Resilient Model Predictive Adaptive Control of Networked Z-Source Inverters Using GMDH

Ahmadi, Amirhossein; Asadi, Yasin; Amani, Ali Moradi; Jalili, Mahdi; Yu, Xinghuo

doi:10.1109/tsg.2022.3174250

Cited by 11 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm then forms its internal structure without any input. The Ivakhnenko polynomial [ 20 ] is used to describe the connection between the input variables y 1 and y 2 :

…”

Section: Proposed Modelmentioning

confidence: 99%

Deep Learning-Inspired IoT-IDS Mechanism for Edge Computing Environments

Aldaej,

Ahanger,

Ullah

2023

Sensors

View full text Add to dashboard Cite

The Internet of Things (IoT) technology has seen substantial research in Deep Learning (DL) techniques to detect cyberattacks. Critical Infrastructures (CIs) must be able to quickly detect cyberattacks close to edge devices in order to prevent service interruptions. DL approaches outperform shallow machine learning techniques in attack detection, giving them a viable alternative for use in intrusion detection. However, because of the massive amount of IoT data and the computational requirements for DL models, transmission overheads prevent the successful implementation of DL models closer to the devices. As they were not trained on pertinent IoT, current Intrusion Detection Systems (IDS) either use conventional techniques or are not intended for scattered edge–cloud deployment. A new edge–cloud-based IoT IDS is suggested to address these issues. It uses distributed processing to separate the dataset into subsets appropriate to different attack classes and performs attribute selection on time-series IoT data. Next, DL is used to train an attack detection Recurrent Neural Network, which consists of a Recurrent Neural Network (RNN) and Bidirectional Long Short-Term Memory (LSTM). The high-dimensional BoT-IoT dataset, which replicates massive amounts of genuine IoT attack traffic, is used to test the proposed model. Despite an 85 percent reduction in dataset size made achievable by attribute selection approaches, the attack detection capability was kept intact. The models built utilizing the smaller dataset demonstrated a higher recall rate (98.25%), F1-measure (99.12%), accuracy (99.56%), and precision (99.45%) with no loss in class discrimination performance compared to models trained on the entire attribute set. With the smaller attribute space, neither the RNN nor the Bi-LSTM models experienced underfitting or overfitting. The proposed DL-based IoT intrusion detection solution has the capability to scale efficiently in the face of large volumes of IoT data, thus making it an ideal candidate for edge–cloud deployment.

show abstract

“…The algorithm then forms its internal structure without any input. The Ivakhnenko polynomial [ 20 ] is used to describe the connection between the input variables y 1 and y 2 :

…”

Section: Proposed Modelmentioning

confidence: 99%

Deep Learning-Inspired IoT-IDS Mechanism for Edge Computing Environments

Aldaej,

Ahanger,

Ullah

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…For instance, in emergency response scenarios, these technologies can analyze real-time data to efficiently dispatch resources like medical supplies, manpower, or equipment to affected areas [92]. Natural Language Processing (NLP): NLP-driven AI systems can sift through vast amounts of textual data from social media, news outlets, or other sources to gather insights, assess public sentiment, and provide early indicators of potential issues or crises [93]. Adaptive Systems for Decision-Making: AI-powered decision support systems can assist decision-makers by processing and analyzing information rapidly, providing recommendations, and even learning from past decisions and outcomes to refine future suggestions [94].…”

Section: Collaboration and Information Sharingmentioning

confidence: 99%

Safeguarding Stability: Strategies for Addressing Dynamic System Variations in Power Grid Cybersecurity

Guzman Erick,

Fatehi Navid

2023

EPHIJSE

View full text Add to dashboard Cite

The power grid stands as a critical infrastructure supporting modern society, yet it remains susceptible to cyber threatsthat could compromise its stability and functionality. Addressing the dynamic variations and evolving challenges posedby cyber threats requires robust strategies in cybersecurity. This paper investigates methods to safeguard the stability ofthe power grid against cyber intrusions and system variations. This study delves into the multifaceted nature of cyberthreats targeting the power grid and analyzes the dynamic variations within the system that could be exploited bymalicious actors. This paper presents a comprehensive framework encompassing proactive and reactive cybersecuritymeasures. Reactive measures include incident response plans, rapid recovery protocols, and the integration of machinelearning and artificial intelligence for real-time threat detection and mitigation. Moreover, considering the interconnectednature of the power grid, this study explores collaborative approaches among stakeholders, such as utility companies,government bodies, regulatory authorities, and cybersecurity experts, to foster information sharing, best practices, andstandardized protocols. Ultimately, this paper serves as a guide for policymakers, grid operators, and cybersecurityprofessionals to develop robust strategies that safeguard the stability of the power grid in the face of evolving cyberthreats and system dynamics. By implementing a holistic cybersecurity approach, the aim is to ensure resilience,reliability, and continuity in the delivery of electricity to society

show abstract

“…Z. Peng. This family was called a Z-source Inverter and abbreviated as ZSI [8][9][10][11] ZSI presents a single-stage inverter that combines the bucking and boosting capabilities for the input voltage within a single unit without adding extra switched devices. The basic structure of the single-stage topology is presented in Fig.…”

Section: Single-stage Systemmentioning

confidence: 99%

Micro Inverter Grid Connected for PV Application Based on SEPIC Differential Inverter

Ismeil,

S. Hussein,

Nasrallah

2023

SVU-International Journal of Engineering Sciences and Applicati

View full text Add to dashboard Cite

The problem of shading in photovoltaic systems has occupied a large part of the researchers' interests, and for this reason, the Micro-inverter (MI) is used as the solution, and the idea of manufacturing them depends on installing a small inverter with a low capacity to a small group of PV cells that agree with this rating. In addition to the interest in efficiency in the case of a connection in the standalone systems or grid electrical network. A traditional inverter was used, accompanied by a large low-frequency transformer to connect to the grid, and this led to higher costs and volume, then the idea of using different types of choppers appeared as a first stage to boost or buck the voltage, but the second stage beside the inverter stage led to higher costs, so the use of a single stage was the best solution. In addition, using MI with differential mode contributes to obtaining many advantages such as fewer passive elements (inductors and capacitors). This results in the reduced total cost and improved reliability. Among differential topologies of the AC inverters, a Single-Ended Primary-Inductor Converter (SEPIC) has been selected. This inverter was chosen because of its advantages, including the possibility of working in the boost or buck mode, and also a high-frequency pulse switching transformer can be used to act as an isolated step up/down the voltage in PV systems. The theory of differential SEPIC has been validated by PSIM software. The results will be compared with mathematical analysis.

show abstract

Resilient Model Predictive Adaptive Control of Networked Z-Source Inverters Using GMDH

Cited by 11 publications

References 45 publications

Deep Learning-Inspired IoT-IDS Mechanism for Edge Computing Environments

Deep Learning-Inspired IoT-IDS Mechanism for Edge Computing Environments

Safeguarding Stability: Strategies for Addressing Dynamic System Variations in Power Grid Cybersecurity

Micro Inverter Grid Connected for PV Application Based on SEPIC Differential Inverter

Contact Info

Product

Resources

About