Dynamic thermal rating assessment of oil-immersed power transformers for multiple operating conditions

In this article,the dynamic thermal rating assessment method of oil-immersed power transformer with multiple operating conditions is proposed,considering the constraints of hot spot temperature(HST),top oil temperature,losses of life and the maximum allowable current of on-load tap changer(OLTC)or bushing,which can determine the dynamic load curves under different operating conditions and give the most sensitive constraints to limit the dynamic load capacity.To improve the accuracy of HST estimation,the temperature estimation model is also improved and the thermal parameters are optimised using the HST measured by optical fibre.Finally,several application examples are studied for transformers in different scenarios.The results show that the normal cyclic dynamic transformer rating(DTR)is mainly limited by the losses of life when the ambient temperature is high,and the average load factor can be increased to 0.82 with a maximum load capacity of 1.23.The main limiting factor of short-term DTR is the OLTC or bushing current constraint,and the average load factor can be increased to 1.00.The maximum load capacity of the transformer under both operating conditions is 23%and 50%higher than its rated load capacity,indicating that the transformer still has a large load potential available.

Skeleton-based Violation Action Recognition Method for Safety Supervision in Operation Field of Distribution Network Based on Graph Convolutional Network

Safety accidents in the operation field of the distribution network often occur,which seriously endanger the safety and lives of operators.Existing identification methods for safety risk can identify static safety risks,such as no-helmet,no-safety gloves,etc.,but fail to identify risks in the dynamic actions of operators.Therefore,this paper proposes a skeletonbased violation action-recognition method for supervision of safety during operations in a distribution network,i.e.,based on spatial temporal graph convolutional network(STGCN)and key joint attention module(KJAM),which can implement dynamic violation behavior recognition of operators.In this method,the human posture estimation method,i.e.Multi-Person Pose Estimation,is utilized to extract the skeleton information of operators during operations,and to construct an undirected graph,which reflects the movement and posture of the human body.Then,the STGCN is utilized to identify actions of operators that can lead to dynamic violations.In addition,the KJAM captures important joint information of operators.The effectiveness and superiority of the proposed method are verified in comparison to other action recognition methods.The experimental results show that the proposed method has higher recognition accuracy for common violations collected at the actual operation site of the distribution network and shows a strong generalization ability,which can be applied to the video monitoring system of field operations to reduce the occurrence of safety accidents.

Discharge characteristics of leader inception and development under 10 m long air gap—experimental observation and simulation results

The physical mechanism of leader formation and development is not well understood.In this study,we present experimental and simulation results obtained with a 10 m long air gap discharge.A 10 m outdoor discharge experiment is carried out to obtain the current,voltage,and optical image during the leader discharge process.Four different impulse voltages were applied to the rod‐plane gap.The measured current is used as an input for a plasma model,then the temperature and electric field could be calculated.The simulation results show that the temperature of the streamer stem during the dark period may exceed 2000 K.In addition,the critical charge required for leader initiation can be as low as 0.27μC for a 10 m air gap.The channel temperature is relatively stable in the process of leader development,which is maintained at about 4500 K.The electron density is about 0.5–3�1020 m-3,and the discharge channel conductivity fluctuates in the range of 1–10 S/m for the leader current between 1 and 2 A.A long dark period is tended to be associated with a higher injected charge by the first streamer.It is inferred that the voltage increments during the dark period play an important role in promoting streamer‐to‐leader transition,except for temperature and the injected charge.

Active Power Correction Strategies Based on Deep Reinforcement Learning Part I:A Simulation-driven Solution for Robustness

Employing the novel Deep Reinforcement Learning approach,this paper addresses the active power corrective control in modern power systems.Seeking to minimize the joint effect engendered by operation cost and blackout penalty,this correction strategy focuses on evaluating the robustness and adaptability aspects of the control agent.In Part I of this paper,where robustness is the primary focus,the agent is developed to handle unexpected incidents and guide the stable operation of power grids A Simulation-driven Graph Attention Reinforcement Learning method is proposed to perform robust active power corrective control.The aim of the graph attention networks is to determine the representation of power system states considering the topological features.Monte Carlo tree search is adopted to select the best suitable action set out of the large action space,including generator redispatch and topology control actions.Finally,driven by simulation,a guided training mechanism along with a long-short-term action deployment strategy are designed to help the agent better evaluate the action set while training and to operate more stably when deployed.The efficacy of the proposed method has been demonstrated in the“2020 I earning to Run a Power Network.Neurips Track 1”global competition and the associated cases.Part II of this paper deals with the adaptability case,where the agent is equipped to better adapt to a grid that has an increasing share of renewable energies through the years.

Active Power Correction Strategies Based on Deep Reinforcement Learning Part II:A Distributed Solution for Adaptability

This article is the second part of Active Power Correction Strategies Based on Deep Reinforcement Learning.In Part II,we consider the renewable energy scenarios plugged into the large-scale power grid and provide an adaptive algorithmic implementation to maintain power grid stability.Based on the robustness method in Part I,a distributed deep reinforcement learning method is proposed to overcome the infuence of the increasing renewable energy penetration.A multi-agent system is implemented in multiple control areas of the power system,which conducts a fully cooperative stochastic game.Based on the Monte Carlo tree search mentioned in Part I,we select practical actions in each sub-control area to search the Nash equilibrium of the game.Based on the QMIX method,a structure of offine centralized training and online distributed execution is proposed to employ better practical actions in the active power correction control.Our proposed method is evaluated in the modified global competition scenario cases of“2020 Learning to Run a Power Network.Neurips Track 2”.

Research on a prediction model for gas insulation performance based on Pareto optimisation

Predicting the insulation performance of SF_(6)substitute gases through gas molecular structures has been a popular topic worldwide.The difficulty is that the relationships between the molecular structure and the gas insulation strength,global warming potential and boiling temperature are not clear,and general linear methods cannot be used to effectively extract the key factors.Based on published molecular structure parameters,the grey correlation method is used to extract the factors that affect the gas dielectric strength,global warming potential and boiling temperature in a dynamic(non-linear)approach.Further,to predict the dielectric strength,global warming potential and boiling temperature of gases,a linear regression method and the factors with high correlations are used as independent variables.Through the Pareto optimal solution,the dielectric strength is set as the target,the global warming potential and boiling temperature are set as the constraints,and the ranges of the molecular structure parameters of the SF_(6)substitute gas are obtained.This research study provides an important reference regarding the SF_(6)substitute gas analysis and provides a research foundation for the design and synthesis of new environmentally friendly gases used in power equipment.