实现可持续的边缘计算框架,用于分散光伏系统的条件监测
Ibtihal Ait Abdelmoula1,2, Samir Idrissi Kaitouni2, Nassim Lamrini2
1SIRC/LAGeS laboratory-EHTP Hassania School of Public Works, Casablanca, Morocco.
Heliyon
|November 29, 2023
概括
本研究介绍了一个边缘计算框架,用于监控智能城市中分散的光伏系统. 人工神经网络 (ANN) 实现了故障检测的最佳性能.
科学领域:
- 计算机科学 计算机科学
- 电气工程 电气工程
- 可再生能源系统可再生能源系统
背景情况:
- 城市地区的数字革命需要对分散的可再生能源系统进行先进的监控.
- 对于光伏 (PV) 系统而言,传统的基于云的处理面临着速度,带宽和成本方面的挑战.
- 边缘计算为智能城市基础设施的实时数据处理提供了一个有前途的解决方案.
研究的目的:
- 提出和评估一种新的边缘计算框架,用于监测分散光伏系统的状况.
- 为了比较各种机器学习模型的性能,在网络边缘准确和低延迟的光伏故障检测.
- 调查监督方法和模型类型对异常检测性能的影响.
主要方法:
- 开发了一个新的边缘学习方案,在分散的边缘节点上部署机器学习模型.
- 四个轻快的机器学习模型 (CBLOF,LOF,KNN,ANN) 被选择并在本地训练.
- 该框架部署在一个智能太阳能校园中,并对各种异常场景进行了实验.
- 模型的评估基于f1分数,推断时间,RAM使用量,模型大小和监督方法.
主要成果:
- 被监督的人工神经网络 (ANN) 显示出卓越的性能,即使在具有挑战性的条件下,也获得了80%的f1得分.
- K-最近邻居 (KNN) 模型被证明是最合适的无监督模型,在多种场景中获得高f1分 (高达100%).
- 与基于云的方法相比,边缘计算有助于显著提高速度和减少带宽消耗.
结论:
- 拟议的边缘计算框架有效地解决了智能城市内的分散光伏系统中监控和故障检测的挑战.
- 监督 (ANN) 和无监督 (KNN) 机器学习模型都显示出在光伏系统中检测异常的巨大潜力,ANN提供了更高的整体准确性,KNN在无监督环境中提供了强大的性能.
- 基于边缘的机器学习是可持续智能城市能源管理的可行和高效战略.
相关概念视频
Power Factor Correction
182
The power transmission to a factory involves the transfer of apparent power, a combination of active and reactive power. The power factor measures how effectively electrical power is converted into useful work output. The ratio of the real power (KW) that does the work to the apparent power (KVA) supplied to the circuit.
182
Power System Distribution
240
Power system distribution involves delivering electrical energy from power plants to consumers through a network of transmission and distribution systems. The process begins at power plants, where energy from coal, gas, nuclear, water, and wind is converted into electrical energy. These plants use three-phase generators, typically rated between 50 to 1300 MVA, with terminal voltages ranging from a few kV to 20 kV, depending on the size and age of the units.
The transmission system is designed...
The transmission system is designed...
240
Fast Decoupled and DC Powerflow
204
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
204
Distributed Loads: Problem Solving
647
Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...
647
Conservation of AC Power
338
The principle of power preservation is applicable to both ac and dc circuits. This principle, when applied to AC power, asserts that the complex, real, and reactive powers produced by the source are equal to the total complex, real, and reactive powers absorbed by the loads. When two load impedances are connected in parallel to an ac source V, the complex power provided by the source can be calculated using the relation
338
Energy and Power Signals
305
In an electrical system with a resistor, voltage and current signals facilitate the measurement of power and energy across the resistor. For a continuous-time signal, the total energy over a time interval is defined as the integral of the square of the signal's magnitude over that interval. Mathematically, this is expressed as:
305


