two intermediate predictions are integrated, to form the net demand forecast. We then propose a gradient-descent approach that backpropagates the net demand forecast errors to update the weights of the agent model and the weights of baseline demand forecast, jointly. We demonstrate the effectiveness of our approach through computation experiments with synthetic demand response traces and a large-scale real world demand response dataset. Our results show that the approach accurately identifies the demand response model, even without any prior knowledge about the baseline demand.