A computer system is configured to group solar power systems that provide electric power to an electricity distribution system into clusters. The computer system identifies a solar source meter in each of the clusters that is representative of the respective one of the clusters as a bellwether meter. Each of the bellwether meters monitors a power output of one of the solar power systems in one of the clusters. The computer system receives solar power generation data from the bellwether meters. The computer system generates a solar power generation forecast for each of the clusters of the solar power systems using the solar power generation data from the bellwether meters in respective ones of the clusters.

A method and system of controlling the time dependent transfer of electrical power between a first electrical network and a second electrical network is disclosed. The first electrical network is operable to provide instantaneous electrical power to the second electrical network located at a location, the second electrical network includes electrical generating capacity at the location based on stored energy accessible at the location. The method and system involves receiving at the second electrical network pricing information from the first electrical network, the pricing information associated with the future supply of electrical power by the first electrical network to the second electrical network and then modifying substantially in real time the transfer of electrical power between the first and second electrical networks in accordance with the pricing information and the electricity demand characteristics of the location.

Various embodiments include a method for operating a control platform for energy exchanges between a plurality of energy systems. The method may include: receiving information related to an intended energy exchange from the energy systems; calculating optimum energy exchanges between the energy systems; receiving a plurality of possible energy exchanges s from at least one of the energy systems; for each of the received possible energy exchanges s, performing an optimization method, and therefore calculating an associated partial solution Z(ζ.sub.s); calculating the total solution from the plurality of partial solutions Z(ζ.sub.s) depending on their probability values ζ.sub.z; and controlling energy exchanges between the plurality of energy systems by the control platform on the basis of the determined total solution.

An embodiment relates to a trash collection device comprising a trash receptacle with a unique identification and an opening to receive a class of trash; an identification scanner for recognizing a user; a trash item counter; a fill level sensor; a display configured to interact with the user; a compactor; a solar panel configured to charge a battery; a data communicator configured to communicate date to a cloud storage; a processor configured to generate incentive for the user; wherein the trash collection device is configured to be modular and configurable to connect with another similar trash collection device to enable to collect additional trash class and is configured to interact with each other through a common software. The device, method and system are further used to generate recycling analytics by using the stored data to provide incentives to users and to facilitate planning of downstream operations.

A photovoltaic string location update method and apparatus includes: obtaining, based on a physical map, a physical location of a first photovoltaic string corresponding to a first logical location in the physical map, the physical map indicating a correspondence between a logical location of a photovoltaic string and a physical location of the photovoltaic string, and the photovoltaic string includes the first photovoltaic string; and when the physical location of the first photovoltaic string in the physical map is different from a first actual physical location of the first photovoltaic string, updating the physical location of the photovoltaic string in the physical map to the first actual physical location, to obtain an updated physical map. The first actual physical location of the photovoltaic string is inconsistent with the physical location in the physical map, to prepare for subsequent operation and maintenance accurately performed on the photovoltaic string.

A method and system for regulating a multi-component power distribution network with high proportion of distributed power sources. The method includes: the distribution network regulation center acquiring user voltage information; the information and optimization model, performing iterative calculation of corresponding preset control objectives for the distribution network regulation center in the optimization model by a Lagrange algorithm, simultaneously controlling errors of the control objectives in the iterative calculation process by a Proportional-Integral-Differential (PID) algorithm, for acquiring a regulation signal of a user side local load, and sending the user side's local load regulation signal to the user side; and performing iterative calculation of control objectives based on the regulation signal of the local load and the calculation part of the optimization model user side, and simultaneously controlling errors of the control objectives in the iterative calculation process by the PID controller, to regulate the local load.

A method for predicting faults in power pack of complex equipment based on a hybrid prediction model is provided. The method includes steps of analyzing the typical faults of the power pack of complex equipment, extracting the core set of attributes therein, decomposing the time series of the power pack into a linear part and a non-linear part, using an Autoregressive Integrated Moving Average model to forecast the linear part, using an Artificial Neural Network model to forecast the residual obtained, and the predictions of the power pack are obtained by summing the predictions of the non-linear component with the linear component. The method further includes using the hybrid prediction model and the parallel parameters of the core attributes in combination with the upper and lower limits to obtain information on the operation status of the power pack.

Systems and methods related to resource distribution for a fleet of machines are disclosed. A system may include a fleet of machines each having an associated resource capacity and a resource requirement to perform a task. The system may further include a controller having a resource requirement circuit to determine an aggregated amount of the resource requirement and an aggregated amount of the resource capacity. A resource distribution circuit may adaptively improve, in response to an aggregated amount of the resource capacity, an aggregated resource delivery of the resource.

Methods and apparatus are provided herein. For example, a method for maintaining a power conversion system can include transmitting, to a computing apparatus in operable communication with the power conversion system, an alert message indicating non-working microinverters and which of the non-working microinverters are under warranty and eligible for replacement; receiving, from the computing apparatus, a request for replacement for the non-working microinverters; and transmitting, to the computing apparatus, an acknowledgment message indicating that the request has been successfully received and replacements for the non-working microinverters are being shipped.

Disclosed is a federated learning-based regional photovoltaic power probability forecasting method, mainly comprising steps of: pinpointing all photovoltaic power stations in a region which participate in a federated learning framework for probability forecasting, collecting information within a period of time and corresponding photovoltaic power variables, and sampling the variables according to time sequence into a sample dataset; processing missing values and outliers in the sample dataset resulting from the step; splitting the sample data set of the photovoltaic power stations into a training set and a testing set according to a preset proportion; normalizing the training set and the testing set, respectively; creating a federated learning framework; building, by a central server, a global forecasting model based on forecast requirements, defining a training error function and a precision requirement, and distributing the network architecture and initialized parameters to all photovoltaic power stations.