Abstract: A photovoltaic system can include multiple photovoltaic power inverters that convert sunlight to power. An amount of power for each of the inverters can be measured over a period of time. These measurements, along with other data, can be collected. The collected measurements can be used to generate artificial neural networks that predict the output of each inverter based on input parameters. Using these neural networks, the total solar power generation forecast for the photovoltaic system can be predicted.

Abstract: Disclosed are various embodiments for optimizing energy management. A quantity of renewable power that will be generated by renewable energy generation sources can be forecasted. The energy demand for a building or a cluster of buildings can be forecasted. A pricing model for buying energy from a grid can be determined. A quantity of energy to import from the grid or export to the grid can be scheduled based on the quantity of renewable energy forecasted and the state of charge or health of battery energy storage system, current and future operations of building HVAC, lighting and plug loads system, the forecasted energy demand for the building, and the pricing of the energy from the grid.

Abstract: A computing device can generate predictions for future consumptions for one or more buildings based on a variety of factors. The factors can include a local climate corresponding to each building, a mass and heat transfer for each building, a daily operation for each building, and an occupancy behavior for each building. A power flow can be determined for one or more power generators. The power flow can be determined based on the predictions of future consumption. A control input vector can be determined for the one or more buildings.

Abstract: Disclosed are various embodiments for optimizing energy management. A quantity of renewable power that will be generated by renewable energy generation sources can be forecasted. The energy demand for a building or a cluster of buildings can be forecasted. A pricing model for buying energy from a grid can be determined. A quantity of energy to import from the grid or export to the grid can be scheduled based on the quantity of renewable energy forecasted and the state of charge or health of battery energy storage system, current and future operations of building HVAC, lighting and plug loads system, the forecasted energy demand for the building, and the pricing of the energy from the grid.

Abstract: A computing device can generate predictions for future consumptions for one or more buildings based on a variety of factors. The factors can include a local climate corresponding to each building, a mass and heat transfer for each building, a daily operation for each building, and an occupancy behavior for each building. A power flow can be determined for one or more power generators. The power flow can be determined based on the predictions of future consumption. A control input vector can be determined for the one or more buildings.

Abstract: Disclosed are various embodiments for predicting the occupancy of a space. Measurements of the occupancy of the space can be obtained. A change point can be detected based on the measurements. The occupancy and the number of occupants, if available, of the space for a future interval can be predicted using the data from the change point detected.

Abstract: A photovoltaic system can include multiple photovoltaic power inverters that convert sunlight to power. An amount of power for each of the inverters can be measured over a period of time. These measurements, along with other data, can be collected. The collected measurements can be used to generate artificial neural networks that predict the output of each inverter based on input parameters. Using these neural networks, the total solar power generation forecast for the photovoltaic system can be predicted.