Combining Physics and Machine Learning for Network Flow Estimation
Authors: Arlei Lopes da Silva, Furkan Kocayusufoglu, Saber Jafarpour, Francesco Bullo, Ananthram Swami, Ambuj Singh
ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirical results show that our method accurately predicts missing flows, outperforming the best baseline, and is able to capture relevant physical properties in traffic and power networks. |
| Researcher Affiliation | Collaboration | Arlei Silva, Furkan Kocayusufoglu Computer Science Department, UC Santa Barbara, CA 93106-5110, USA Saber Jafarpour, Francesco Bullo Mechanical Engineering Department and the Center of Control, Dynamical Systems and Computation, UC Santa Barbara, CA 93106-5070, USA Ananthram Swami U.S. Army Research Lab, Adelphi, MD 20783, USA Ambuj Singh Computer Science Department, UC Santa Barbara, CA 93106-5110, USA |
| Pseudocode | Yes | Algorithm 1 describes our RMD approach for flow estimation. |
| Open Source Code | Yes | Implementation4: We have implemented Algorithm 1 using Py Torch, CUDA, and Higher (Grefenstette et al., 2019), a meta-learning framework that greatly facilitates the implementation of bilevel optimization algorithms by implicitly performing the reverse iterations for a list of optimization algorithms, including SGD. Moreover, our GCN implementation is based on the Deep Graph Library (DGL) (Wang et al., 2019). 4https://github.com/arleilps/flow-estimation |
| Open Datasets | Yes | Traffic: Flow data was collected from the Caltrans the California Department of Transportation Pe MS (Performance Measurement System).1 Sensors are placed at major highways in the state. We use sensor geo-locations and other attributes to approximately match them to a compressed version of road network extracted from Openstreetmap.2 The compression merges any sequence of segments without a branch, as these extra edges would not affect the flow estimation results. We emphasize that this dataset is not of as high quality as Power, due to possible sensor malfunction and matchings of sensors to the wrong road segments. This explains why flow estimation is more challenging in Traffic. Figure 4 is a visualization of our traffic dataset with geographic (lat-long) located vertices and colors indicating light versus heavy traffic (compared to the average). The road segments in the graph (approximately) cover the LA County area. We show the map (from Openstreetmap) of the area covered by our road network in Figure 5. Power: We will provide more details on how we build the power dataset. Py PSA (Python for Power System Analsys) is a toolbox for the simulation of power systems (Brown et al., 2017). We applied the European transmission system (Py PSA-Eur), which covers the ENTSO-E area (H orsch et al., 2018), to generate a single network snapshot. |
| Dataset Splits | Yes | We report results of a 10-fold cross-validation based on the set of labeled flows. Moreover, we use 10% of training flows for validation. |
| Hardware Specification | Yes | Hardware: We ran our experiments on a single machine with 4 NVIDIA Ge Force RTX 2080 GPUs (each with 8Gb of RAM) and 32 Intel Xeon CPUs (2.10GHz and 128Gb of RAM). |
| Software Dependencies | No | The paper mentions 'Py Torch, CUDA, and Higher' and 'Deep Graph Library (DGL)' but does not specify their version numbers. |
| Experiment Setup | Yes | Hyperparameter settings: We have selected the parameters based on RMSE for each method using grid search with learning rate over [100, 10 1, 10 2, 10 3] and number of nodes in the hidden layer over [4, 8, 16]. The total number of iterations was set to 3000 for Min-Div and 5000 for MLP and GCN, all with early stop on convergence after 10 iterations. For our methods (both based on Algorithm 1), we set T = 10, J = 300, α = 10 2, β = 10 2 and K = 10 in all experiments. |