| Model Type | Time Series Forecasting |
|---|---|
| Framework | LiteRT (TensorFlow Lite) |
| Algorithm | Fully Connected Neural Network |
| Technical Details | This model uses a fully connected neural network to predict household electricity usage. It is trained on minute-resolution data spanning four years. Inputs are 120 time steps of 7 features, and the output is one step ahead prediction of Global_active_power. Designed for edge deployment using LiteRT (TensorFlow Lite). |
Time Series Forecast for Electricity Consumption
Neural network model for forecasting household electricity consumption using historical time series data.
Leave your message here
Fill the form with the required information
$0.00
Time Series Forecast for Electricity Consumption
app details
Resources
Use Cases
Predictive Maintenance
Anomaly Detection
Supported SECO Devices
AI optimized hardware
Fanless embedded PCs
Modules
supported chipsets
Intel® Core™ i3
Qualcomm® Dragonwing QCS6490
Qualcomm® Dragonwing QCS5430
NXP i.MX 8M Plus
NXP i.MX 95
Performance Benchmark
Hardware
Latency (ms)
Memory Usage
Processing unit
SECO SOM-SMARC-QCS6490
0.813 ms
0.024 MB
CPU
SECO SOM SMARC iMX8Plus
3.86 ms
0.024 MB
CPU
SECO SOM-SMARC-MX95
2.66 ms
0.024 MB
CPU
SECO Titan 300 TGL-UP3 AI
0.311 ms
0.024 MB
CPU
Time Series Anomaly Detection with Isolation Forest
Lightweight anomaly detector for time series data using Isolation Forest, designed for edge environments.
View Model
MiDaS for Monocular Depth Estimation
Efficient single-camera depth estimation using quantized MiDaS v2 model optimized for edge AI deployment.
View Model|
|