Knowledge distillation-based abnormal power consumption pattern detection for edge environmentFan, Yuanliang; Wu, Han; Li, Zewen; Lin, Jianli; Li, Lingfei; Huang, Xinghua; Chen, Weiming; Chen, Beibei
doi: 10.1088/1742-6596/2855/1/012001pmid: N/A
Abnormal power consumption pattern detection can effectively reduce the non-technical loss of electric energy, which is of great significance in maintaining the safe operation of the power grid and protecting the rights and interests of normal users. However, for edge environments with limited communication conditions, uploading electricity consumption data to the cloud for centralized computation is prone to problems such as network congestion and transmission delays. For this reason, this paper proposes a knowledge distillation (KD)-based anomalous power consumption pattern detection model that can be deployed at edge computing terminals. First, the ResNet50 network is selected as the teacher model, and the self-attention mechanism (SAM) is introduced to improve the feature extraction capability of long-term dependency. Then, ResNet18 is used as the student model, and the difference between the output of the student model and the output of the teacher model is minimized by optimizing the distillation loss function. Finally, the effectiveness of the proposed method is verified in practice.
Reactive power and voltage control based on reactive power compensation coefficient and sensitivity factorXie, Zhihua; Wei, Wenqi; Jia, Peng
doi: 10.1088/1742-6596/2855/1/012007pmid: N/A
Aiming at the problems that the existing reactive power allocation methods do not take into account the specific operating state of each doubly-fed induction generator (DFIG) and the established optimization model has many variables and is complicated, this paper proposes to construct an optimization model based on reactive power compensation coefficient and sensitivity factor, to reduce the number of variables in the mathematical model and simplify the expression of the relationship between each key parameter, so the speed of the reactive power and voltage control are improved. In the process of constructing specific optimization models, the objective of minimizing the active loss takes into account the operating copper consumption of each DFIG. The objective of minimizing the voltage fluctuation of each DFIG is also taken into account, in addition to the operating state constraints of each DFIG, so that the final reactive power allocation is more practical. In solving the multi-objective optimization problem, the improved NSGA-II algorithm is utilized, which can achieve the simultaneous optimization of multiple objectives, and when combined with the simplified model established in this paper, the correctness and speed of obtaining the optimal solution set of Pareto can be further improved. Finally, the effectiveness of the proposed strategy in reducing active losses and voltage fluctuations in wind farms is verified by simulation examples.
Harmonic characteristics analysis and power quality requirements of Light-Emitting Diode lamps used in nuclear power plant lighting systemLu, Jinjun; Jiang, Geling
doi: 10.1088/1742-6596/2855/1/012010pmid: N/A
This article conducts an in-depth study of the application of LED (Light-Emitting Diode) lamps in nuclear power plant lighting systems and conducts a comprehensive analysis of its impact on the power quality of the plant’s low-voltage AC power system. First of all, through a detailed discussion of the harmonic characteristics of LED lamps and the power quality requirements of nuclear power plants, it is pointed out that the harmonics of LED lamp drivers will inevitably have an impact on the power quality of low-voltage AC power systems. Therefore, the harmonic characteristics of LED lamps must comply with certain constraints. Subsequently, the application of LED lamps under different capacity transformers was analyzed and combined with relevant standards and specifications, and application suggestions for LED lamps in nuclear power plant lighting systems were put forward. Finally, measures to improve the total harmonic distortion rate of LED lamp current were discussed, emphasizing the importance of power factor correction technology. In summary, this article provides important reference and guidance for the application of LED lamps in nuclear power plants, helping to ensure the safe and stable operation of nuclear power plants.
A method for quality fault diagnosis based on Bayesian network D-cut setLi, Ziyan; Tong, Shanggao; Wang, Zhaowei
doi: 10.1088/1742-6596/2855/1/012002pmid: N/A
Quality issues are important factors restricting the development of hydrogen fuel cells. Quality problems in hydrogen fuel cells may stem from various stages, including technology, preparation processes, equipment used, usage environment, and personnel operation. Moreover, different problems are coupled with each other, resulting in the characteristics of one cause with multiple effects and multiple causes with one effect in the quality issues of hydrogen fuel cells. However, there are often similarities between these qualities in high-level information, such as mechanism, object, and behaviour, which are reflected in the similarity of network models in Bayesian diagnostic networks. Therefore, this article discusses how to reuse the Bayesian diagnosis network of previous quality problem cases to construct a Bayesian diagnosis network for hydrogen fuel cell quality problem diagnosis, thereby effectively improving the diagnosis efficiency of hydrogen fuel cell quality problems.
A smooth switching strategy for steady-state operation control and fault transient control of doubly fed induction generatorZhuang, Shenglun; Kong, Xiangmei; Qu, Huixing; Sun, Sujuan
doi: 10.1088/1742-6596/2855/1/012004pmid: N/A
As the proportion of wind power generation systems in power systems continues to rise, their dynamic response during system malfunctions has gained significant importance. As the grid short-circuit ratio continues to decrease, traditional fault ride-through algorithms for wind power generators may no longer be applicable. This is evidenced by voltage oscillations under significant disturbances and overvoltage issues during low-voltage ride-through, which are further aggravated during asymmetric fault conditions. Therefore, this paper focuses on the low-voltage ride-through issues of doubly fed induction wind power generators in weak power grids. It investigates the steady-state operation and transient control schemes and proposes a smooth transition strategy for steady-state and fault transient operations of doubly fed wind power generators. This approach guarantees the synchronization of active and reactive power, mitigates steady-state reactive power imbalance, and prevents voltage fluctuations triggered by recurring low-voltage ride-through occurrences. Furthermore, during fault recovery, a ramped active power restoration approach is employed to mitigate the coupling of active and reactive power introduced by the phase-locked loop, enabling rapid and stable restoration of active and reactive power outputs. As a result, superior dynamic performance is achieved during both symmetric and asymmetric fault processes. Finally, the superiority of the proposed smooth transition strategy under different fault scenarios is validated through simulations with the RTLAB platform.
Peer Review Statementdoi: 10.1088/1742-6596/2855/1/011002pmid: N/A
All papers published in this volume have been reviewed through processes administered by the Editors. Reviews were conducted by expert referees to the professional and scientific standards expected of a proceedings journal published by IOP Publishing.• Type of peer review: Single Anonymous• Conference submission management system: Morressier• Number of submissions received: 48• Number of submissions sent for review: 32• Number of submissions accepted: 19• Acceptance Rate (Submissions Accepted / Submissions Received × 100): 39.6• Average number of reviews per paper: 3• Total number of reviewers involved: 6• Contact person for queries:Name: XuexiaEmail: [email protected]: AEIC Academic Exchange Information Centre
The applicability study of the large wind farm wake effect modelHan, Yi; Li, Qian; Liu, Wei; Peng, Huaiwu; Zhang, Lihui
doi: 10.1088/1742-6596/2855/1/012006pmid: N/A
As the scale of the wind farm becomes bigger and the wind turbines are increasingly clustered, a large wind farm wake effect occurs. In this work, the initial distance where the large wind farm wake effect model starts to take effect is investigated analytically. The large wind farm wake effect is evaluated by constructing a large-scale wind farm with a regular arrangement of wind turbines similar to Horns Rev. The essential variables that influence the wind deficit trend of the large wind farm wake effect model are explored numerically. The wake deficit becomes more obvious as the surface roughness gets lower, the apparent turbine spacing gets smaller, or the thrust coefficient decreases. The wake deficits between the large wind farm wake effect model and the wake superposition of the modified Park model are compared. The transition distance, where the dominator of the wind deficit switches from the modified Park model to the large wind farm wake effect model, moves upstream along the incoming wind for the rougher surface or the lower thrust coefficient. In addition, for the similar resultant turbine spacing, the slightly staggered wind farm layout does not show an obvious influence on the wake deficit obtained by the large wind farm wake effect model.
Real-time voltage control of centralized and distributed coordination in active distribution network under multiple couplingDou, Wenlei; Tong, Yongji; Song, Zhuoran; Zhang, Mingli; Lu, Sichen; Zhu, Hongbo
doi: 10.1088/1742-6596/2855/1/012008pmid: N/A
At present, the “source-load interaction” distribution network operation mode has gradually replaced the “source-load operation” mode. The uncertainty and volatility of the distribution system have been enhanced, the controllability has been weakened, the voltage fluctuations have been frequent, and the power quality has been decreased. Voltage regulation is crucial to fully absorbing new energy generation and improving the operation safety of the active distribution network. To solve the problem of real-time control of distribution networks, this paper proposes a distributed voltage control method of active distribution networks with global sensitivity, establishes a distributed communication mechanism, and builds a distributed forward push-back communication rule to transfer power and voltage information between nodes. The global sensitivity of voltage, active power, and reactive power is used for real-time, independent, and effective control of multiple devices at each node, and the distributed control process is simulated according to actual production conditions. Furthermore, the centralized and decentralized real-time voltage control methods are proposed, and the centralized and distributed methods are implemented in medium voltage primary distribution network (MVPN) and low voltage secondary distribution network (LVSN), respectively, to play the advantages of high computing efficiency and fast control response. Based on model predictive control (MPC), intra-day rolling time scale voltage regulation is constructed, and second-level control is used to adapt the MPC results, finally promoting the optimal scheduling and rapid response of various controllable flexible resources in the multi-level active distribution network.
Solid-state supercapacitors based on different electrolytes: structural characteristics and comparative performanceJin, Guimei; Duan, Zhiyuan; Dong, Zhiwei; Zhou, Qihang
doi: 10.1088/1742-6596/2855/1/012009pmid: N/A
Solid-state supercapacitors bring huge potential for the next generation of energy storage systems and are especially significant for portable and wearable electronic devices, medical equipment, and smart textiles. This paper provides a concise overview of the device mechanism while discussing the developing status of solid-state supercapacitor electrolytes. The performance evaluation of solid-state supercapacitors is reviewed and compared based on their energy storage characteristics and electrode types (e.g., freestanding, fibre-based, and flexible), followed by an exploration of future research directions and key technical challenges in this field.