Abstract: A method of controlling assets connected to an electricity distribution grid is disclosed. For each of a plurality of assets to be configured, a trained neural network model is provided, which takes an asset configuration as input, the asset configuration specifying a response of the asset to variations in one or more operating conditions detected at the asset, and outputs one or more performance indicators relating to the operation of the asset when operated using the asset configuration. The outputs of the neural network models are provided as inputs to an optimization function. A search process optimizes the optimization function by varying asset configurations for the assets. The final asset configurations are then used to control the assets to provide a coordinated demand response service.

Abstract: A method of controlling assets connected to an electricity distribution grid operating at a predetermined grid frequency is disclosed. The assets comprise assets supplying electrical energy to and/or consuming electrical energy from the grid, with at least some of the assets being configurable to adjust energy flow to or from the grid to counteract grid frequency fluctuations. The method includes configuring an aggregate response by a group of assets to fluctuations in the grid frequency, wherein the aggregate response comprises respective adjustments of energy flow between each of the group of assets and the grid. The adjustments are arranged in combination to counteract a fluctuation in grid frequency. A divergence is detected between a first grid frequency measured in a portion of the grid comprising a first asset of the group of assets and a second grid frequency measured in a portion of the grid comprising a second asset of the group of assets.

Abstract: A deep approximation neural network architecture which extrapolates data over unseen states for demand response applications in order to control distribution systems like product distribution systems of which energy distribution systems, e.g. heat or electrical power distribution, are one example. The method is a model-free control technique mainly in the form of Reinforcement Learning (RL) where a controller learns from interaction with the system to be controlled to control product distributions of which energy distribution systems, e.g. heat or electrical power distribution, are one example.

Abstract: Energy loads, sources or batteries exchange mathematical models with each other to form clusters of devices that together provide a service (self-reliance, frequency control, etc.) to a grid operator. Models are exchanged before or after forming clusters; a particular model is used to control its own device and is also used by another load/source to influence its control policy. Heuristics and an optimization technique (using models) are used to form a cluster of devices. Exchanging models obviates the need for a central entity to directly control loads/sources, and the need to exchange real-time data between loads/sources, providing resilience against communication failure. A service manager (demand-response aggregator) sends a service or technical constraints to loads/sources to form clusters on their own. Negotiation between manager and clusters occurs to form consensus on a response.

Abstract: Energy loads, sources or batteries exchange mathematical models with each other to form clusters of devices that together provide a service (self-reliance, frequency control, etc.) to a grid operator. Models are exchanged before or after forming clusters; a particular model is used to control its own device and is also used by another load/source to influence its control policy. Heuristics and an optimization technique (using models) are used to form a cluster of devices. Exchanging models obviates the need for a central entity to directly control loads/sources, and the need to exchange real-time data between loads/sources, providing resilience against communication failure. A service manager (demand-response aggregator) sends a service or technical constraints to loads/sources to form clusters on their own. Negotiation between manager and clusters occurs to form consensus on a response.

Abstract: A method or system for controlling an energy or power supply network having a coordination centre, a plurality of local end-user units and a communications network linking the local units and the coordination centre and a supply network connecting the local units and the coordination centre for energy or power supply. The supply network has constraints that limits power or energy consumption at at least one of the local end-user units. The method or system is adapted so that the coordination centre transmits a control signal indicating a degree of imbalance of the system to the at least one of the local end-user units, and the at least one local end-user unit is adapted to transmit a reaction signal to the coordination centre indicative of a power schedule for the local unit.

Abstract: Control methods, systems and controllers of devices in an electrical or heat distribution network which devices can be, for example, particularly or mainly thermostatically controlled loads (TCL) such as heat pumps. The methods are based on modeling a network with representative simulated tracer devices. Preferably, only a limited number of simulated tracer devices are used, i.e. limited in number compared to the number of devices in the electrical or heat distribution network. The simulated tracer devices are preferably governed by and have characteristics that are similar to those of actual devices in the electrical or heat distribution network or are representative of a major type of such devices. These simulated tracer devices can be used to represent behavior, for example, of an entire cluster of homogeneous or heterogeneous TCLs.

Abstract: A deep approximation neural network architecture which extrapolates data over unseen states for demand response applications in order to control distribution systems like product distribution systems of which energy distribution systems, e.g. heat or electrical power distribution, are one example. The method is a model-free control technique mainly in the form of Reinforcement Learning (RL) where a controller learns from interaction with the system to be controlled to control product distributions of which energy distribution systems, e.g. heat or electrical power distribution, are one example.

Abstract: Method and system for distributing and/or controlling an energy flow to a cluster of a plurality of nodes in an electricity network, wherein each node has an associated status, taking into account constraints relating to the energy delivered to the nodes and constraints relating to the electricity network, comprised of: allocating a local agent to each node of the cluster of a plurality of nodes, wherein the local agent receives a priority for energy to be delivered; allocating a regional concentrator agent to the regional network, comprising at least a part of the cluster, wherein a total of the at least one regional network forms the electricity network; receiving by the at least one regional concentrator agent, the priority for energy to be delivered among the nodes and determining an aggregate priority for energy to be delivered to the at least one regional network, depending on voltage limitations.

Abstract: The system comprises a controller comprising software components for determining the difference between the amount of energy determined by the smart grid agent to be delivered to and from the cluster over a predetermined period of time and the amount of energy measured by the meter actually delivered to the cluster over the predetermined period of time, the controller comprising software components for simulating a virtual smart grid participating device based on the determined difference and for providing the smart grid agent with information based on the determined difference such that the smart grid agent is configured to determine the amount of electrical energy in function of time to be delivered to and from the electrical grid for both the smart grid participating and non-participating devices of the cluster based on information of both the devices of the cluster and the smart grid and such that the difference is reduced.

Abstract: Method for distributing an energy flow to a cluster of a plurality of devices taking into account constraints relating to the energy to be delivered to the devices, comprising the steps of: A. gathering flexibility information of the respective devices in the cluster, combining the flexibility information of the devices of the cluster into flexibility information for the cluster, B. determining accumulated energy to be delivered in function of time over the predetermined period of time, C. supplying the determined accumulated energy to the cluster by obtaining, from the flow of energy, power in function of time based on the determined accumulated energy to be delivered in function of time, determining priority for power for all devices in the cluster and distributing the obtained power among the devices of the cluster.

Abstract: A method for buffering thermal energy comprises a thermal buffering medium contained by a thermal energy buffer. The volume of the thermal buffering medium is subdivided in one or more parts such that the different parts of the volume of the thermal buffering medium together form the total thermal buffering medium. The thermal energy buffer comprises a temperature sensor for each part. A controller has at least one signal representing at least one thermal energy value related to the thermal energy buffer. The thermal energy values comprise a predetermined minimum amount of thermal energy present in the thermal energy buffer. The controller controls a heater such that the amount of thermal energy present in the thermal energy buffer is higher than or equals the predetermined minimum amount of energy present in the thermal energy buffer.

Abstract: A method or system for controlling an energy or power supply network having a coordination centre, a plurality of local end-user units and a communications network linking the local units and the coordination centre and a supply network connecting the local units and the coordination centre for energy or power supply. The supply network has constraints that limits power or energy consumption at at least one of the local end-user units. The method or system is adapted so that the coordination centre transmits a control signal indicating a degree of imbalance of the system to the at least one of the local end-user units, and the at least one local end-user unit is adapted to transmit a reaction signal to the coordination centre indicative of a power schedule for the local unit.

Abstract: Method and system for distributing and/or controlling an energy flow to a cluster of a plurality of nodes in an electricity network, wherein each node has an associated status, taking into account constraints relating to the energy delivered to the nodes and constraints relating to the electricity network, comprised of: allocating a local agent to each node of the cluster of a plurality of nodes, wherein the local agent receives a priority for energy to be delivered; allocating a regional concentrator agent to the regional network, comprising at least a part of the cluster, wherein a total of the at least one regional network forms the electricity network; receiving by the at least one regional concentrator agent, the priority for energy to be delivered among the nodes and determining an aggregate priority for energy to be delivered to the at least one regional network, depending on voltage limitations.

Abstract: A method for buffering thermal energy comprises a thermal buffering medium contained by a thermal energy buffer. The volume of the thermal buffering medium is subdivided in one or more parts such that the different parts of the volume of the thermal buffering medium together form the total thermal buffering medium. The thermal energy buffer comprises a temperature sensor for each part. A controller has at least one signal representing at least one thermal energy value related to the thermal energy buffer. The thermal energy values comprise a predetermined minimum amount of thermal energy present in the thermal energy buffer. The controller controls a heater such that the amount of thermal energy present in the thermal energy buffer is higher than or equals the predetermined minimum amount of energy present in the thermal energy buffer.

Abstract: The system comprises a controller comprising software components for determining the difference between the amount of energy determined by the smart grid agent to be delivered to and from the cluster over a predetermined period of time and the amount of energy measured by the meter actually delivered to the cluster over the predetermined period of time, the controller comprising software components for simulating a virtual smart grid participating device based on the determined difference and for providing the smart grid agent with information based on the determined difference such that the smart grid agent is configured to determine the amount of electrical energy in function of time to be delivered to and from the electrical grid for both the smart grid participating and non-participating devices of the cluster based on information of both the devices of the cluster and the smart grid and such that the difference is reduced.

Abstract: A method for buffering thermal energy comprises a thermal buffering medium contained by a thermal energy buffer. The volume of the thermal buffering medium is subdivided in one or more parts such that the different parts of the volume of the thermal buffering medium together form the total thermal buffering medium. The thermal energy buffer comprises a temperature sensor for each part. A controller has at least one signal representing at least one thermal energy value related to the thermal energy buffer. The thermal energy values comprise a predetermined minimum amount of thermal energy present in the thermal energy buffer. The controller controls a heater such that the amount of thermal energy present in the thermal energy buffer is higher than or equals the predetermined minimum amount of energy present in the thermal energy buffer.

Abstract: Method for distributing an energy flow to a cluster of a plurality of devices taking into account constraints relating to the energy to be delivered to the devices, comprising the steps of: A. gathering flexibility information of the respective devices in the cluster, combining the flexibility information of the devices of the cluster into flexibility information for the cluster, B. determining accumulated energy to be delivered in function of time over the predetermined period of time, C. supplying the determined accumulated energy to the cluster by obtaining, from the flow of energy, power in function of time based on the determined accumulated energy to be delivered in function of time, determining priority for power for all devices in the cluster and distributing the obtained power among the devices of the cluster.