Load forecasting for energy communities: a novel LSTM-XGBoost hybrid model based on smart meter data

Semmelmann, Leo; Henni, Sarah; Weinhardt, Christof

doi:10.1186/s42162-022-00212-9

Cited by 14 publications

(12 citation statements)

References 46 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ndings demonstrated that machine learning models presented promising results. Semmelmann et al [34] presented a novel hybrid bi-directional LSTM-XGBoost model for energy load forecasting. The results indicated that the performance analysis of the hybrid model outperformed traditional energy load forecasting.…”

Section: Literature Reviewmentioning

confidence: 99%

Daily Scale Streamflow Forecasting Based-Hybrid Gradient Boosting Machine Learning Model

Kilinç

Ahmadianfar²,

Demir

et al. 2023

Preprint

View full text Add to dashboard Cite

Hybrid model selection built with models based on machine learning (ML) and Deep learning (DL) has a significant impact on river flow predictions. Sustainable use of water resources is possible with the evaluation of basin management principles, effective natural resource management and correct water resources planning. These conditions require accurate estimation of the flows of rivers in the basin. In this study, river flow estimation was made with daily streamflow data from E12A057 (Adatepe), E12A24 (Aktaş) and E12A22 (Rüstümköy) flow measurement stations (FMSs) determined on the critical points of Sakarya Basin, which is among the important basins of Turkey. For three stations, 10 years of flow data obtained from EIEI (General Directorate of Electrical Works Survey Administration) were used. In addition, a method combining the GA-CatBoost model was proposed, which aimed to improve the performance of flow estimation. The performance of the hybrid model was compared to the CatBoost, Long-Short Term Memory (LSTM) and Linear Regression (LR) models. To analyze the performance of the model, the first 80% of the data was used for training and the remaining 20% for testing the three FMS. The results revealed that the proposed hybrid model can adapt nicely with the high nonlinearity of the river flow estimation. It has been observed that the hybrid model was superior to other models in statistical measurement metrics used in the study.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Daily Scale Streamflow Forecasting Based-Hybrid Gradient Boosting Machine Learning Model

Kilinç

Ahmadianfar²,

Demir

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…For the planning and operation of modern power systems and distribution grids, the forecasting and subsequent reduction of peak loads are essential [18,19]. Besides the fact that the before-mentioned studies are focused on an overall load forecast, several studies emphasise the tendency of neural network-based approaches to underestimate peak loads [7,20,21]. Hence, the authors in ref.…”

Section: Related Workmentioning

confidence: 99%

“…The authors in ref. [7] pursue another approach by combining LSTMs with a dedicated peak time and peak load XGBoost forecast. Thereby, the overall load and peak load forecasting accuracy are improved.…”

Section: Related Workmentioning

confidence: 99%

“…The parameter max _depth is discreet and thus rounded before use. We derive the parameters from past XGBoost-based load forecasting studies [7,58,59].…”

Section: Bayesian Hyperparameter Tuningmentioning

confidence: 99%

“…As peaks constitute the maximum strain on the grid, predicting the maximum load and especially the timing of peaks is crucial for the grid stability. Yet, most approaches in the discipline of electrical peak demand forecasting are either concerned with only predicting the peak load quantity [5] or the peak time forecast is inferred from an overall load forecast by considering the time when the predicted load curve is at its maximum [6,7]. As a high general prediction accuracy does not necessarily imply a good prediction quality concerning peak loads and peak times [7], further research specifically about peak times is necessary.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Privacy‐preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineering

Semmelmann,

Resch,

Henni

et al. 2023

IET Smart Grid

View full text Add to dashboard Cite

In modern power systems, predicting the time when peak loads will occur is crucial for improving efficiency and minimising the possibility of network sections becoming overloaded. However, most works in the load forecasting field are not focusing on a dedicated peak time forecast and are not dealing with load data privacy. At the same time, developing methods for forecasting peak electricity usage that protect customers' data privacy is essential since it could encourage customers to share their energy usage data, leading to more data points for the effective management and planning of power grids. Hence, the authors employ a dedicated Learning to Rank XGBoost algorithm to forecast peak times with only ranks of loads instead of absolute load magnitudes as input data, thereby offering potential privacy‐preserving properties. We show that the presented Learning to Rank XGBoost model yields comparable results to a benchmark XGBoost load forecasting model. Additionally, we describe our extensive feature engineering process and a state‐of‐the‐art Bayesian hyperparameter optimisation for selecting model parameters, which leads to a significant improvement of forecasting accuracy. Our method was used in the context of the final round of the international BigDEAL load forecasting challenge 2022, where we consistently achieved high‐ranking results in the peak time track and an overall fourth rank in the peak load forecasting track with our general XGBoost model.

show abstract

Design of Encoded and Tunable Graphene-Gold Metasurface-Based Surface Plasmon Resonance Sensors for Glucose Detection in the Terahertz Regime

Anushkannan,

Wekalao,

Patel

et al. 2024

Plasmonics

View full text Add to dashboard Cite

Load forecasting for energy communities: a novel LSTM-XGBoost hybrid model based on smart meter data

Cited by 14 publications

References 46 publications

Daily Scale Streamflow Forecasting Based-Hybrid Gradient Boosting Machine Learning Model

Daily Scale Streamflow Forecasting Based-Hybrid Gradient Boosting Machine Learning Model

Privacy‐preserving peak time forecasting with Learning to Rank XGBoost and extensive feature engineering

Design of Encoded and Tunable Graphene-Gold Metasurface-Based Surface Plasmon Resonance Sensors for Glucose Detection in the Terahertz Regime

Contact Info

Product

Resources

About