Abstract: Improvements in the field of electric vehicles (EV) are provided, including EV telematics estimation. Prior techniques estimate a state of charge (SoC) of a battery of an EV based on electrochemical measurements of the battery, such as battery terminal voltage, battery current, or cell temperature. The present improvements estimate SoC or other parameters based on non-electrochemical variables, referred to as exogenous information, meaning information other than electrochemical parameters of the battery. Example exogenous information includes battery type, and battery capacity, vehicle type or load, driver behaviour, weather conditions, or traffic or road conditions. Exogenous information may be used to enable more accurate estimations of EV SoC by EV related systems.

Abstract: A system and method for energy optimization is disclosed. The system may collect information from an information collector data including energy usage and storage data of at least one renewable energy generation system and battery energy storage system (BESS). The system may identify historical events that result in curtailment of renewable energy production, determine whether there is a curtailment of renewable energy production based at least on one historical event supervise the charge and discharge cycles of the at least one BESS; and ensuring that the diesel generators minimum up/down time is satisfied based on controlling at least one parameter of the BESS.

Abstract: Disclosed herein are embodiments for optimization of an energy grid system. First and second prediction models associated with a first energy grid system and a second energy grid system, respectively, may be trained based on historical data associated with each energy grid system. A prediction model basis may be created including the first and second prediction models. Training data associated with a third energy grid system may be input into each prediction model of the prediction model basis, and an accuracy of the prediction models may be evaluated to determine whether the prediction model basis is complete. When complete, a context-matching model may be trained based on subsequent energy grid systems until the context-matching model is determined to be sufficiently accurate. Then, the context-matching model may be used to identify a prediction model matching a new energy grid system, which may be used to warm-start the new energy grid system.

Abstract: Methods and systems relating to improvements in controlling power grid systems are provided. Improvements include dynamic tuning of compromise optimization control in power grid systems. The controlling of assets associated with a power grid system may include optimizing for several conflicting objectives. The performance of the optimization with respect to each objective may be monitored in real-time or near real-time and based on streaming and historic data relating to the system. The optimization may be adjusted in real-time or near real-time when it is determined that the performance of the optimization is not meeting specific levels of performance in regard to one or more of the conflicting objectives. Further, user input may be provided to the system to assign priority levels to one or more of the conflicting objectives.

Abstract: Improvements in computer-based energy asset management technologies are provided. An energy asset management system with a data summarization mechanism can perform computations, for example relating to controlling the assets, which may include electric vehicles (EVs), with fewer computing resources. Further, the system can perform computations on large datasets where such computations would have otherwise been impractical with conventional systems due to the size of the data. A large dataset relating to the energy asset management system is reduced using the summarization mechanism, and a computation model is trained using the reduced dataset. Energy assets in the system may be controlled using the trained computational model. Assets may include EVs, and controlling the EVs may be based on generated predictions relating to charging interactions. The predictions may be based on road traffic information and/or weather related information.

Abstract: Systems and methods are provided for dynamically selecting a control policy from among several available control policies for controlling an energy system having multiple controllable assets. The performance of the selected control policy is monitored and a different control policy may be deployed in its place if the different control policy has a higher chance of providing better performance given the current control environment. Thus, as the control environment changes, the control policy that controls the power system may also be changed in an adaptive manner. In this way, the control policies may be changed as the control environment changes to provide an improved real-time performance compared to the use of a single control policy.

Abstract: Disclosed herein are embodiments for optimization of an energy grid system. First and second prediction models associated with a first energy grid system and a second energy grid system, respectively, may be trained based on historical data associated with each energy grid system. A prediction model basis may be created including the first and second prediction models. Training data associated with a third energy grid system may be input into each prediction model of the prediction model basis, and an accuracy of the prediction models may be evaluated to determine whether the prediction model basis is complete. When complete, a context-matching model may be trained based on subsequent energy grid systems until the context-matching model is determined to be sufficiently accurate. Then, the context-matching model may be used to identify a prediction model matching a new energy grid system, which may be used to warm-start the new energy grid system.

Abstract: Methods and systems are provided relating to energy management of controllable assets in a system, such as vehicles in a fleet. Where the vehicle fleet has little or no historical data for a particular type of vehicle, for example electric vehicles, a data-driven based predictor for the fleet may be trained using third party data for that particular type of vehicle. This enables a data-driven control approach even when the fleet has little or no historical data of a give type. Historical data may include information relating to journeys travelled by vehicles on roads. A specific journey of a given vehicle may be subdivided into segments, and a segment signature data structure may be created and populated for each segment. The predictor(s) may be trained using data in a global repository of segment signatures. A fleet specific signature repository may be created for use by the fleet by selecting a subset of the signatures from the global repository.

Abstract: A system and method for energy optimization is disclosed. The system may collect information from an information collector data including energy usage and storage data of at least one renewable energy generation system and battery energy storage system (BESS). The system may identify historical events that result in curtailment of renewable energy production, determine whether there is a curtailment of renewable energy production based at least on one historical event supervise the charge and discharge cycles of the at least one BESS; and ensuring that the diesel generators minimum up/down time is satisfied based on controlling at least one parameter of the BESS.

Abstract: Systems and methods for dynamically charging energy storage devices connected to a power grid or other power system are provided. Charging decisions for charging the energy storage devices may be optimized, for example by basing the decisions on historical data, to provide more efficient or effective charging and use of power. The historical data may include an amount of energy previously discharged by each of the energy storage devices, a previous charging decision for each of the devices, a previous total fixed load power request of the power grid, and/or a pervious amount of power received by the power grid, which may include power received from intermittent power sources. In some aspects, the present techniques do not require current system state information or explicit predictions of future intermittent power availability. In some aspects, charging decisions are based on a solution to an online optimization problem.

Abstract: Systems and methods are provided for dynamically selecting a control policy from among several available control policies for controlling an electric vehicle fleet charging system. A control policy may take into account fluctuating local renewable generation and/or time of use electricity pricing. The performance of the selected control policy is monitored and a different control policy may be deployed in its place if the different control policy has a higher chance of providing better performance given the current control environment. Thus, as the control environment changes, the control policy that controls the power system may also be changed in an adaptive manner. In this way, the control policies may be changed as the control environment changes to provide an improved real-time performance compared to the use of a single control policy.

Abstract: Systems and methods are provided for dynamically selecting a control policy from among several available control policies for controlling an electric vehicle fleet charging system. A control policy may take into account fluctuating local renewable generation and/or time of use electricity pricing. The performance of the selected control policy is monitored and a different control policy may be deployed in its place if the different control policy has a higher chance of providing better performance given the current control environment. Thus, as the control environment changes, the control policy that controls the power system may also be changed in an adaptive manner. In this way, the control policies may be changed as the control environment changes to provide an improved real-time performance compared to the use of a single control policy.

Abstract: Disclosed herein are embodiments for optimization of an energy grid system. First and second prediction models associated with a first energy grid system and a second energy grid system, respectively, may be trained based on historical data associated with each energy grid system. A prediction model basis may be created including the first and second prediction models. Training data associated with a third energy grid system may be input into each prediction model of the prediction model basis, and an accuracy of the prediction models may be evaluated to determine whether the prediction model basis is complete. When complete, a context-matching model may be trained based on subsequent energy grid systems until the context-matching model is determined to be sufficiently accurate. Then, the context-matching model may be used to identify a prediction model matching a new energy grid system, which may be used to warm-start the new energy grid system.

Abstract: A system and method for energy optimization is disclosed. The system may collect information from an information collector data including energy usage and storage data of at least one renewable energy generation system and battery energy storage system (BESS). The system may identify historical events that result in curtailment of renewable energy production, determine whether there is a curtailment of renewable energy production based at least on one historical event supervise the charge and discharge cycles of the at least one BESS; and ensuring that the diesel generators minimum up/down time is satisfied based on controlling at least one parameter of the BESS.

Abstract: Systems and methods are described for distributed hierarchical artificial intelligence (AI) in smart grids using two levels. At a higher level, the AI center module sits at the high-voltage transmission or distribution substation level, and manages a few points of aggregations (POA). At a lower hierarchy, each POA consists of all controllable and non-controllable elements in distribution feeder, distribution transformer, or microgrid level. These elements include distributed energy resources, energy storage systems, residential and commercial energy management systems, electric vehicle charging stations, etc. Each POA may be logically and/or physically connected to other POAs. Within each POA, AI edge module calculates the optimal disaggregation of set-points received from the AI center module to the controllable elements based on local information, and information gathered from the AI center module.

Abstract: Disclosed herein are embodiments for optimization of an energy grid system. First and second prediction models associated with a first energy grid system and a second energy grid system, respectively, may be trained based on historical data associated with each energy grid system. A prediction model basis may be created including the first and second prediction models. Training data associated with a third energy grid system may be input into each prediction model of the prediction model basis, and an accuracy of the prediction models may be evaluated to determine whether the prediction model basis is complete. When complete, a context-matching model may be trained based on subsequent energy grid systems until the context-matching model is determined to be sufficiently accurate. Then, the context-matching model may be used to identify a prediction model matching a new energy grid system, which may be used to warm-start the new energy grid system.

Abstract: A method and system for short term wind power prediction using real time wind speed measurements is disclosed. The method includes receiving at least one real-time characteristic associated with at least one wind turbine, maintaining a database of characteristics associated with the at least one wind turbines, training a machine learning model based on one or both of the database of characteristics and the at least one characteristic, testing the accuracy of the at least one machine learning model and outputting from the machine learning model generated output data based on the training and testing data. Responsive to determining that the accuracy exceeds a predetermined value, one or both of wind speed and energy output of the at least one wind turbine can be calculated.

Abstract: A system and method for energy optimization is disclosed. The system may collect information from an information collector data including energy usage and storage data of at least one renewable energy generation system and battery energy storage system (BESS). The system may identify historical events that result in curtailment of renewable energy production, determine whether there is a curtailment of renewable energy production based at least on one historical event supervise the charge and discharge cycles of the at least one BESS; and ensuring that the diesel generators minimum up/down time is satisfied based on controlling at least one parameter of the BESS.

Abstract: Disclosed herein are embodiments for optimization of an energy grid system. First and second prediction models associated with a first energy grid system and a second energy grid system, respectively, may be trained based on historical data associated with each energy grid system. A prediction model basis may be created including the first and second prediction models. Training data associated with a third energy grid system may be input into each prediction model of the prediction model basis, and an accuracy of the prediction models may be evaluated to determine whether the prediction model basis is complete. When complete, a context-matching model may be trained based on subsequent energy grid systems until the context-matching model is determined to be sufficiently accurate. Then, the context-matching model may be used to identify a prediction model matching a new energy grid system, which may be used to warm-start the new energy grid system.

Abstract: Disclosed herein are embodiments for optimization of an energy grid system. First and second prediction models associated with a first energy grid system and a second energy grid system, respectively, may be trained based on historical data associated with each energy grid system. A prediction model basis may be created including the first and second prediction models. Training data associated with a third energy grid system may be input into each prediction model of the prediction model basis, and an accuracy of the prediction models may be evaluated to determine whether the prediction model basis is complete. When complete, a context-matching model may be trained based on subsequent energy grid systems until the context-matching model is determined to be sufficiently accurate. Then, the context-matching model may be used to identify a prediction model matching a new energy grid system, which may be used to warm-start the new energy grid system.