The disclosure provides a method for planning a power distribution network, an apparatus for planning a power distribution network, and a storage medium. The method includes: establishing a model for planning the power distribution network, the model including a target function and constraints, the target function for minimizing a cost of the power distribution network when branches and nodes are installed into the power distribution network, the nodes including transformers and substations, the constraints including a power balance constraint of the power distribution network, a power constraint of the branches, a power constraint of the transformers, a radial operation constraint of the power distribution network, a fault constraint, a calculation constraint of indices of a reliability, a constraint of the indices of the reliability, and a logic constraint; and solving the model to determine whether the branches and the nodes are installed into the power distribution network.

A system and method for optimizing power grid operations and enhancing the life of switching components therein is provided. Current meteorological information of a region of operation of the power grid is collected during operation thereof, along with historical meteorological data of the region. A plurality of prediction models are executed using the current meteorological information and/or the historical meteorological data and a meteorological parameter of the region is forecast by selectively combining outputs of at least some of the executed prediction models, the meteorological parameter being a parameter that causes a renewable energy source in the power grid to generate power. The forecasted meteorological parameter is compensated with physical models and the historical meteorological data, and optimal switching operations of switching components in the power grid are computed based on the compensated forecasted meteorological parameter, with the switching components being controlled based on the computed optimal switching operations.

Disclosed in the present disclosure are a hybrid photovoltaic power prediction method and system based on multi-resource data fusion. The method includes: acquiring historical power sequence data and external meteorological data on a day to be predicted; inputting the data into a trained convolutional neural network prediction sub-model, long short-term memory network prediction sub-model and extreme gradient boosting tree prediction sub-model to predict photovoltaic power; classifying weather types according to a cloud cover on the day to be predicted, and determining prediction weights of the prediction sub-models; and fusing prediction results of the prediction sub-models based on the weights to obtain a final the prediction result of the photovoltaic power. The present disclosure integrates data of various different architectures, fully analyzes features of historical power data, meteorological data and satellite image data, and then fuses the data into unified data which is better and richer than single data.

The present disclosure provides systems and methods for flexible renewable energy power generation. The present disclosure also provides systems and methods for firming power generation from multiple renewable energy sources.

Technologies for switching network traffic include a network switch. The network switch includes one or more processors and communication circuitry coupled to the one or more processors. The communication circuitry is capable of switching network traffic of multiple link layer protocols. Additionally, the network switch includes one or more memory devices storing instructions that, when executed, cause the network switch to receive, with the communication circuitry through an optical connection, network traffic to be forwarded, and determine a link layer protocol of the received network traffic. The instructions additionally cause the network switch to forward the network traffic as a function of the determined link layer protocol. Other embodiments are also described and claimed.

An asset management method for a substation in accordance with the present invention generates a unique reliability model for each element of the substation by comparing reliability of a reference reliability model for each substation type with a health index of the each element thereof generated based on state data and real-time monitoring data of the each element of the substation and compensating the reference reliability model for the each element of the substation; assessing system reliability index and economic feasibility for each maintenance scenario based on a reference system reliability model for each candidate element subject to maintenance among the elements of the substation; selecting a maintenance scenario as a result of the health index and the unique reliability model for the each element of the substation, the system reliability index, and the economic feasibility and updating the unique reliability model for the each element of the substation by executing maintenance.

Embodiments implement non-intrusive load monitoring using machine learning. A trained convolutional neural network (CNN) can be stored, where the CNN includes a plurality of layers, and the CNN is trained to predict disaggregated target device energy usage data from within source location energy usage data based on training data including labeled energy usage data from a plurality of source locations. Input data can be received including energy usage data at a source location over a period of time. Disaggregated target device energy usage can be predicted, using the trained CNN, based on the input data.

Disclosed is a method of predictively maintaining equipment by means of a distribution map. The method can: extract a peak value based on a change in the amount of energy required for the equipment to perform a working process in a normal state; generate the distribution map based on the extracted peak value; and predictively detect, in advance, abnormalities of the equipment on the basis of a change in a distribution probability of a detection section having a low distribution probability and a somewhat high risk in the generated distribution map, so as to induce maintenance and replacement of the equipment to be carried out in a timely manner. Thus, enormous financial losses due to equipment failure may be prevented.

A method for predictive maintenance of equipment via a distribution chart is disclosed. Peak values are extracted based on a change in an amount of energy required for performing a work process by the equipment in a normal state, a distribution chart of the extracted peak values is constructed, and an abnormal symptom of the equipment is predictively detected in advance based on a change in distribution probability of a detection section having a low distribution probability and somewhat high risk in the constructed distribution chart thereof such that maintenance and replacement of the equipment are induced to be carried out at an appropriate time. Thus, an enormous monetary loss caused by a failure in the equipment may be prevented in advance.

A capacity configuration method and system of energy storage in a microgrid. In this application, the time-series data related to photovoltaic power generation is acquired and processed to obtain the preprocessed time-series data; a time-series generative adversarial network (Time GAN) is trained based on the preprocessed time-series data to perform data enhancement to obtain enhanced time-series data; and based on the enhanced time-series data, a distributionally robust optimization model is used to perform capacity configuration of energy storage.