The invention discloses a power quality monitoring system, which includes a power data acquisition module, and the like. The power quality monitoring system has the advantages as follows: power quality problems can be detected in real time to ensure residential and industrial power consumption demands; power compensation can be provided when the power quality is monitored to be abnormal; stream computing is coupled to the system, and high-performance transformation on the traditional signal transmission is carried out; interference can be reduced while monitoring data is ensured; misoperationof relay protection is eliminated; safe operation of a power grid monitoring system is improved; and the loss caused by abnormal power quality is reduced.

Power quality monitoring system

The invention provides a power grid planning big data analysis system, which comprises a big data server, and a big data management terminal and a monitoring operation terminal connected thereto. Thebig data server is in communication connection with a server of a power grid database system; multiple kinds of power grid data are read therefrom; according to multiple dimensions of power supply areas, natural months and voltage levels, the power grid data indexes, namely power supply, power utilization, power generation device operation, power transmission line and load index, are monitored; and comparison, analysis, calculation and display are carried out together with the power grid operation standard data. The professional "big data" is subjected to direct collection, finishing and analysis; timely discovery of the problems of the power grid is achieved; related project solutions are arranged; and power grid planning establishment quality and project reservation quality are improved.

Power grid planning big data analysis system

The invention discloses a power quality monitoring method. The method comprises steps of networking of a power data collection module, a power quality monitoring center, a query module, a power quality compensation module, an electromagnetic relay module and an alarm module and the like. The power quality monitoring method has the following advantages: power quality problems can be detected in real time to satisfy the residential and industrial power demands; power compensation can be provided while the abnormal power quality is monitored; on the basis of coupling of stream calculation and thesystem, high-performance modification is carried out on the traditional ground signal transmission effectively; the interference is reduced while the monitoring data is ensured; the relay protectionmisoperation is prevented, so that the safe operation of the power grid monitoring system is improved; and thus losses caused by the power quality abnormity are reduced.

Power quality monitoring method

The invention discloses a power load prediction method based on LSTM and LGBM, and belongs to the technical field of power load prediction, and the method comprises the following steps: carrying out the preprocessing; constructing an LSTM network containing a plurality of layers of neural units to obtain an LSTM model prediction value; calculating a cost function of the LSTM model; constructing anLGBM decision tree to obtain an LGBM model prediction value; calculating a cost function of the LGBM model according to the cost function of the LSTM model; and taking the negative direction of the model loss function gradient as a search direction, iteratively solving a target value by utilizing a gradient descent method, and calculating an average absolute percentage error MAPE. According to the method, the power load prediction model based on the LSTM long short-term memory neural network and the LGBM decision tree gradient improvement method is constructed, so that better fitting of powerdata is achieved, potential distribution information in existing data is fully mined, and the purpose of power load prediction tasks considering weather factors is accurately achieved.

Power load prediction method based on LSTM and LGBM

The invention provides a process-oriented visual analysis method for power system fault handling. Firstly, an analysis and evaluation index system for power grid operation fault disposal is established. Secondly, the weights and scoring elements of the evaluation indexes are allocated in the database. Then, select the fault event to be analyzed, start the analysis and evaluation, the analysis andevaluation module calculates independently, calculates the corresponding calculation value according to the configured scoring elements, and further calculates the overall evaluation result accordingto the configured weight; Finally, the evaluation results will be analyzed to form a visual evaluation report. The invention can fully embody the hierarchical relationship between the evaluation targets and the causality of the fault handling process, Tracing the specific causes of operational risk, tracking the progress of the implementation of fault disposal, leading to the evaluation of the effectiveness of fault disposal, to meet the operational risk assessment indicators and fault disposal process data streamlined cascade query service habits and functional requirements.

A process-oriented visual data analysis method for power system fault handling

The invention discloses a big data technology-based power distribution network operation state assessment system and method. The method mainly comprises the following steps of: 1) acquiring data of each power supply area of a smart power grid; 2) preprocessing the acquired data; 3) carrying out multisource heterogeneous data fusion on data from each system, and storing the received data to a Hadoop distributed file system (HDFS) in a real-time or timed manner; 4) calculating evaluation indexes of the power supply areas; 5) calculating a weight of each layer and obtaining operation state assessment results of A+ to E type power supply partitions and the current power supply area; 6) visualizing the operation state assessment results; 7) visually combining GIS data of an operation state assessment area to express different operation states on a map by using different colors; and 8) visually combining an open-source visual chart plug Echarts of Baidu to make a smart dashboard (Dashboard),and displaying a real-time operation state curve and a real-time state assessment result through the Dashboard.

Big data technology-based power distribution network operation state assessment system and method

The invention discloses a distribution network short-term load forecasting method based on multi-mode fusion, which mainly comprises the following steps: 1) collecting power network historical load sequence data X. 2) performing STL time series decomposition on that historical load time serie data X. 3) The LSTM neural network model with N kinds of structure of trend term serie, Xtrend and LSTM neural network model with N kinds of structure of residual term series Xremainder and an ensemble forecasting model are obtained. 4) that prediction result Os of the periodic term is obtained. 5) obtaining a prediction sample. 6) inputting that prediction sample into the prediction model, thereby obtaining a trend item prediction result Ot and a residual item prediction result Or. 7) integrating that prediction results Os of the cycle item, the trend item prediction result Ot and the remaining item prediction result Or, and using integrated forecasting to obtain a final forecasting result (shownin the description). The present invention contributes to improving the forecasting accuracy of the model while improving the robustness and generalization performance of the load forecasting model force.

A distribution network short-term load forecasting method based on multi-mode fusion

The invention discloses a hierarchical abstraction and compression method for a distribution network model. The distribution network model is abstractly divided into four layers: a plant station layer, a switch layer, a connectivity layer and a user layer, wherein the connectivity layer, the switch layer and the user layer are obtained according to a compression algorithm, the compression rule of which is as follows: the connectivity layer: a feeder line is a whole object which is compressed to a segment and connectivity switches among different feeder lines are retained; the switch layer: a transitional branch without a switch object is compressed and the tail end of a radiation pattern branch of a non-important user is compressed, and no pole and tower information is retained, and cyclic compression is carried out; and the user layer: a transitional branch without a switch object is compressed, important pole and tower information and user nodes are retained, and cyclic compression is carried out. According to the method disclosed by the invention, the topological attributes of a multi-sided hierarchical model and a GIS detailed model of the distribution network are fully consistent, thereby better blending the requirement of macro and micro decision-making views required by a power distribution operation decision on corresponding abstraction model of the distribution network.

Tang Shan

Papers

Big data technology-based power distribution network operation state assessment system and method

A distribution network short-term load forecasting method based on multi-mode fusion

Hierarchical abstraction and compression method for distribution network model