Department of Computer Science and Engineering, Institute of Technology, Nirma University, Ahmedabad 382481, India.
Institute of Computer Technology, Ganpat University, Ahmedabad 384012, India.
Sensors (Basel). 2022 May 26;22(11):4048. doi: 10.3390/s22114048.
Integrating information and communication technology (ICT) and energy grid infrastructures introduces smart grids (SG) to simplify energy generation, transmission, and distribution. The ICT is embedded in selected parts of the grid network, which partially deploys SG and raises various issues such as energy losses, either technical or non-technical (i.e., energy theft). Therefore, energy theft detection plays a crucial role in reducing the energy generation burden on the SG and meeting the consumer demand for energy. Motivated by these facts, in this paper, we propose a deep learning (DL)-based energy theft detection scheme, referred to as , which uses a data-driven analytics approach. uses a DL-based long short-term memory (LSTM) model to predict the energy consumption using smart meter data. Then, a threshold calculator is used to calculate the energy consumption. Both the predicted energy consumption and the threshold value are passed to the support vector machine (SVM)-based classifier to categorize the energy losses into technical, non-technical (energy theft), and normal consumption. The proposed data-driven theft detection scheme identifies various forms of energy theft (e.g., smart meter data manipulation or clandestine connections). Experimental results show that the proposed scheme () identifies energy theft more accurately compared to the state-of-the-art approaches.
将信息和通信技术（ICT）与电网基础设施集成，引入智能电网（SG）以简化能源的生成、传输和分配。ICT 被嵌入到电网网络的选定部分中，这部分部署了 SG，并引发了各种问题，如技术或非技术（即能源盗窃）损失。因此，能源盗窃检测在减轻 SG 的能源生成负担和满足消费者对能源的需求方面起着至关重要的作用。受这些事实的启发，在本文中，我们提出了一种基于深度学习（DL）的能源盗窃检测方案，称为 ，它使用数据驱动的分析方法。 使用基于深度学习的长短时记忆（LSTM）模型使用智能电表数据预测能源消耗。然后，使用阈值计算器计算能源消耗。预测的能源消耗和阈值都被传递给基于支持向量机（SVM）的分类器，将能源损耗分为技术损耗、非技术损耗（能源盗窃）和正常损耗。所提出的数据驱动的盗窃检测方案可以识别各种形式的能源盗窃（例如，智能电表数据操纵或秘密连接）。实验结果表明，与现有方法相比，所提出的方案（）能够更准确地识别能源盗窃。
