Menu
Account
Search
Advanced Search
Back to the App List
main product photo

Time Series Forecast for Electricity Consumption

by SECO

Neural network model for forecasting household electricity consumption using historical time series data.

Contact us
$0.00
More Information
Time Series Forecast for Electricity Consumption
app details
Model Type

Time Series Forecasting
Framework

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 TensorFlow Lite.
Use Cases
Predictive Maintenance and Anomaly Detection
Supported IoT 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

Related models

Time Series Anomaly Detection with Isolation Forest
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
MiDaS for Monocular Depth Estimation

Efficient single-camera depth estimation using quantized MiDaS v2 model optimized for edge AI deployment.

 View Model