Search

As technology advances, the use of Machine Learning (ML) in cybersecurity is becoming increasingly crucial to tackle the growing complexity of cyber threats. While traditional ML models can enhance cybersecurity, their high energy and resource demands limit their applications, leading to the emergence of Tiny Machine Learning (TinyML) as a more suitable solution for resource-constrained environments. TinyML is widely applied in areas such as smart homes, healthcare, and industrial automation. TinyML focuses on optimizing ML algorithms for small, low-power devices, enabling intelligent data processing directly on edge devices. This paper provides a comprehensive review of common challenges of TinyML techniques, such as power consumption, limited memory, and computational constraints; it also explores potential solutions to these challenges, such as energy harvesting, computational optimization techniques, and transfer learning for privacy preservation. On the other hand, this paper discusses TinyML’s applications in advancing cybersecurity for Electric Vehicle Charging Infrastructures (EVCIs) as a representative use case. It presents an experimental case study that enhances cybersecurity in EVCI using TinyML, evaluated against traditional ML in terms of reduced delay and memory usage, with a slight trade-off in accuracy. Additionally, the study includes a practical setup using the ESP32 microcontroller in the PlatformIO environment, which provides a hands-on assessment of TinyML’s application in cybersecurity for EVCI.

This paper proposes a practical and reliable decentralized load shedding strategy to protect the integrity of the direct-current (DC) microgrid. The proposed strategy utilizes time delays that automatically adapt to the DC microgrid operating conditions through continuous evaluation of the bus voltage variations, without depending on remote communication. It is evaluated in comparison with the conventional timer-based load shedding strategy. The studies are performed in the PSCAD software environment, on a detailed model of a DC microgrid that contains various types of loads and distributed energy resources. The results of the investigations show that the proposed adaptive time delay strategy (i) effectively restores the balance between the power demand and supply in the DC microgrid by quickly shedding the necessary amount of loads, (ii) is able to prioritize the non-critical loads by coordinating the load shedding steps based on a pre-determined order, (iii) prevents the steady-state values of the DC microgrid voltages from falling below a predetermined lower limit, (iv) significantly limits the voltage sags caused by power deficit in the microgrid, (v) is highly expandable and is able to coordinate a large number of load shedding steps, and (vi) improves the reliability of the electrical power provided to the DC microgrid loads, by avoiding inessential load shedding.

The mode-adaptive droop control (MADC) strategy enables bus voltage regulation and power sharing between the distributed energy resources (DERs) in the direct current (dc) microgrid without communication systems. The conventional MADC strategy may fail to provide acceptable voltage regulation and power sharing performance in large dc microgrids where the voltage drops across the dc lines are not negligible. This paper proposes an improved MADC strategy for the dc microgrid. The proposed control strategy minimizes the adverse effects of the aforementioned voltage drops on the bus voltage regulation and the power sharing between the DERs in the dc microgrid. The performance of the proposed control strategy is investigated under various operating conditions and disturbance scenarios, using a detailed and realistic dc microgrid study system that is modeled in the PSCAD/EMTDC software environment. The study results indicate that the proposed control strategy: 1) effectively maintains the power balance in the dc microgrid; 2) accurately regulates the dc bus voltages under various operating conditions; 3) improves power sharing between the DERs without using communication systems; 4) significantly reduces the circulating currents between the DERs in the islanded microgrid; and 5) enhances the dc microgrid reliability, flexibility, modularity, and scalability.

The direct current (DC) microgrid requires a fast load shedding scheme that prevents instability and voltage collapse when the distributed energy resources are unable to meet the power demand. The load shedding scheme is also expected to prevent unnecessary service interruptions caused by over-shedding of loads. This paper proposes an adaptive voltage-based load shedding scheme utilizing voltage thresholds that are automatically adjusted depending on the rate of change of locally measured bus voltages. The performance of the proposed load shedding scheme is investigated and compared with that of the conventional voltage-based load shedding scheme, using a realistic and detailed study system, under various disturbances. The comprehensive simulation studies that are conducted using the PSCAD software indicate that the adaptive load shedding scheme (i) effectively maintains the DC microgrid power balance through fast and coordinated load shedding, (ii) prevents the DC bus voltages from falling below acceptable levels, (iii) ensures that the critical loads do not experience excessive steady-state voltage deviations, (iv) minimizes the durations and magnitudes of the temporary voltage drop caused by sudden disturbances, and (v) improves power supply reliability.

Without utilizing costly communication systems, the existing protection strategies fail to reliably detect the occurrence and direction of faults in the inverter-dominated microgrid. To address this issue, this paper introduces a selective and reliable non-pilot protection strategy for the inverter-dominated microgrid. The proposed protection strategy (i) does not require communication signals, (ii) incorporates phase- and sequence-domain protective elements for reliable detection of symmetrical and asymmetrical faults, (iii) improves the existing sequence-domain directional elements and effectively utilizes them for accurate determination of the fault direction in the presence of inverter-interfaced distributed energy resources, (iv) selectively protects the inverter-dominated microgrid against internal and external faults, (v) is robust against the grid-connection mode of the microgrid, and (vi) enables fuse protection of laterals and non-critical circuits. The acceptable performance of the proposed protection strategy is verified through comprehensive fault studies conducted on a realistic study system simulated in the PSCAD/EMTDC software environment. This paper also demonstrates that the proposed protection strategy can be implemented using an off-the-shelf digital relay.

High-impedance faults (HIF) are difficult to detect because of their low current amplitude and highly diverse characteristics. In recent years, machine learning (ML) has been gaining popularity in HIF detection because ML techniques learn patterns from data and successfully detect HIFs. However, as these methods are based on supervised learning, they fail to reliably detect any scenario, fault or non-fault, not present in the training data. Consequently, this paper takes advantage of unsupervised learning and proposes a convolutional autoencoder framework for HIF detection (CAE-HIFD). Contrary to the conventional autoencoders that learn from normal behavior, the convolutional autoencoder (CAE) in CAE-HIFD learns only from the HIF signals eliminating the need for presence of diverse non-HIF scenarios in the CAE training. CAE distinguishes HIFs from non-HIF operating conditions by employing cross-correlation. To discriminate HIFs from transient disturbances such as capacitor or load switching, CAE-HIFD uses kurtosis, a statistical measure of the probability distribution shape. The performance evaluation studies conducted using the IEEE 13-node test feeder indicate that the CAE-HIFD reliably detects HIFs, outperforms the state-of-the-art HIF detection techniques, and is robust against noise.

This study proposes a versatile decentralised control strategy for the direct current (DC) microgrid based on the DC bus signalling method. Performance of the proposed control strategy is investigated under various generation and load disturbances in both grid-connected and islanded operation modes of the DC microgrid. The studies are conducted using a realistic DC microgrid study system simulated in the PSCAD/EMTDC software. The study results indicate that the proposed control strategy: (i) effectively maintains the power balance in the DC microgrid, (ii) effectively limits the DC bus voltage deviations under large disturbances, (iii) improves stability and dynamic response, (iv) does not curtail renewable power generation unless it is necessary, (v) does not require excessively large grid-tied converter and battery energy storage systems, and (vi) enhances system reliability, flexibility, modularity, and expandability.

Burn wounds are a common challenge for medical professionals. Current burn wound models hold several limitations, including a lack of comparability due to the heterogeneity of wounds and differences in individual wound healing. Hence, there is a need for reproducible in vivo models. In this study, we established a new burn wound model using the chorioallantoic membrane assay (CAM) as a surrogate model for animal experiments. The new experimental setup was tested by investigating the effects of the auspicious biophysical therapy, photobiomodulation (PBM), on the wound healing of an induced CAM burn wound with a metal stamp. PBM has been shown to positively influence wound healing through vascular proliferative effects and the increased secretion of chemotactic substances. The easily accessible burn wounds can be treated with various therapies. The model enables the analysis of ingrowing blood vessels (angiogenesis) and diameter and area of the wounds. The established model was used to test the effects of PBM on burn wound healing. PBM promoted angiogenesis in burn wounds on day 4 (p = 0.005). Furthermore, there was a not significant trend toward a higher number of vessels for day 6 (p = 0.065) in the irradiated group. Changes in diameter (p = 0.129) and the burn area (p = 0.131) were not significant. Our results suggest that CAM can be a suitable model for studying burn wounds. The novel experimental design enables reproducible and comparable studies on burn wound treatment., (© 2023. The Author(s).)

Angiogenesis is a highly regulated process. It promotes tissue regeneration and contributes to tumor growth. Existing therapeutic concepts interfere with different steps of angiogenesis. The quantification of the vasculature is of crucial importance for research on angiogenetic effects. The chorioallantoic membrane (CAM) assay is widely used in the study of angiogenesis. Ex ovo cultured chick embryos develop an easily accessible, highly vascularised membrane on the surface. Tumor xenografts can be incubated on this membrane enabling studies on cancer angiogenesis and other major hallmarks. However, there is no commonly accepted gold standard for the quantification of the vasculature of the CAM. We compared four widely used measurement techniques to identify the most appropriate one for the quantification of the vascular network of the CAM. The comparison of the different quantification methods suggested that the CAM assay application on the IKOSA platform is the most suitable image analysis application for the vasculature of the CAM. The new CAM application on the IKOSA platform turned out to be a reliable and feasible tool for practical use in angiogenesis research. This novel image analysis software enables a deeper exploration of various aspects of angiogenesis and might support future research on new anti-angiogenic strategies for cancer treatment.