The escalating cyber-attacks targeting power infrastructure underscore the critical importance of smart grid security. However, existing solutions often struggle with the challenge of balancing security and performanc...
详细信息
ISBN:
(纸本)9798350318562;9798350318555
The escalating cyber-attacks targeting power infrastructure underscore the critical importance of smart grid security. However, existing solutions often struggle with the challenge of balancing security and performance overhead, leading to suboptimal protection or increased operational latency. To address this, we propose an intrusion detection system (IDS) designed to operate within P4-based programmable network devices, enabling real-time identification of critical attacks like distributed denial-of-service (DDoS) and false data injection (FDI). Central to our approach is a novel data structure optimized for time series data, capturing key information such as packet timing and data payload distribution. Leveraging decision trees, a robust machine learning technique, enables effective anomaly detection and prediction. Additionally, we integrate data compression techniques to reduce device memory usage while maintaining detection accuracy. Our evaluation results demonstrate minimal overhead in packet processing speed with 1 to 20 nanoseconds differences per packet, and enhanced data storage efficiency with compression ratios reaching up to 60.9%. Despite these optimizations, there is only a slight decrease in detection accuracy, such as a 2.81% drop in detecting false data injection attack (FDIA).
The current parallel resource allocation model of power network query engine task is mostly based on informatization model processing, and the allocation efficiency of parallel resources is relatively low, resulting i...
详细信息
ISBN:
(纸本)9798331530372;9798331530365
The current parallel resource allocation model of power network query engine task is mostly based on informatization model processing, and the allocation efficiency of parallel resources is relatively low, resulting in the decreasing allocation frequency, for this reason, we propose to design and analyze the design and analysis of the parallel resource allocation method of power network query engine task based on the cross-platform communication protocol. According to the current determination, real-time resource collection and preprocessing are carried out first, matching of resource feature points is carried out, cross-platform communication protocols are adopted to improve the allocation efficiency of parallel resources, cross-platform communication protocols are constructed for parallel resource allocation model of electric power network query engine task, and adaptive adjustment is adopted to realize resource allocation processing. Test results show that: compared with the cloud edge dynamic measurement resource allocation method, intelligent cooperative user scheduling and resource allocation, this design of cross-platform communication protocol power network query engine task parallel resource allocation method ultimately results in a relatively high frequency of allocation, which indicates that this design of cross-platform communication protocol power network query engine task parallel resource allocation method of real-time processing efficiency machine is targeted to a high degree, the effect of allocation is significantly improved, which has practical application value and innovative significance.
With the continuous development of the electricity market, the scale of power terminal access continues to expand, and distributed photovoltaic collection and control strategies have become an important research hotsp...
Occupancy refers to the presence of people in rooms and buildings. It is an essential input for IoT applications, including controlling lighting, heating, access, and monitoring space limitation policies. Occupancy in...
详细信息
ISBN:
(纸本)9798350369458;9798350369441
Occupancy refers to the presence of people in rooms and buildings. It is an essential input for IoT applications, including controlling lighting, heating, access, and monitoring space limitation policies. Occupancy information can also be used to improve users' comfort and to reduce energy waste in buildings. This paper evaluates the performance and resource consumption of recent machine learning techniques for occupancy detection and measurement by exploiting data from distributed environmental sensors. This evaluation is founded on a dataset captured by our dedicated sensor network for indoor monitoring, comprising temperature, humidity, and carbon dioxide (CO2) sensors. Using different sensor modalities and spatio-temporal data selections, we compare eight classification algorithms based on the accuracy achieved and the required runtimes. Binary classification for occupancy detection (OD) achieves accuracies over 90% for individual modalities and close to 100% for modality combinations. Multi-class classification for occupancy measurements (OM) shows as clear ranking of the sensor modalities, and gradient boosting algorithms are superior when combining sensor modalities and fusing data from multiple sensors.
The construction of a distributed heterogeneous data platform for power grid dispatching faces challenges of diversity, large scale, and high performance. However, existing data platform design methods in both the pow...
详细信息
ISBN:
(纸本)9798350375145;9798350375138
The construction of a distributed heterogeneous data platform for power grid dispatching faces challenges of diversity, large scale, and high performance. However, existing data platform design methods in both the power and computer science fields struggle to meet practical production requirements effectively. This paper constructs a distributed data storage architecture model for power grid dispatching, defining the elements and their relationships within the architecture. Additionally, it proposes methods for managing massive source data and distributed heterogeneous database clusters. Based on these findings, a power grid dispatching business data platform is designed. Test results indicate that the proposed architecture effectively supports the efficient execution of power grid dispatching business, providing a specialized data platform design paradigm for the power industry.
Under the premise of the reform of the power system, the spot market has ushered in an era of vigorous development. In the face of the complex and diverse users and electricity bill settlement methods in the spot mark...
详细信息
ISBN:
(纸本)9798350375794;9798350375800
Under the premise of the reform of the power system, the spot market has ushered in an era of vigorous development. In the face of the complex and diverse users and electricity bill settlement methods in the spot market, this study proposes a trial calculation method of complex and multi-user electricity charges in the spot market based on concurrent computing architecture. Based on the current situation of the spot market in China, this study establishes a learning model based on Apriori algorithm to explore the relationship between different electricity bill settlement packages and multiple users in the face of different types of electricity tariff calculation methods such as fixed time-sharing, tariff and hybrid and complex and diverse user categories. According to the correlation results, different electricity packages are applicable to different types of users, so the concurrent calculation method can be established to effectively improve the efficiency of electricity bill settlement.
The Minimum -Weight Parity Factor (MWPF) decoder is renowned for its accuracy in Quantum Error Correction (QEC) for various space-time codes, including surface codes and quantum LDPC codes. This work explores the scal...
详细信息
ISBN:
(纸本)9798331541378
The Minimum -Weight Parity Factor (MWPF) decoder is renowned for its accuracy in Quantum Error Correction (QEC) for various space-time codes, including surface codes and quantum LDPC codes. This work explores the scalability of MWPF decoders through parallelization, similar to parallel MWPM decoders. We introduce a dynamic fusion graph to schedule fusion operations in dynamic quantum circuits. It allows parts of the decoding graph to be solved and fused at a later stage, without having the full fusion tree at the very beginning. It also reduces the overhead caused by the traversing of the fusion tree. The dynamic fusion graph represents a novel and efficient method for real-time QEC decoding, providing enhancements in throughput and scalability for fault -tolerant quantum computing.
For a given positive integer k, the k-circle formation problem asks a set of distributed autonomous, identical, oblivious, asynchronous robots to form disjoint circles having k robots each at distinct locations. The r...
详细信息
We present two new assignments in the Peachy parallel Assignments series of assignments for teaching parallel and distributedcomputing. Submitted assignments must have been successfully used previously and are select...
详细信息
ISBN:
(纸本)9798350364613;9798350364606
We present two new assignments in the Peachy parallel Assignments series of assignments for teaching parallel and distributedcomputing. Submitted assignments must have been successfully used previously and are selected for being easy for other instructors to adopt and for being "cool and inspirational" so that students spend time on them and talk about them with others. The first assignment in this paper familiarizes students with the RAFT library for performing GPU-accelerated computation, pail of the RAPIDS AI ecosystem. Students use this library to accelerate a Radius Nearest Neighbor computation, finding all points within a given distance from a query point. In the second assignment, students parallelize a bird flocking simulation using OpenMP or OpenACC. It is a visual assignment which allows students to readily see the performance improvement.
HEPS is a fourth-generation synchrotron light source, and the experiments conducted at HEPS will transition to high-throughput, multi-modal, ultra-fast frequency, and cross-scale formats. The annual data flux generate...
详细信息
暂无评论