Litcius/Paper detail

SecTCN: Privacy-Preserving Short-Term Residential Electrical Load Forecasting

Liqiang Wu, Shaojing Fu, Yuchuan Luo, Ming Xu

2023IEEE Transactions on Industrial Informatics22 citationsDOI

Abstract

Short-term residential electrical load forecasting (SRLF) as a cloud service usually requires fine-grained electricity consumption data as input. However, those data are closely related to users' lifestyles, thus bringing about privacy concerns. We adapt homomorphic encryption into temporal convolutional networks (TCN) to yield an efficient design for SRLF, named SecTCN, which preserves privacy for both user data and model parameters. First, a homomorphic-encryption-friendly model is proposed through novel Ticktock approximations. Second, secure load forecasting over the encrypted data is executed by cloud–edge collaboration. Third, a novel data representation and related ciphertext computations are proposed to accelerate forecasting, and a position shuffler is devised to protect models from equation-solving attacks. Experimental evaluations demonstrate that SecTCN reduces a root-mean-squared error by 21.75 averagely and a mean absolute percentage error by 4.22% <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\text{ to } $</tex-math></inline-formula> 22.16%, compared to unencrypted long short-term memory (LSTM) and TCN. On average, SecTCN requires only 1.10 s to make forecasting with 10.27 MB communication traffic.

Topics & Concepts

Homomorphic encryptionComputer scienceEncryptionTerm (time)Cloud computingComputationCiphertextTheoretical computer scienceData miningAlgorithmComputer securityQuantum mechanicsPhysicsOperating systemEnergy Load and Power ForecastingTraffic Prediction and Management TechniquesHydrological Forecasting Using AI
SecTCN: Privacy-Preserving Short-Term Residential Electrical Load Forecasting | Litcius