Privacy-Preserving Federated Learning for Value-Added Service Model in Advanced Metering Infrastructure

Zhang, Xiao‐Yu; Córdoba‐Pachón, José‐Rodrigo; Guo, Peiqian; Watkins, Chris; Kuenzel, Stefanie

doi:10.1109/tcss.2022.3204361

Cited by 11 publications

(3 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A trust model, a confidence assessment, and trustbased security methods are all included in the model. In order to handle the confidence connections between the system's components, the paradigm also contains a set of trust management systems [36].…”

Section: Review Of Security Models For Securing Cyber Physical Deploy...mentioning

confidence: 99%

BSCSML: Design of an Efficient Bioinspired Security &Privacy Model for Cyber Physical System using Machine Learning

Megha Sanjay Wankhade

2023

IJRITCC

View full text Add to dashboard Cite

With the increasing prevalence of Smart Grid Cyber Physical Systems with Advanced Metering Infrastructure (SG CPS AMI), securing their internal components has become one of the paramount concerns. Traditional security mechanisms have proven to be insufficient in defending against sophisticated attacks. Bioinspired security and privacy models have emerged as promising solutions due to their stochastic solutions. This paper proposes a novel bio-inspired security and privacy model for SG CPS AMI that utilizes machine learning to strengthen their security levels. The proposed model is inspired by the hybrid Grey Wolf Teacher Learner based Optimizer (GWTLbO) Method’s ability to detect and respond to threats in real-time deployments. The GWTLbO Model also ensures higher privacy by selecting optimal methods between k-privacy, t-closeness & l-diversity depending upon contextual requirements. This study improves system accuracy and efficiency under diverse attacks using machine learning techniques. The method uses supervised learning to teach the model to recognize known attack trends and uncontrolled learning to spot unknown attacks. Our model was tested using real-time IoT device data samples. The model identified Zero-Day Attacks, Meter Bypass, Flash Image Manipulation, and Buffer-level attacks. The proposed model detects and responds to attacks with high accuracy and low false-positive rates. In real-time operations, the proposed model can handle huge volumes of data efficiently. The bioinspired security and privacy model secures CPS efficiently and is scalable for various cases. Machine learning techniques can improve the security and secrecy of these systems and revolutionize defense against different attacks.

show abstract

Section: Review Of Security Models For Securing Cyber Physical Deploy...mentioning

confidence: 99%

BSCSML: Design of an Efficient Bioinspired Security &Privacy Model for Cyber Physical System using Machine Learning

Megha Sanjay Wankhade

2023

IJRITCC

View full text Add to dashboard Cite

show abstract

“…It plays an important role in providing near real-time two-way communication between consumers and energy systems, as well as providing a range of value-added services to increase customer satisfaction. However, given that its existing services are implemented in a centralized manner, it will still have security and privacy issues [52]. The construction of the Energy Internet should be based on full respect for human rights and protection of the privacy of each user.…”

Section: Potential Problemmentioning

confidence: 99%

The Key Technology of Smart Energy System and Its Disciplinary Teaching Reform Measures

et al. 2022

View full text Add to dashboard Cite

Based on the rapid development of new energy technology, modern information technology, intelligent management technology and different countries’ strategic demand and deployment in the field of energy, the construction of intelligent energy systems is booming with the combination of new energy technology and Internet technology. The Energy Internet is the representative product of intelligent energy systems at the present stage. Its advantages are the effective promotion of energy saving, consumption reduction and optimization of deployment, thus improving the energy system. However, the large-scale construction of the Energy Internet requires a large number of professionals. In order to meet the needs of Energy Internet construction, the talent training mode of higher education is facing new challenges. To cultivate talents in Energy Internet construction, an effective measure is to reform the teaching system based on the current electrical engineering major in universities. This paper investigates the development and construction of the Energy Internet and the current situation of the electrical engineering discipline and puts forward teaching reform measures to transform the traditional electrical engineering discipline into an Energy Internet engineering discipline, considering course structure design, examination form, teacher allocation and teaching mode. This is important for promoting the large-scale construction of the Energy Internet and improving the competitiveness of graduates in the electrical engineering field.

show abstract

“…A long short-term memory (LSTM) neural network using the FL architecture on 200 houses has been trained in [28] while using FedAvg at the server to aggregate local model updates, while also exploring the personalizing of local models. A bidirectional LSTM neural network model has been adopted to solve the long-range dependency problem of conventional neural networks in [29]. Considering the fact that load data amongst heterogeneous clients would not be independent and identically distributed (non-IID), [30] designs a local data evaluation mechanism for cost modeling and devises an incentive algorithm for optimal pricing and training strategies.…”

Section: Related Work In Federated Learningmentioning

confidence: 99%

Federated and Multi-Task Learning for Privacy-Preserving Short-Term Electric Load Forecasting

Ghalib

View full text Add to dashboard Cite

Electric load forecasting involves gathering and analyzing load data from end-users to help utilities maintain the balance between supply and demand, plan and manage their infrastructure, and price their services. Privacy concerns arise from sharing electric load data. Federated Learning (FL) entails training a global model among several clients by sharing model weights instead of data. Using multiple server aggregation algorithms, we implement several fine-tuning (personalizing) optimizers to improve the local load forecasting accuracy compared to non-personalized FL. We also propose training a Temporal Fusion Transformer (TFT), a type of deep learning model that combines the strengths of transformers and LSTM networks, via FL, which improved load forecasting accuracy and reduced communication and computation costs compared to other common deep learning models. Recommendations are presented regarding several TFT architecture hyperparameters to improve load forecasting accuracy and reduce costs even further. Enforcing and relaxing lockdown rules and changing habits of people caused major uncertainty in load forecasting during the Coronavirus disease of 2019 (COVID-19).To overcome this, we propose two disaster-aware multi-task learning (MTL) models for residential and city levels load forecasting. The proposed MTL models allowed learning from two different datasets with different features, and reduced load forecasting error for both levels compared to a non-MTL approach.

show abstract

Privacy-Preserving Federated Learning for Value-Added Service Model in Advanced Metering Infrastructure

Cited by 11 publications

References 50 publications

BSCSML: Design of an Efficient Bioinspired Security &Privacy Model for Cyber Physical System using Machine Learning

BSCSML: Design of an Efficient Bioinspired Security &Privacy Model for Cyber Physical System using Machine Learning

The Key Technology of Smart Energy System and Its Disciplinary Teaching Reform Measures

Federated and Multi-Task Learning for Privacy-Preserving Short-Term Electric Load Forecasting

Contact Info

Product

Resources

About