DeepCoin: A Novel Deep Learning and Blockchain-Based Energy Exchange Framework for Smart Grids

Abstract

In this paper, we propose a novel deep learning and blockchain-based energy framework for Smart Grids, entitled DeepCoin. The DeepCoin framework uses two schemes, a blockchain-based scheme and a deep learning-based scheme. The blockchain-based scheme consists of five phases; setup phase, agreement phase, creating a block phase and consensus-making phase, and view change phase. It incorporates a novel reliable peer-to-peer energy system that is based on the practical Byzantine fault tolerance algorithm and it achieves high throughput. In order to prevent smart grid attacks, the proposed framework makes the generation of blocks using short signatures and hash functions. The proposed deep learning-based scheme is an intrusion detection system (IDS), which employs recurrent neural networks (RNNs) for detecting network attacks and fraudulent transactions in the blockchain-based energy network. We study the performance of the proposed IDS on three different sources the CICIDS2017 dataset, a Power System dataset, and a Bot-IoT dataset.

Internet of Things Cyber Attacks Detection using Machine Learning

“…Table VI shows the comparison of the results obtained from the two studies. When the results are examined, it can be seen that the Random Forest algorithm used in our study is higher than that used in [14], and the same thing can be seen for most attack types with the NB algorithm. So, we can see that the new features used in our work increased the performance of both algorithms.…”

“…The final results of the implementation (see Table VI) are compared with a study in the literature. For this comparison, the study conducted by Ferrag et al [14] in 2019 was chosen. The reason for this is that the mentioned work used the same dataset as well as two machine learning methods similar to the ones we used.…”

“…The studies provide evidence that machine learning techniques can achieve success for attack detection. From the works discussing the issue of using machine learning for IoT security, the detection methodologies can be categorized as unsupervised methods [10], [12], [13], [14] and supervised methods [15], [16], [17], [9], [18].…”

“…[22] is another study that used the BoT-IoT dataset. 2018 Bot-IoT [10] 2018 Real dataset [8] 2016 Simulated dataset [12] 2018 N-BaIoT dataset [14] 2019 CICIDS2017-Simulated dataset-Bot-IoT [19] 2016 Simulated dataset [13] 2017 KDD /DARPA [20] 2015 Real dataset [15] 2017 Real dataset [21] 2018 Real dataset [18] 2018 Simulated dataset [16] 2017 USNW-NB15 [22] 2019 Bot-IoT [23] 2019 Real dataset [24] 2019 Bot-IoT [17] 2019 Bot-IoT…”

“…Moustafa et al [9] sought to address the shortcomings by designing the Bot-IoT dataset, which we used for our experiments. The Bot-IoT dataset incorporates legitimate and simulated IoT network traffic along with various types of attacks [14]. The BotIoT database attacks are classified into three types: Probing attacks, DoS, and theft information theft.…”