DER Forecast Using Privacy-Preserving Federated Learning

Venkataramanan, V.; Sridevi, Kaza,; Annaswamy, Anuradha M.

doi:10.1109/jiot.2022.3157299

Cited by 30 publications

(10 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adversarial federated transfer learning training method proposed in this paper can significantly improve the accuracy of mask load prediction. It can be observed that when the mask load accounted for 20% and 30% of the total load data, the MAPE of the prediction model was reduced by 6.7% compared with the traditional FL [25,26]. And when the mask load was increased to 50%, the average MAPE was reduced by 9.6%.…”

Section: Experimental Results and Analysismentioning

confidence: 95%

Research on Load Forecasting of Novel Power System Based on Efficient Federated Transfer Learning

Wang,

Wei,

Zeng

et al. 2023

Energies

View full text Add to dashboard Cite

The load forecasting research for an NPS faces challenges including a high model accuracy, non-sharing of data, and a high communication cost. This paper proposes a load forecasting method for an NPS, based on efficient federated transfer learning (FTL). The adversarial feature extractor is added on the basis that FTL can effectively transfer the parameter features of the non-mask load to the local load data, and make up for the loss of mask load prediction accuracy. In order to improve the efficiency of the gradient compression of federated learning (FL), a depth dynamic threshold compression sensing method is proposed, which replaces the sparse signal in compressed sensing via the U-Net model and achieves an observation dimension reduction through a convolutional neural network (CNN). The experimental results show that the mean absolute percentage error (MAPE) and the root-mean-square error (RMSE) of the load forecasting method proposed in this paper are reduced by 9.6% and 2.31 kW, on average, when the load data are covered up to different degrees. Compared with the traditional FL model, the proposed compression algorithm saves 23.5% of the communication cost, without changing the accuracy of the model. The proposed prediction framework is easily interpretable, and robust under different validation metrics.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 95%

Research on Load Forecasting of Novel Power System Based on Efficient Federated Transfer Learning

Wang,

Wei,

Zeng

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

“…Data heterogeneity [4], [17], [18], [25], [27], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44] x x [45] x x [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57], [58], [59], [60] x [61] x x x [28], [62], [63] x x [64] x x [7], [20] x x x x [8], [9], [19], [65], [66], [67], [68], [69], [70], [71],…”

Section: Model Generalization Abilitymentioning

confidence: 99%

Advancing Power System Services With Privacy-Preserving Federated Learning Techniques: A Review

Zheng,

Sumper,

Aragüés-Peñalba

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Digitalization has enabled the potential for artificial intelligence techniques to lead the power system to a sustainable transition by extracting the data generated by widely deployed edge devices, including advanced sensing and metering. Due to the increasing concerns about data privacy, federated learning has attracted much attention and is emerging as an innovative application for machine learning solutions in the power and energy sector. This paper presents a holistic analysis of federated learning applications in the energy sector, ranging from applications in generation, microgrids, and distribution systems to the energy market and cyber security. The following federated learning-based services for energy sectors are analyzed: non-intrusive load monitoring, fault detection, energy theft detection, demand forecasting, generation forecasting, energy management systems, voltage control, anomaly detection, and energy trading. The identification and classification of the data-driven methods are conducted in collaboration with federated learning implemented in these services. Furthermore, the interrelation is mapped between the categories of machine learning, data-driven techniques, the application domain, and application services. Finally, the future opportunities and challenges of applying federated learning in the energy sector will be discussed.

show abstract

“…Also, in ref. [33], a federated learning model for privacy‐preserving forecasting of distributed energy resources, such as solar PV, EV storage or flexible loads, is developed. The authors validate their study with 1000 IoT nodes and show that the approach can be used for grid services such as predicting curtailment events or load swings.…”

Section: Related Workmentioning

confidence: 99%

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

DER Forecast Using Privacy-Preserving Federated Learning

Cited by 30 publications

References 38 publications

Research on Load Forecasting of Novel Power System Based on Efficient Federated Transfer Learning

Research on Load Forecasting of Novel Power System Based on Efficient Federated Transfer Learning

Advancing Power System Services With Privacy-Preserving Federated Learning Techniques: A Review

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

Contact Info

Product

Resources

About