Power Load Prediction Based on Multi-IoT Monitoring Sensors and Protection Detection Response Recovery Network Security Model
Source abstract
Abstract
With the expansion and deployment of smart metering in power grid management and control, the need for security protection in the power system is continuously growing.However, the current construction of a comprehensive defense system for terminal data is inadequate.In this paper, we report a study on power loads to address the security challenges facing grid management, using the protection detection response recovery (PDRR) network security model as the basis.Firstly, we design an end-to-end security perception architecture using IoT technology and develop an optimization model for monitoring sensor information.In addition, we construct a data aggregation model that improves adversarial domain adaptation and incorporates deep convolutional neural networks to extract features.The proposed model enhances short-term load forecasting by combining linear predictions from autoregressive models with the nonlinear trend analysis capabilities of deep learning models.The performance of the proposed method is compared with those of the Adam and stochastic gradient descent (SGD) optimizers.Experimental results confirm that the proposed method ensures reliable data transmission, facilitates effective classification aggregation of heterogeneous data, and yields fast and accurate load forecasting results.Furthermore, the proposed method enhances the robustness of the model.Sensors and Materials, Vol.36, No. 1 (2024) Detection, Response, and Recovery. (1,2)Among these elements, security detection is a proactive defense measure that requires security monitoring to address the vulnerabilities caused by unforeseen security threats.By employing various technological means to collect and analyze data from the power grid, it is possible to achieve a sense of situational awareness regarding the security of the distribution network.Currently, there is a need for research on deep networks that are more suitable for domain adaptation to overcome the limitations of deep learning.Convolutional neural networks (CNNs) were originally proposed by LeCun in France for postal code recognition. (3)Baid et al. improved the structure of one-dimensional CNNs and introduced the temporal convolutional network (TCN), an algorithm designed for time series data prediction. ( 4 Moreover, there are other deep learning networks such as recurrent neural network (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU).Deep domain adaptation enhances the traditional deep classification network structure by introducing adaptive layers to achieve the goals of data distribution adaptation.This method was initially introduced in the domain adaptive neural network (DaNN). (5)(6)(7)(8) Subsequently, numerous researchers have been influenced by generative adversarial networks (GANs), (9) which consist of generating networks and discriminating networks, and have made advancements in adaptive methods. (10)While these techniques of data aggregation and analysis are mature, they still encounter challenges in handling substantial amounts of diverse security data.Therefore, there is a pressing need for innovations using the IoT technology proposed. (11)With the popularization of IoT technology, it is particularly important to set up appropriate sensors in the field of power. (12,13)However, the research on the modeling of wireless sensor transmission in power systems is not perfect.In this study, we first construct a monitoring sensor optimization model to improve communication channels and design a distribution network security data aggregation model based on adversarial domain adaptation networks.Data is effectively classified through reasonable feature extraction.Secondly, we use real data from smart grid terminals to build a load prediction model based on AdaBelief optimization.The accuracy and robustness of the model are verified through simulation experiments.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Smart Grid and Power Systems · Technology and Security Systems · Wireless Sensor Networks and IoT
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References
Reference metadata was not supplied for this record.