Effective demand response and GANs for optimal constraint unit commitment in solar‐tidal based microgrids

Mobtahej, Mohammadamin; Esapour, Khodakhast; Tajalli, Seyede Zahra; Mohammadi, Mojtaba

doi:10.1049/rpg2.12331

Cited by 19 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In (17), TP = true positives, TN = true negatives, FP = false positives, and FN = false negatives. Precision and recall are calculated as follows:…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Distribution System State Estimation and False Data Injection Attack Detection with a Multi-Output Deep Neural Network

et al. 2023

View full text Add to dashboard Cite

Distribution system state estimation (DSSE) has been introduced to monitor distribution grids; however, due to the incorporation of distributed generations (DGs), traditional DSSE methods are not able to reveal the operational conditions of active distribution networks (ADNs). DSSE calculation depends heavily on real measurements from measurement devices in distribution networks. However, the accuracy of real measurements and DSSE results can be significantly affected by false data injection attacks (FDIAs). Conventional FDIA detection techniques are often unable to identify FDIAs into measurement data. In this study, a novel deep neural network approach is proposed to simultaneously perform DSSE calculation (i.e., regression) and FDIA detection (i.e., binary classification) using real measurements. In the proposed work, the classification nodes in the DNN allow us to identify which measurements on which phasor measurement unit (PMU), if any, were affected. In the proposed approach, we aim to show that the proposed method can perform DSSE calculation and identify FDIAs from the available measurements simultaneously with high accuracy. We compare our proposed method to the traditional approach of detecting FDIAs and performing SE calculations separately; moreover, DSSE results are compared with the weighted least square (WLS) algorithm, which is a common model-based method. The proposed method achieves better DSSE performance than the WLS method and the separate DSSE/FDIA method in presence of erroneous measurements; our method also executes faster than the other methods. The effectiveness of the proposed method is validated using two FDIA schemes in two case studies: one using a modified IEEE 33-bus distribution system without DGs, and the other using a modified IEEE 69-bus system with DGs. The results illustrated that the accuracy and F1-score of the proposed method are better than when performing binary classification only. The proposed method successfully detected the FDIAs on each PMU measurement. Moreover, the results of DSSE calculation from the proposed method has a better performance compared to the regression-only method, and the WLS methods in the presence of bad data.

show abstract

“…In (17), TP = true positives, TN = true negatives, FP = false positives, and FN = false negatives. Precision and recall are calculated as follows:…”

Section: Methodsmentioning

confidence: 99%

“…In addition to these differences, renewable energy sources are becoming more common in DNs [16][17][18]. These sources typically introduce higher variance and inconsistency, making it more difficult to perform state estimation.…”

mentioning

confidence: 99%

Distribution System State Estimation and False Data Injection Attack Detection with a Multi-Output Deep Neural Network

et al. 2023

View full text Add to dashboard Cite

show abstract

“…By comparison, robust method and fuzzy chance constraint method essentially only need to calculate one scenario, so their calculation time is very small, but the results tend to be conservative, resulting in an increase in total operating costs. Compared with the literature [36], there are several differences: (1). The objects of scheduling are different: this paper focuses on the load side, i.e., manufacturing enterprises, with the lowest production cost as the objective function; [36] focuses on the power system side, with the lowest generation cost as the objective function; (2).…”

Section: B Calculation Efficiency Analysismentioning

confidence: 99%

“…Compared with the literature [36], there are several differences: (1). The objects of scheduling are different: this paper focuses on the load side, i.e., manufacturing enterprises, with the lowest production cost as the objective function; [36] focuses on the power system side, with the lowest generation cost as the objective function; (2). The methods of problem solving are different: in this paper, the scheduling model is modeled using MILP using the STN method, which can be directly solved using commercial solvers; mathematical model in [36] can be solved using multi-objective and multi-stage optimization algorithms.…”

Section: B Calculation Efficiency Analysismentioning

confidence: 99%

Day-Ahead Intelligent Energy Management Strategy for Manufacturing Load Participating in Demand Response

Zhang

Zuo

2023

IEEE Access

View full text Add to dashboard Cite

Flexible resources such as adjustable load widely participate in interaction with power grid, which can effectively promote renewable energy consumption. In previous studies, researchers generally focused on industrial and household users, but usually ignored the manufacturing load. Therefore, in this paper, an day-ahead intelligent energy management strategy for manufacturing load is proposed. Firstly, we analyze the power demand behavior of manufacturing load in detail, and describe the energy flow and material flow of manufacturing load through state task network (STN) method and mixed integer linear programming model. Then, the conditional deep convolution generative adversarial networks (C-DCGAN) algorithm is used to describe the uncertainty of new energy and construct a set of scheduling scenarios. Finally, case study shows that the proposed method can effectively improve the regional renewable energy consumption level and economic benefits of enterprises. INDEX TERMSManufacturing load; state task network (STN) method; conditional deep convolution generative adversarial networks (C-DCGAN) algorithm; typical scenario screening method

show abstract

“…From the consumer's point of view, the MG can increase reliability, reduce greenhouse gas emissions, improve power quality, and from power generation companies' point of view, it can eliminate peak consumption points, reduce power loss, reduce operation costs, etc. [1][2][3][4]. Moreover, the development of MG is able to aid to supply remote loads when the proper distributions or transmission infrastructure are not available.…”

Section: Introductionmentioning

confidence: 99%

Reinforcing Data Integrity in Renewable Hybrid AC-DC Microgrids from Social-Economic Perspectives

Mohammadi

Kavousi‐Fard

Dehghani

et al. 2023

ACM Trans. Sen. Netw.

Self Cite

View full text Add to dashboard Cite

The microgrid (MG) is a complicated cyber-physical system that operates based on interactions between physical processes and computational components, which make it vulnerable to varied cyber-attacks. In this paper, the impact of data integrity attack (DIA) has been considered, as one of the most dangerous cyber threats to MGs, on the steady-state operation of hybrid MGs (HMGs). Additionally, a novel method based on sequential hypothesis testing (SHT) approach, is proposed to detect DIA on the renewable energy sources’ metering infrastructure and improve the data security within the HMGs. The proposed method generates a binary sample, which is used to compute a test statistic that is further used against two thresholds to decide among three alternatives. The performance of the suggested method is examined using an IEEE standard test system. The results illustrated the acceptable performance of the proposed methodology in detection of DIAs. Also, to evaluate the effect of DIA on the operation of the HMGs, DIAs with different severities are launched on the measured power generation of renewable energy resources (RESs) like wind turbine (WT). The results of this part showed that a successful DIA on renewable units can severely affect the operation of electric grids and cause serious damages.

show abstract

Effective demand response and GANs for optimal constraint unit commitment in solar‐tidal based microgrids

Cited by 19 publications

References 21 publications

Distribution System State Estimation and False Data Injection Attack Detection with a Multi-Output Deep Neural Network

Distribution System State Estimation and False Data Injection Attack Detection with a Multi-Output Deep Neural Network

Day-Ahead Intelligent Energy Management Strategy for Manufacturing Load Participating in Demand Response

Reinforcing Data Integrity in Renewable Hybrid AC-DC Microgrids from Social-Economic Perspectives

Contact Info

Product

Resources

About