According to an embodiment of a first aspect of the invention, there is provided a distributed network comprising a plurality of nodes. Each of the plurality of nodes is configured to run one or more computational units comprising its own unit state. The network is configured to individually execute, by an execution subset of the plurality of nodes, s set of execution messages in a deterministic manner, thereby mutating the unit states of one or more of the computational units of the execution subset. The network is further configured to regularly make, by the nodes of the execution subset, a read snapshot of the unit states of the one or more computational units of the execution subset and to provide, by one or more nodes of the execution subset, user access to the read snapshot.

Further aspects of the invention relate to a corresponding computer-implemented method, a node, a computer program product and a software architecture.

Disclosed herein is a method of provisioning a message authentication protocol in a system of connected devices, the method comprising, by at least one of the connected devices: generating a private key and a public key; transmitting the public key to each other connected device; generating, by a sequence of hash operations using the private key, a hash tree, wherein each leaf node of the hash tree can have two or more values, each of the two or more values being associated with a respective nonce value, and wherein each leaf node has a hash computed from the concatenation of the respective nonce values; signing a root of the hash tree with the private key; and transmitting the root and the root signature to each other connected device.

A nanogrid and a virtual inverter controller for the nanogrid are disclosed. The nanogrid includes at least one parallel branch, and at least one branch is equipped with a protector. At least one of the protectors is equipped with one virtual inverter controller. The virtual inverter controller includes a sensor component configured to detect at least one characteristic parameter on the branch, and a control component affecting the electrical connection state of the corresponding protector of the virtual inverter controller according to the characteristic parameter.

Adaptive scanning is described. The adaptive scanning may include performing a passive scan of communications associated with a device, where the passive scan comprises observing one or more communications of the device over a network. One or more attributes associated with the device based on the passive scan are determined and an active scan of the device is performed based on the one or more attributes based on the passive scan. The active scan is customized for the device based on the one or more attributes determined based on the passive scan and the active scan comprises sending one or more requests to the device. One or more attributes associated with the device may be determined based on the active scan. The one or more attributes based on the passive scan and the one or more results based on the active scan associated with the device are stored.

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.

In one aspect, a method to determine a capacity of a microgrid includes applying a current test load to the microgrid and measuring a current through an energy storage device, the current indicating a charging status of the energy storage device based on a current load being applied to the microgrid through activated power outlets being served by the microgrid and the current test load, the energy storage device being integrated with the microgrid. The method also includes, responsive to a determination that the measured current based on the current load being applied to the microgrid and the current test load indicates that the energy storage device is discharging, determining the capacity of the microgrid, wherein the capacity is the current load being applied to the microgrid through activated power outlets and a test load applied to the microgrid immediately preceding the current test load.

A system and a method for regulating charging and discharging of an energy storage device as part of an electrical power distribution network is described. The invention is a smart control algorithm for a bi-directional switch in which an energy storage device, such as a battery set, is charged when electricity prices are low and discharged when electricity prices are high. The invention uses two different types of pricing data: forecasted price data and real-time price data. The forecasted price data is used to set a threshold. When the real-time price data of electricity exceeds this threshold, the energy storage device is set to discharge and send power to the grid. Otherwise the energy storage device is set to charge. The threshold is set periodically, typically in 30 minute to several hour intervals to capture the latest data.

System, method, and interface for visualized resource allocation and algorithms for the reallocation of resources to achieve a goal. The system analyses an initial state of resource allocation, a cost function for undesirable resources, and a set of potential incremental improvements, each with an associated cost, and determines a step-wise path of applying the incremental improvements to achieve an ultimate resource-allocation goal in an economically feasible way. Simultaneously, a user interface depicts the state of the allocation at the beginning, at the end, and along the path, allowing an intuitive understanding of how the goal will be achieved.

The present invention relates to a method for automatic translation of ladder logic to a SMT-based model checker in a network comprising defining (10) the topology of the network as an enriched network topology based on packets exchanged in the network, extracting (20) a program from the packets relating to a PLC in the network and identifying inputs, outputs, variables and a ladder diagram of the PLC, translating (30) the inputs, outputs, variables and ladder diagram into a predefined formal model, wherein the predefined formal model is a circuit-like SMT-based model checker, and wherein the translating (30) comprises translating the set of data types of the program according to a predefined model set of data types of the circuit-like SMT-based model checker, translating the inputs of the PLC as model inputs of the circuit-like SMT-based model checker of the same type, translating the outputs of the PLC as model output latches of the circuit-like SMT-based model checker of the same type, translating the variables of the PLC as model variable latches of the circuit-like SMT-based model checker of the same type, translating comparators and arithmetic operators of the ladder diagram into a plurality of predefined model functions of the circuit-like SMT-based model checker, translating contacts and coils of the ladder diagram according to predefined model recursive procedures relating to the predefined model set of data types, the model inputs, the model output latches, the model variable latches and the plurality of predefined model functions, wherein the contacts are switches that can block or allow the flow of the current in a connection and each of the contacts is controlled by a Boolean input or variable, and wherein the coils are assignments to Boolean variables.

According to some embodiments, a system, method and non-transitory computer readable medium are provided comprising a memory storing processor-executable steps; and a processor to execute the processor-executable steps to cause the system to: receive a first data value of a plurality of data values from a data store, wherein the first data value is from a digital twin model of an industrial asset; determine, via a vulnerability module, whether the received at least one data value is a near boundary case or not a near boundary case; in a case it is determined the first data value is a near boundary case, generate one or more adversarial samples for the first data value; input each of the one or more adversarial samples to the digital twin model; execute the digital twin model to output a system response for each input adversarial sample; determine whether the system response to each input adversarial sample has a negative impact; in a case it is determined the system response has a negative impact for a given input adversarial sample, update a trained attack detection model with the given input adversarial sample; and generate a second decision boundary based on the updated trained attack detection model. Numerous other aspects are provided.