# EMForecaster: A Deep Learning Framework for Time Series Forecasting in Wireless Networks with Distribution-Free Uncertainty Quantification

arXiv: https://arxiv.org/abs/2504.00120 · HTML: https://mlsanity.com/paper/2504.00120/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 83 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting](https://mlsanity.com/paper/2205.14415/) (2022)
- [Uncertainty Sets for Image Classifiers using Conformal Prediction](https://mlsanity.com/paper/2009.14193/) (2020)
- [TSMixer: An All-MLP Architecture for Time Series Forecasting](https://mlsanity.com/paper/2303.06053/) (2023)
- [Learning to Embed Time Series Patches Independently](https://mlsanity.com/paper/2312.16427/) (2023)
- [A Survey of Deep Learning and Foundation Models for Time Series Forecasting](https://mlsanity.com/paper/2401.13912/) (2024)
- [Transformer-Based Wireless Traffic Prediction and Network Optimization in O-RAN](https://mlsanity.com/paper/2403.10808/) (2024)
- [Rate-Splitting Multiple Access for Uplink Massive MIMO With Electromagnetic Exposure Constraints](https://mlsanity.com/paper/2212.07028/) (2022)
- [Health Risks Associated with 5G Exposure: A View from the Communications Engineering Perspective](https://mlsanity.com/paper/2006.00944/) (2020)
- [Multivariate Time Series characterization and forecasting of VoIP traffic in real mobile networks](https://mlsanity.com/paper/2307.06645/) (2023)
- [Molecular Absorption-Aware User Assignment, Spectrum, and Power Allocation in Dense THz Networks with Multi-Connectivity](https://mlsanity.com/paper/2408.03451/) (2024)
- [Joint data rate and EMF exposure analysis in Manhattan environments: stochastic geometry and ray tracing approaches](https://mlsanity.com/paper/2301.11097/) (2023)
- [Joint Metrics for EMF Exposure and Coverage in Real-World Homogeneous and Inhomogeneous Cellular Networks](https://mlsanity.com/paper/2302.03559/) (2023)
- [Joint Uplink and Downlink EMF Exposure: Performance Analysis and Design Insights](https://mlsanity.com/paper/2302.04517/) (2023)
- [On the Uplink and Downlink EMF Exposure and Coverage in Dense Cellular Networks: A Stochastic Geometry Approach](https://mlsanity.com/paper/2312.08978/) (2023)
- [Unveiling Passive and Active EMF Exposure in Large-Scale Cellular Networks](https://mlsanity.com/paper/2312.10344/) (2023)

## Built on by (most cited first, 2 of 2)

- [EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting](https://mlsanity.com/paper/2512.15067/) (2025)
- [Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks](https://mlsanity.com/paper/2609.17297/) (2026)

## Abstract (arXiv)

With the recent advancements in wireless technologies, forecasting electromagnetic field (EMF) exposure has become critical to enable proactive network spectrum and power allocation, as well as network deployment planning. In this paper, we develop a deep learning (DL) time series forecasting framework referred to as textitEMForecaster. The proposed DL architecture employs patching to process temporal patterns at multiple scales, complemented by reversible instance normalization and mixing operations along both temporal and patch dimensions for efficient feature extraction. We augment EMForecaster with a conformal prediction mechanism, which is independent of the data distribution, to enhance the trustworthiness of model predictions via uncertainty quantification of forecasts. This conformal prediction mechanism ensures that the ground truth lies within a prediction interval with target error rate α, where 1-α is referred to as coverage. However, a trade-off exists, as increasing coverage often results in wider prediction intervals. To address this challenge, we propose a new metric called the textitTrade-off Score, that balances trustworthiness of the forecast (i.e., coverage) and the width of prediction interval. Our experiments demonstrate that EMForecaster achieves superior performance across diverse EMF datasets, spanning both short-term and long-term prediction horizons. In point forecasting tasks, EMForecaster substantially outperforms current state-of-the-art DL approaches, showing improvements of 53.97% over the Transformer architecture and 38.44% over the average of all baseline models. EMForecaster also exhibits an excellent balance between prediction interval width and coverage in conformal forecasting, measured by the tradeoff score, showing marked improvements of 24.73% over the average baseline and 49.17% over the Transformer architecture.