---
license: mit
pipeline_tag: time-series-forecasting
metrics:
- accuracy
- mae
- mape
---


# Model Card for DMP-PCFC

<!-- Provide a quick summary of what the model is/does. -->

Advanced neural architecture , DMP-PCFC is an interpretable and accurate model for multi-step energy loads prediction in integrated energy systems, 
or the broader task of time series forecasting.

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->


- **Developed by:**  Xingyu Liang and Min Xia.
- **Model type:**  DMP-PCFC (Dual-Resolution Channel Multi-Period Cross Reconstruction Parallel Closed-Form Continuous-Time Network)
- **Language(s) (NLP):**  Not applicable 
- **License:**  MIT License
- **Finetuned from model [optional]:**  Original implementation

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/nuist-xf/DMP-PCFC


## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

Energy engineers and researchers can do so directly using the DMP-PCFC framework:
- Multi-energy load forecasting for integrated energy systems (electricity, cooling, heat)
- Multi-resolution dynamic capture and long-term trend analysis
- Interpretable feature interaction analysis based on biological neuron dynamics
- Predicting sudden changes in energy demand patterns under extreme climate events such as hurricanes and heat waves
- Provides highly accurate input signals for demand response systems


### Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

- Smart Grid Real-Time Dispatch System
- Energy consumption optimisation for industrial IoT devices
- Assessing the carbon reduction potential of renewable energy alternatives

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

- Non-periodic time series forecasting (e.g., sudden event detection)
- Non-energy sector forecasts (e.g., financial time series)
- Unstructured data processing such as image/text

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

- Training data limitations: current validation of an IES system based on climatic conditions in Arizona, USA

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
- Recommended for migrated learning in conjunction with local data

## How to Get Started with the Model

All data acquisition, preprocessing, loading, hyperparameters of the model, inference speed, 
number of parameters and the rest of the relevant content about the experiment have been presented in the repository： https://github.com/nuist-xf/DMP-PCFC


## Training Details

### Training Data

More Information Needed

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

### Training Procedure

More Information Needed

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Training Hyperparameters

- **Training regime:** More Information Needed
  
#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

More Information Needed

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

More Information Needed

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

More Information Needed

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

More Information Needed

### Results

More Information Needed

#### Summary

More Information Needed

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

- **Hardware Type:** NVIDIA GeForce RTX 3090
- **Hours used:** More Information Needed
- **Cloud Provider:** More Information Needed
- **Compute Region:** More Information Needed
- **Carbon Emitted:** More Information Needed


## Model Card Authors

**Xingyu Liang**

## Model Card Contact
For technical support or data access requests:
- **Liguo Weng**  
  📧 002311@nuist.edu.cn 
  🏛 Nanjing University of Information Science & Technology