RESUMO
This paper presents a novel incentive-based load shedding management scheme within a microgrid environment equipped with the required IoT infrastructure. The proposed mechanism works on the principles of reverse combinatorial auction. We consider a region of multiple consumers who are willing to curtail their load in the peak hours in order to gain some incentives later. Using the properties of combinatorial auctions, the participants can bid in packages or combinations in order to maximize their and overall social welfare of the system. The winner determination problem of the proposed combinatorial auction, determined using particle swarm optimization algorithm and hybrid genetic algorithm, is also presented in this paper. The performance evaluation and stability test of the proposed scheme are simulated using MATLAB and presented in this paper. The results indicate that combinatorial auctions are an excellent choice for load shedding management where a maximum of 50 users participate.
RESUMO
Nowadays, hackers take illegal advantage of distributed resources in a network of computing devices (i.e., botnet) to launch cyberattacks against the Internet of Things (IoT). Recently, diverse Machine Learning (ML) and Deep Learning (DL) methods were proposed to detect botnet attacks in IoT networks. However, highly imbalanced network traffic data in the training set often degrade the classification performance of state-of-the-art ML and DL models, especially in classes with relatively few samples. In this paper, we propose an efficient DL-based botnet attack detection algorithm that can handle highly imbalanced network traffic data. Specifically, Synthetic Minority Oversampling Technique (SMOTE) generates additional minority samples to achieve class balance, while Deep Recurrent Neural Network (DRNN) learns hierarchical feature representations from the balanced network traffic data to perform discriminative classification. We develop DRNN and SMOTE-DRNN models with the Bot-IoT dataset, and the simulation results show that high-class imbalance in the training data adversely affects the precision, recall, F1 score, area under the receiver operating characteristic curve (AUC), geometric mean (GM) and Matthews correlation coefficient (MCC) of the DRNN model. On the other hand, the SMOTE-DRNN model achieved better classification performance with 99.50% precision, 99.75% recall, 99.62% F1 score, 99.87% AUC, 99.74% GM and 99.62% MCC. Additionally, the SMOTE-DRNN model outperformed state-of-the-art ML and DL models.
RESUMO
The line-of-sight (LoS) channel is one of the requirements for efficient data transmission in visible-light communications (VLC), but this cannot always be guaranteed in indoor applications for a variety of reasons, such as moving objects and the layout of rooms. The relay-assisted VLC system is one of the techniques that can be used to address this issue and ensures seamless connectivity. This paper investigates the performance of half-duplex (HD) conventional DF relay system and cooperative systems (i.e., selective DF (SDF) and incremental DF (IDF)) over VLC channels in terms of outage probability and energy consumption. Analytical expressions for both outage probability and the minimum energy-per-bit performance of the aforementioned relaying systems are derived. Furthermore, Monte Carlo simulations are provided throughout the paper to validate the derived expressions. The results show that exploiting SDF and IDF relaying schemes can achieve approximately 25% and 15% outage probability enhancement compared to single-hop and DF protocols, respectively. The results also demonstrate that the performance of the single-hop VLC system deteriorates when the end-to-end distances become larger. For example, when the vertical distance is 3.5m, the single-hop approach consumes 20%, 40% and 45% more energy in comparison to the DF, SDF, and IDF approaches, respectively.
