Privacy-Preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach

Li, Yang; Li, Jiazheng; Wang, Yi

doi:10.1109/tii.2021.3098259

Cited by 113 publications

(39 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, the agent with trained weights might provide reference to investing other kinds of cryptocurrency by adopting the idea of transfer learning and fine-tuning. Third, it would be interesting to develop a privacy-preserving bitcoin transaction strategy through motivating bitcoin owners to participate in federated learning [27]. Finally, combined with manual work, the proposed method may achieve a more controllable risk investment strategy in practice.…”

Section: Discussionmentioning

confidence: 99%

Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning

Liu

Ren

Zhai

et al. 2021

2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE)

View full text Add to dashboard Cite

The emerging cryptocurrency market has lately received great attention for asset allocation due to its decentralization uniqueness. However, its volatility and brand new trading mode has made it challenging to devising an acceptable automatically-generating strategy. This study proposes a framework for automatic high-frequency bitcoin transactions based on a deep reinforcement learning algorithmproximal policy optimization (PPO). The framework creatively regards the transaction process as actions, returns as awards and prices as states to align with the idea of reinforcement learning. It compares advanced machine learning-based models for static price predictions including support vector machine (SVM), multi-layer perceptron (MLP), long short-term memory (LSTM), temporal convolutional network (TCN), and Transformer by applying them to the real-time bitcoin price and the experimental results demonstrate that LSTM outperforms. Then an automatically-generating transaction strategy is constructed building on PPO with LSTM as the basis to construct the policy. Extensive empirical studies validate that the proposed method perform superiorly to various common trading strategy benchmarks for a single financial product. The approach is able to trade bitcoins in a simulated environment with synchronous data and obtains a 31.67% more return than that of the best benchmark, improving the benchmark by 12.75%. The proposed framework can earn excess returns through both the period of volatility and surge, which opens the door to research on building a single cryptocurrency trading strategy based on deep learning. Visualizations of trading the process show how the model handles high-frequency transactions to provide inspiration and demonstrate that it can be expanded to other financial products.

show abstract

Section: Discussionmentioning

confidence: 99%

Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning

Liu

Ren

Zhai

et al. 2021

2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE)

View full text Add to dashboard Cite

show abstract

“…Also, in [22], the authors have extended the mentioned generative model to increase the quality and realisticness of samples generated in an optimization problem framework. Another machine learning‐based method called Fed‐LSGAN is presented in [23]. In this method, samples of renewable energy productions are generated based on a combination of federated learning and least square generative adversarial networks.…”

Section: Probabilistic Evaluation Using Lhs Methodsmentioning

confidence: 99%

A generalized probabilistic multi‐objective method for optimal allocation of soft open point (SOP) in distribution networks

Rezaeian‐Marjani

Galvani

Talavat

2022

IET Renewable Power Gen

View full text Add to dashboard Cite

Soft open point (SOP) as a novel power electronics‐based device has been introduced to control active power flow, compensate reactive power, and regulate voltage for flexible operation of distribution networks. The increasing penetration of renewable energy sources (RESs) such as wind turbine (WT) and photovoltaic (PV) units with uncertain outputs in distribution networks increases the importance of optimal and robust allocation of SOP against multiple uncertainties to improve the performance of these networks. In this paper, a probabilistic multi‐objective framework is proposed for optimal allocation of SOP in RESs included distribution networks. A novel SOP modeling in the forward‐backward load flow method without any simplification is introduced. In addition, this study investigates the impact of various correlation levels between uncertain input variables in the problem. The multi‐objective particle swarm optimization (MOPSO) method is used to extract Pareto‐based solutions set considering the expected value of active power losses, feeder load balancing index (LBI), and investment cost of SOP as objective functions. Also, the Latin hypercube sampling (LHS) and Cholesky decomposition methods are implemented to uncertainties modeling and handling the correlations, respectively. The results of the proposed study framework are argued on the IEEE 33‐node and the IEEE 118‐node distribution networks.

show abstract

“…Generative adversarial network (GAN) is a machine learning algorithm that is widely used to generate synthetic data. Being first proposed in 2014 by Goodfellow et al [41], GAN is currently popular and comes in different forms, one of them being least square generative adversarial network (LSGAN), which was used by Li et al [42] together with federated learning to generate renewable scenarios. Through federated learning, a model was trained by gathering knowledge from different renewable sites, and then LSGAN was employed to generate renewable scenarios from the same distribution as the historical data, thanks to the capability of capturing the spatiotemporal characteristics of renewable powers.…”

Section: Review Of Privacy-preserving Ai In Industrial Applicationsmentioning

confidence: 99%

Privacy-Preserving and Explainable AI in Industrial Applications

et al. 2022

View full text Add to dashboard Cite

The industrial environment has gone through the fourth revolution, also called “Industry 4.0”, where the main aspect is digitalization. Each device employed in an industrial process is connected to a network called the industrial Internet of things (IIOT). With IIOT manufacturers being capable of tracking every device, it has become easier to prevent or quickly solve failures. Specifically, the large amount of available data has allowed the use of artificial intelligence (AI) algorithms to improve industrial applications in many ways (e.g., failure detection, process optimization, and abnormality detection). Although data are abundant, their access has raised problems due to privacy concerns of manufacturers. Censoring sensitive information is not a desired approach because it negatively impacts the AI performance. To increase trust, there is also the need to understand how AI algorithms make choices, i.e., to no longer regard them as black boxes. This paper focuses on recent advancements related to the challenges mentioned above, discusses the industrial impact of proposed solutions, and identifies challenges for future research. It also presents examples related to privacy-preserving and explainable AI solutions, and comments on the interaction between the identified challenges in the conclusions.

show abstract

Privacy-Preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach

Cited by 113 publications

References 23 publications

Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning

Bitcoin Transaction Strategy Construction Based on Deep Reinforcement Learning

A generalized probabilistic multi‐objective method for optimal allocation of soft open point (SOP) in distribution networks

Privacy-Preserving and Explainable AI in Industrial Applications

Contact Info

Product

Resources

About