Optimum Power Flow in DC Microgrid Employing Bayesian Regularized Deep Neural Network

Jeyaraj, Pandia Rajan; Asokan, Siva Prakash; Karthiresan, Aravind Chellachi

doi:10.1016/j.epsr.2021.107730

Cited by 19 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Collect real-time operation data and historical operation data from the main network. The real-time operation data of the main network is collected using the main network sensor equipment, and the collection results of real-time operation data are obtained by setting collection parameters [10]. Due to the different types of electrical energy connected to the main network, there may be formatting differences in the collected real-time operational data.…”

Section: Normalization Processing Of Main Network Operation Datamentioning

confidence: 99%

Research on optimization strategy of main network maintenance scheduling based on regional power demand

Huang,

Luo,

Chen

et al. 2024

Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023)

View full text Add to dashboard Cite

In order to regulate and control the operation state of the main network efficiently and stably, this paper puts forward the research on the optimization strategy of the main network maintenance scheduling based on the regional power demand. According to the three time scales of day before, rolling in the day and real-time, the main network is divided into three time periods for optimal scheduling, and an optimization framework of main network scheduling under regional power demand is constructed. On this basis, the operation data of the main network are normalized, and the maintenance scheduling optimization process of the main network is constructed to realize the maintenance scheduling optimization of the main network. The experimental results show that after optimization, the comprehensive risk index of each test equipment is obviously improved, and the optimization strategy of main network maintenance scheduling has good results.

show abstract

Section: Normalization Processing Of Main Network Operation Datamentioning

confidence: 99%

Research on optimization strategy of main network maintenance scheduling based on regional power demand

Huang,

Luo,

Chen

et al. 2024

Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023)

View full text Add to dashboard Cite

show abstract

“…The presented method can identify the grid topology changes and is applicable for line outage scenarios. A Bayesian regularized Deep Neural Network (BDNN) is proposed in [45] to reduce the loss in load expectation and assess the voltage quality and various reliability indexes by solving the power flow problem in a DC microgrid…”

Section: Related Workmentioning

confidence: 99%

Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids

Tiwari,

Zideh,

Talreja

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Most power systems' approaches are currently tending towards stochastic and probabilistic methods due to the high variability of renewable sources and the stochastic nature of loads. Conventional power flow (PF) approaches such as forward-backward sweep (FBS) and Newton-Raphson require a high number of iterations to solve non-linear PF equations making them computationally very intensive. PF is the most important study performed by utility, required in all stages of the power system, especially in operations and planning. This paper discusses the applications of deep learning (DL) to predict PF solutions for three-phase unbalanced power distribution grids. Three deep neural networks (DNNs); Radial Basis Function Network (RBFnet), Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN), are proposed in this paper to predict PF solutions. The strength of the proposed DNN models over the traditional iterative-based PF solvers is that these models can capture the nonlinear relationships in PF calculations to accurately predict the solutions. The PF problem is formulated as a multi-output regression model where two or more output values are predicted based on the inputs. The training and testing data are generated through the OpenDSS-MATLAB COM interface. These methods are completely data-driven where the training relies on reducing the mismatch at each node without the need for the knowledge of the system. The novelty of the proposed methodology is that the models can accurately predict the PF solutions for the unbalanced distribution grids with mutual coupling and are robust to different R/X ratios, topology changes as well as generation and load variability introduced by the integration of distributed energy resources (DERs) and electric vehicles (EVs). To test the efficacy of the DNN models, they are applied to IEEE 4-node and 123-node test cases, and the American Electric Power (AEP) feeder model. The PF results for RBFnet, MLP, and CNN models are discussed in this paper which demonstrate that all three DNN models provide highly accurate results in predicting PF solutions.INDEX TERMS Power flow analysis, deep neural networks, radial basis function networks, multi-layer perceptron, convolutional neural networks, unbalanced power distribution grids.The associate editor coordinating the review of this manuscript and approving it for publication was Ehab Elsayed Elattar .

show abstract

“…The forecasting of generation, load and prices are carried out by using a combination of RNN and gated recurrent unit for scheduling purposes. Finally, in [39], a Bayesian regularized Deep Neural Network (BDNN) for efficient charging/discharging of BESS is employed to meet the supply-load compensation during changes caused by intermittent RESs.…”

Section: Size Of the Bessmentioning

confidence: 99%

Challenges and Perspectives of Smart Grid Systems in Islands: A Real Case Study

et al. 2023

View full text Add to dashboard Cite

Islands are facing significant challenges in meeting their energy needs in a sustainable, affordable, and reliable way. Traditionally, the primary source of electricity on the islands has been imported diesel fuel, with high financial costs for most utilities. In this context, even replacing part of the traditional production with renewable energy source can reduce costs and improve the quality of life of islanders. However, integrating large amounts of renewable energy production into existing grids introduces many concerns regarding feasibility, economic analysis, and technical implementation. From this point of view, machine learning and deep learning techniques are efficient tools to mitigate these problems. Their potential results are beneficial considering isolated grids of small islands which are not connected to the national grid. In this paper, a study of the Italian island of Ponza is carried out. The isolation leads to several challenges, such as the high cost related to the transport, installation, and maintenance of renewable energy sources in a small area with several constraints and their intermittent power production, which requires the use of storage systems for dispatching purposes. The proposed study aims to identify future developments of the electricity grid by considering the deployment of both renewable energy sources and energy storage systems. Furthermore, future scenarios are depicted through the use of autoregressive and deep learning techniques to give an idea about the economic costs of both energy demand and supply.

show abstract

Optimum Power Flow in DC Microgrid Employing Bayesian Regularized Deep Neural Network

Cited by 19 publications

References 26 publications

Research on optimization strategy of main network maintenance scheduling based on regional power demand

Research on optimization strategy of main network maintenance scheduling based on regional power demand

Power Flow Analysis Using Deep Neural Networks in Three-Phase Unbalanced Smart Distribution Grids

Challenges and Perspectives of Smart Grid Systems in Islands: A Real Case Study

Contact Info

Product

Resources

About