Risk-aware learning for scalable voltage optimization in distribution grids
نویسندگان
چکیده
Real-time coordination of distributed energy resources (DERs) is crucial for regulating the voltage profile in distribution grids. By capitalizing on a scalable neural network (NN) architecture, one can attain decentralized DER decisions to address lack real-time communications. This paper develops an advanced learning-enabled scheme by accounting potential risks associated with reactive power prediction and deviation. Such are quantified conditional value-at-risk (CVaR) using worst-case samples only, we propose mini-batch selection algorithm training speed issue minimizing CVaR-regularized loss. Numerical tests real-world data IEEE 123-bus test case have demonstrated computation safety improvements proposed risk-aware learning decision making, especially terms reducing feeder violations.
منابع مشابه
Risk Aware Overbooking for Commercial Grids
The commercial exploitation of the emerging Grid and Cloud markets needs SLAs to sell computing run times. Job traces show that users have a limited ability to estimate the resource needs of their applications. This offers the possibility to apply overbooking to negotiation, but overbooking increases the risk of SLA violations. This work presents an overbooking approach with an integrated risk ...
متن کاملReliability-Aware Energy Optimization Algorithm for Network-on-Chip with Voltage-Scalable Links
A reliability-aware energy optimization algorithm is proposed for Network-on-Chip (NoC) with voltage scalable links. Considering the effect of reduced voltage on fault rates, this approach achieves energy/reliability trade-off when performing routing path allocation and links voltage assignment statically. A novel energy-efficiency gradient driven heuristic is proposed to assign the voltages fo...
متن کاملMulti-objective and Scalable Heuristic Algorithm for Workflow Task Scheduling in Utility Grids
To use services transparently in a distributed environment, the Utility Grids develop a cyber-infrastructure. The parameters of the Quality of Service such as the allocation-cost and makespan have to be dealt with in order to schedule workflow application tasks in the Utility Grids. Optimization of both target parameters above is a challenge in a distributed environment and may conflict one an...
متن کاملA Bi-Level Optimization Approach for Optimal Operation of Distribution Networks with Retailers and Micro-grids
Distributed energy resources (DERs) including distributed generators (DGs) and controllable loads (CLs) are managed in the form of several microgrids (MGs) in active distributions networks (ADNs) to meet the demand locally. On the other hand, some loads of distribution networks (DNs) can be supplied by retailers which participate in wholesale energy markets. Therefore, there are several decisio...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Electric Power Systems Research
سال: 2022
ISSN: ['1873-2046', '0378-7796']
DOI: https://doi.org/10.1016/j.epsr.2022.108605