Distributed load forecasting using smart meter data: Federated learning with Recurrent Neural Networks

Fekri, Mohammad Navid; Grolinger, Katarina; Mir, Syed

doi:10.1016/j.ijepes.2021.107669

Cited by 100 publications

(45 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, their proposed solution does not address the issue of scaling and cannot be parallelized to improve performance, as it relies upon RNNs. In order to address the need for more computationally efficient ways to create multiple models, a distributed ML load forecasting solution in the form of federated learning has been recently proposed [38]. Nevertheless, the evaluation took place on a small dataset and the chosen architecture still prohibited parallelization.…”

Section: Related Workmentioning

confidence: 99%

Transformer-Based Model for Electrical Load Forecasting

2022

Self Cite

View full text Add to dashboard Cite

Amongst energy-related CO2 emissions, electricity is the largest single contributor, and with the proliferation of electric vehicles and other developments, energy use is expected to increase. Load forecasting is essential for combating these issues as it balances demand and production and contributes to energy management. Current state-of-the-art solutions such as recurrent neural networks (RNNs) and sequence-to-sequence algorithms (Seq2Seq) are highly accurate, but most studies examine them on a single data stream. On the other hand, in natural language processing (NLP), transformer architecture has become the dominant technique, outperforming RNN and Seq2Seq algorithms while also allowing parallelization. Consequently, this paper proposes a transformer-based architecture for load forecasting by modifying the NLP transformer workflow, adding N-space transformation, and designing a novel technique for handling contextual features. Moreover, in contrast to most load forecasting studies, we evaluate the proposed solution on different data streams under various forecasting horizons and input window lengths in order to ensure result reproducibility. Results show that the proposed approach successfully handles time series with contextual data and outperforms the state-of-the-art Seq2Seq models.

show abstract

Section: Related Workmentioning

confidence: 99%

Transformer-Based Model for Electrical Load Forecasting

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The earliest work in this area by Taik and Cherkaoui [19] applied a federated approach to short-term load forecasting for residential houses and evaluated their framework with data from 200 houses from Texas, USA. Similarly, other studies [2], [3] have been working towards improving distributed shortterm energy forecasting and improving privacy measures in relation to federated learning for load forecasting at customer level. However, it is worth noting that the feasibility of the proposed approach is highly dependent on the capabilities of the edge devices to perform local training.…”

Section: B Federated Learning Schemesmentioning

confidence: 99%

“…In a traditional setting, energy load forecasting occurs at the control centre by executing advanced deep learning models which indeed achieve good forecasting performance [2], [3]. However, the existing centralized approach requires retailers to share and transmit energy consumption information to the control centre where models are trained and executed.…”

Section: Introductionmentioning

confidence: 99%

FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers

Husnoo¹,

Anwar²,

Hosseinzadeh³

et al. 2022

Preprint

View full text Add to dashboard Cite

As Smart Meters are collecting and transmitting household energy consumption data to Retail Energy Providers (REP), the main challenge is to ensure the effective use of fine-grained consumer data while ensuring data privacy. In this manuscript, we tackle this challenge for energy load consumption forecasting in regards to REPs which is essential to energy demand management, load switching and infrastructure development. Specifically, we note that existing energy load forecasting is centralized, which are not scalable and most importantly, vulnerable to data privacy threats. Besides, REPs are individual market participants and liable to ensure the privacy of their own customers. To address this issue, we propose a novel horizontal privacy-preserving federated learning framework for REPs energy load forecasting, namely FedREP. We consider a federated learning system consisting of a control centre and multiple retailers by enabling multiple REPs to build a common, robust machine learning model without sharing data, thus addressing critical issues such as data privacy, data security and scalability. For forecasting, we use a state-of-theart Long Short-Term Memory (LSTM) neural network due to its ability to learn long term sequences of observations and promises of higher accuracy with time-series data while solving the vanishing gradient problem. Finally, we conduct extensive data-driven experiments using a real energy consumption dataset. Experimental results demonstrate that our proposed federated learning framework can achieve sufficient performance in terms of MSE ranging between 0.3 to 0.4 and is relatively similar to that of a centralized approach while preserving privacy and improving scalability.

show abstract

“…The experimental results show that their proposed method creates high-performance models compared to a centralized method while preserving privacy. Fekri et al [34] compared two FL approaches for load forecasting: federated averaging (FedAVG) and federated stochastic gradient descent (FedSGD) [11]. While FedSGD calculates one step of the gradient descent on the client's server before merging updates on the central server, FedAVG calculates several steps before merging.…”

Section: Distributed Learning For Short-term Load Forecastingmentioning

confidence: 99%

“…FedAVG reduces the communication cost compared to FedSGD. Their evaluation showed that FedAVG outperformed FedSGD, the personalized method proposed in [34], the central approach, and the individual method.…”

Section: Distributed Learning For Short-term Load Forecastingmentioning

confidence: 99%

Hierarchical Multiobjective Distributed Deep Learning for Residential Short-Term Electric Load Forecasting

Sakuma

Nishi

2022

IEEE Access

View full text Add to dashboard Cite

Short-term load forecasting plays an essential role in appliance control in households and demand response at the neighborhood or community level. When load forecasting is simultaneously performed at different levels in a smart community, a central method that directly aggregates raw household data may incur a security issue. However, an individual method that builds separate models for each level requires additional data collection. We propose a distributed load forecasting framework that is secure, data efficient, and resource efficient. Our proposed method shares the latent variables, the reduced expression of the input data, of the household models without revealing the raw data. The latent variables are aggregated and fed to the neighborhood model, and during inference, input data collection can be abbreviated in the neighborhood. Because household models provide informative latent variables, the number of model parameters for the neighborhood model can be reduced. Our proposed method is evaluated using real

show abstract

Distributed load forecasting using smart meter data: Federated learning with Recurrent Neural Networks

Cited by 100 publications

References 13 publications

Transformer-Based Model for Electrical Load Forecasting

Transformer-Based Model for Electrical Load Forecasting

FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers

Hierarchical Multiobjective Distributed Deep Learning for Residential Short-Term Electric Load Forecasting

Contact Info

Product

Resources

About