The automatic identification of the topology power networks is important for data-driven and situation-aware operation grids. Traditional methods lack a data-tolerant mechanism, accuracy their performance in terms thus affected by quality data. Topology related to link prediction problem. graph neural network can be used predict state unlabeled nodes (lines) through training on features labeled with fault tolerance. Inspired characteristics network, we applied it this study. We propose...

Transient stability assessment (TSA) based on security region is of great significance to the power systems. In this paper, we propose a novel methodology for online transient margin. Combined with geographic information system (GIS) and transformation rules, topology pre-fault flow characteristics can be extracted by 2D computer-vision-based images (CVPFIs). Then, convolutional neural network (CNN)-based comprehensive constructed map relationship between steady-state generator indices under...

With the increase of distributed generation penetration, economic operation microgrid has been fully developed. For islanded microgrid, due to lack large grid support and limited capacity (DG), energy supply may not meet need users in real time. Therefore, it is great significance solve problem insufficient power improve economy its operation. Firstly, this paper analyses frequency characteristics DG, establishes models oriented regulation introduces mathematical model DG. Then, an day-ahead...

Summary Load forecast is very important for power system operation. Pursuing higher accuracy of load always the major target this field. The existence bad historical data could badly affect accuracies time series–based techniques. Within multi‐node data, outliers them are merely appeared instantaneously; impact be decreased by making use spatial relativity data. A novel forecasting approach based on spatial‐temporal feature clustering proposed in paper. temporal regular pattern extracted...

Abstract Transient stability is the key aspect of power system dynamic security assessment, and data-driven methods are becoming alternative measures assessment. The current only construct correlations between variables while neglecting causal relationships. Therefore, they face problems such as poor robustness, which restrict their practical application. This paper introduces an improved constraint-inference approach for causality exploration transient stability. Firstly, a structure...

Under the vision of high proportion renewable energy power system in future, (RE) such as wind power/PV with variation and uncertainty, main supplier, brings great flexibility demand to system. Typical model considering only one type flexible resource planning method based on net load envelope will no longer applicable new complex scenarios. This paper introduces index quantitatively evaluate regulatory potential source-load-storage multi-type resources incorporate into an optimal decision...

Abstract Each person will have a different emotional experience for the same scene or exhibit, which reduces accuracy of recognition and leads to complexity evaluation visitors' in digital museums. In order improve user museums, optimization methods museums based on virtual reality (VR) technology emotion algorithm are studied. A spectrogram is generated according voice sent by tourists when they visit museum, CSWNet_CRNN depth learning model input, evaluates tourists' results draws their...

With the expansion of power grid scale and deepening component coupling, operation behavior system becomes more complex, traditional function decoupling dispatching architecture is not available anymore. Firstly, this paper studies corresponding relationship between reinforcement learning method decision problem, constructs artificial intelligent knowledge model based on (AIDLM). Then, a data-driven proposed, interpretable obtained. Finally, efficiency evaluation indexes proposed used to...

The deep learning algorithm represented by CNN has achieved remarkable results in complex feature extraction, classification and regression. Since the adopts an end-to-end training process, carrier of acquisition knowledge is a high-dimensional non-linear function, which hard to understand humans. Therefore, it difficult be widely used online decision-making engineering scenarios such as fast assessment power system transient voltage stability. In this paper, key input elements extracted are...

By deeply analyzed virtual reality technology, industrial robot assemble system and related software hardware platform, the overall structure fundamental configuration of training applying to general was put forward.The scene UI developed with Unity3D, Leap Motion used indentify hand gesture carry out human-machine interactions.The solution for models bundling uploading database, dynamically loading from database given.Finally, a prototype assembles based on Unity3D developed, feature achieved.

Transient stability margin assessment provides power grid dispatchers with important criteria for decision-making and preventive control. The computational efficiency of online transient can be largely improved the use steady-state information. In this paper, we propose a novel methodology assessment. A multi-swing based strategy that overcomes false identification issues previous methods is firstly illustrated. Based on strategy, composite neural network constructed trained offline to...

Model validation is a basic and important work to ensure the dynamic simulation accuracy which influences decision of power system design, planning, operation control. Because large scale systems have great many components, model very complex. A measurement-based software(PSMV) introduced in paper. Current can be evaluated by trajectory comparison between measurements simulations all around grid. Effects models parameters trajectories during disturbance investigated modification types...

Although numerical simulation is an important method of researching dynamic frequency process, obvious deviations have been found between and the measured trajectory in many accidents. And existing model parameters cannot describe actual process accurately. Research was carried out on influence four to which based WSCC system. The include inertia constant generator, generator coefficient, dead band turbine intermediate superheating coefficient. Northeast China power grid data are used verify...

This paper addresses the need to make judgments quickly and accurately after a transient stability failure in power system. A method for assessment of systems based on CapsNet is proposed. does not require manual calculation directly simulation data. Using self-learning ability strong feature extraction ability, offline training model used find mapping relationship between input data set stability, then online evaluation. effectively improves accuracy evaluation by constructing matrix; By...

Transient stability prediction under the concept of security region a power system can be used to identify potential unstable states and ensure its secure operation. In this paper, we propose method predict transient margin based on long short-term memory (LSTM) network attention mechanism (AM). This rapid accurate situational awareness operators in terms stability. The LSTM layer reduces dimension historical steady-state flow data, temporal characteristics are extracted from data....

With the rapid development of wind power industry, absorption problem has become an increasingly severe challenge which China's industry is faced with. In fact, through configuration large capacity thermal storage devices in existing system, electrothermal association system formed by combining electric with can not only increase peak load regulation but also local load, thus greatly improving absorptive system. This paper will make systematic analysis mechanism promoting utilizing devices,...

This paper discusses the method of solving forward and inverse kinematics industrial robot in simulation environment MATLAB with Robotics toolkit. In order to prove correctness solution kinematics, we determine final position given joint angle first, then use result kinematics. includes discussion space, displacement each joint, angler velocity, smooth acceleration robot. We divide borderline workspace on XZ surface into five arcs, generate arc workspace. proposes nested loop workspace,...

Fault detection and location is a critically significant application of supervisory control system in smart grid. The methods based on random matrix theory (RMT) have been practiced using measurements to detect short circuit faults occurring transmission lines. However, the diagnostic accuracy influenced by noise signal measurements. relationship between mean eigenvalue deduced this paper, defects Mean Spectral Radius (MSR) as an indicator fault are pointed out theoretically. Therefore,...