Gaia —
Temporal Convolutional Geothermal Controller
Gaia optimizes ground-source heat pump systems by predicting optimal ground loop flow rates, compressor staging, and supplemental heat engagement. Named for the Greek earth goddess. The most complex thermal model in the fleet due to the slow thermal dynamics of ground-coupled systems (time constants of hours to days).
Abstract
Background
Gaia optimizes ground-source heat pump systems by predicting optimal ground loop flow rates, compressor staging, and supplemental heat engagement. Named for the Greek earth goddess. The most complex thermal model in the fleet due to the slow thermal dynamics of ground-coupled systems (time constants of hours to days).
Approach
The model was trained in AxonML (a pure-Rust deep learning framework) and compiled through the Hailo Dataflow Compiler (DFC 3.33.1) targeting Hailo-8 silicon. Post-training INT8 quantization was applied during the DFC compilation pass with production telemetry calibration data. The resulting Hailo Executable Format (HEF) binary executes on Hailo’s fixed-function dataflow architecture with deterministic latency and zero framework overhead at the edge.
Results
On production hardware (Hailo-8 M.2 (P/N: HM218B1C2FAE, S/N: HLDDM2A234600289)), Gaia achieves 394 FPS (hw_only) with 2.559 ms hardware latency at 2.13 W average power draw.
Conclusion
Gaia is production-ready as a single HEF binary deployed to edge devices with no external dependencies beyond the HailoRT vendor runtime. The model meets real-time latency requirements for its target hvac optimization application.
| Model | Gaia |
| Domain | HVAC Optimization |
| Architecture | Temporal Convolutional Geothermal Controller |
| Target silicon | Hailo-8 |
| Measured on | Hailo-8 M.2 (P/N: HM218B1C2FAE, S/N: HLDDM2A234600289) |
| DFC compiler | 3.33.1 |
| Framework | AxonML v0.6 (pure-Rust, CUDA + CPU backends) |
| Author | Andrew Jewell Sr. · ORCID 0009-0005-2158-7060 |
| Organization | AutomataNexus LLC · Fort Wayne, Indiana |
Executive overview
Gaia optimizes ground-source heat pump systems by predicting optimal ground loop flow rates, compressor staging, and supplemental heat engagement. Named for the Greek earth goddess. The most complex thermal model in the fleet due to the slow thermal dynamics of ground-coupled systems (time constants of hours to days).
Network I/O
Input: 32-channel geothermal system telemetry. Output: compressor stage + pump speed + supplemental enable.
Architecture
Temporal Convolutional Geothermal Controller
8-layer deep dilated TCN (the deepest in the fleet, needed to capture multi-day ground thermal dynamics). 32 input channels including: ground loop supply/return temps (multiple wells), indoor zone temps, outdoor conditions, compressor run status per unit, reversing valve positions, supplemental heat status, soil temperature probes at multiple depths, and historical load accumulator. Dilation factors extend to 256 to capture weekly patterns. Output predicts compressor staging, loop pump speed, and supplemental heat enable.
Compilation constraints
All AxonML models targeting Hailo silicon are compiled under the fixed-function dataflow constraints: no dynamic control flow, no variable-length dimensions, all activations representable in INT8 after calibration, and no operations requiring dedicated softmax hardware (replaced with ReLU gating or depthwise convolution equivalents where necessary).
Silicon performance
Measured on production hardware via hailortcli benchmark with 5-second sustained inference. Device: Hailo-8 M.2 (P/N: HM218B1C2FAE, S/N: HLDDM2A234600289).
| Metric | Measured Value |
|---|---|
| FPS (hw_only) | 394.12 |
| FPS (streaming) | 394.12 |
| HW Latency | 2.559000 ms |
| Power (streaming avg) | 2.12800 W |
| Power (streaming max) | 2.13500 W |
| Power (idle) | 0.74979 W |
| Quantization | INT8 (post-training, DFC calibration) |
| DFC Compiler | 3.33.1 |
| HailoRT | 4.20.0 |
| Measured On | Hailo-8 M.2 (P/N: HM218B1C2FAE, S/N: HLDDM2A234600289) |
Deployment
Deployed as a single HEF binary. No ONNX runtime, TensorFlow Lite, or Python inference stack required at the edge.
| Target silicon | Hailo-8 |
| Measured on | Hailo-8 M.2 (P/N: HM218B1C2FAE, S/N: HLDDM2A234600289) |
| DFC compiler | 3.33.1 |
| Quantization | INT8 (post-training, production telemetry calibration) |
| Runtime | HailoRT (vendor runtime) |
| Edge platform | Raspberry Pi 5 + Hailo AI HAT+ (M.2 Key M) |
Deployment procedure
Copy the .hef binary to the target device. hailortcli run loads the HEF directly into the Hailo-8 dataflow engine over PCIe. Inference begins immediately with deterministic per-frame latency. No model conversion, graph optimization, or warmup phase required.
References
- Jewell, A. (2026). AxonML: A Pure-Rust Deep Learning Framework for Edge Inference. AutomataNexus LLC. Technical whitepaper.
- Hailo Technologies Ltd. (2024). Hailo Dataflow Compiler User Guide. DFC v3.33.1.
- Hailo Technologies Ltd. (2024). Hailo-8 Product Datasheet.
AutomataNexus LLC · Fort Wayne, Indiana · andrew.jewellsr@automatanexus.com
Andrew Jewell Sr. · ORCID 0009-0005-2158-7060
May 2026 · All rights reserved.