# A Bayesian Deep Learning Technique for Multi-Step Ahead Solar Generation Forecasting

Source: [A Bayesian Deep Learning Technique for Multi-Step Ahead Solar Generation Forecasting](<https://www.sota2.com/research/paper/68fa6c0c1e209131cea31b24>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:02:49.336Z

Authors: Devinder Kaur, Shama Naz Islam, Md. Apel Mahmud

Published: 2022-03-21T22:53:05.000Z

## Abstract

In this paper, we propose an improved Bayesian bidirectional long-short term memory (BiLSTM) neural networks for multi-step ahead (MSA) solar generation forecasting. The proposed technique applies alpha-beta divergence for a more appropriate consideration of outliers in the solar generation data and resulting variability of the weight parameter distribution in the neural network. The proposed method is examined on highly granular solar generation data from Ausgrid using probabilistic evaluation metrics such as Pinball loss and Winkler score. Moreover, a comparative analysis between MSA and the single-step ahead (SSA) forecasting is provided to test the effectiveness of the proposed method on variable forecasting horizons. The numerical results clearly demonstrate that the proposed Bayesian BiLSTM with alpha-beta divergence outperforms standard Bayesian BiLSTM and other benchmark methods for MSA forecasting in terms of error performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [PV power production forecasting on Ausgrid](<https://www.sota2.com/research/sota/pv-power-production-forecasting-on-ausgrid.md>): PV power production forecasting; Ausgrid; RMSE: 0.1319.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.11379>)

[PDF](<https://arxiv.org/pdf/2203.11379.pdf>)
