MiniTEE—A Lightweight TrustZone-Assisted TEE for Real-Time Systems

Liu, Songran; Guan, Nan; Guo, Zhishan; Yi, Wang

doi:10.3390/electronics9071130

Cited by 1 publication

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper compares the forecasting and scheduling performance of this paper's system with several other commonly used methods. In this section, the experimental results will be shown from two aspects, namely, the power data analysis and prediction module and the intelligent scheduling and optimization module, respectively [31,32]. This table illustrates the CCP system's superiority in predicting both day-ahead and short-term power main grid loads.…”

Section: B Experimental Resultsmentioning

confidence: 99%

Cloud-Enabled Real-Time Monitoring and Alert System for Primary Network Resource Scheduling and Large-Scale Users

Zhang,

Shu,

et al. 2024

ijacsa

View full text Add to dashboard Cite

This paper innovatively combines cloud computing with Bayesian networks, aiming to provide an efficient and realtime prediction and scheduling platform for power main network scheduling and large-scale user monitoring. The core of the research lies in the development of a set of novel intelligent scheduling algorithms, which integrates multi-objective optimization theory and deep reinforcement learning technology to achieve dynamic and optimal allocation of power grid resources in the cloud environment. By constructing a comprehensive evaluation system, this study verifies the advancement of the proposed model in multiple dimensions: not only does it make breakthroughs in the in-depth parsing and accurate prediction of electric power data, but it also significantly improves the prediction accuracy of the main grid load changes, tariff dynamic adjustments, grid security posture, and power consumption patterns of large users. The empirical study shows that compared with the existing methods, the model proposed in this study effectively reduces energy consumption and operation costs while improving prediction accuracy and dispatching efficiency, demonstrating its significant innovative value and practical significance in the field of intelligent grid management. The innovation of this paper lies in the development of a composite prediction model that integrates the powerful classification and prediction capabilities of Bayesian networks and the efficient learning mechanism of deep reinforcement learning in complex decision-making scenarios.

show abstract

Section: B Experimental Resultsmentioning

confidence: 99%