SE2250614A1

SE2250614A1 - Optimized energy delivery

Info

Publication number: SE2250614A1
Application number: SE2250614A
Authority: SE
Inventors: Felix Mannerhagen; Niclas Jarhäll
Original assignee: Smartergy Ab
Priority date: 2022-05-24
Filing date: 2022-05-24
Publication date: 2023-11-25
Also published as: WO2023229504A1

Abstract

The present disclosure relates to a method, control system, a distributed energy storage system, a computer program carrier and a computer program product for optimized delivery of electricity in an electricity distribution network. The method comprises obtaining from a sensor system, sensor data associated with electricity consumption of at least one electricity-consumer and/or sensor data associated with electricity production of at least one electricity-producer coupled to the electricity distribution network. Further, the method comprises predicting a probability of a future electricity need of the at least one electricity-consumer and/or predicting a probability of future electricity production of the at least one electricity-producer based on the obtained sensor data. The method further comprises optimizing, based on the predicted probability of the future electricity need of the at least one electricity-consumer and/or the predicted probability of the future electricity production of the at least one electricity-producer, any one of an electricity storage scheme for an operationally decentralized distributed energy storage system coupled to the electricity distribution network, and an electricity delivery scheme for the at least one electricity-consumer. Further, the method comprises delivering, by the distributed energy storage system to the at least one electricity-consumer, an electricity need of the at least one electricity-consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme.

Description

TECHNICAL FIELD The present disclosure relates to optimized delivery and storage of electrical energy. More specifically, the aspects and embodiments of the present disclosure relate to systems and methods for optimizing delivery and storage of electricity in an electrical grid network.

BACKGROUND Changed lifestyles and future higher demands for uninterrupted electricity supply, new electricity-intensive industry, electrification of the transport sector and the transition to renewable energy production are the current and future trends in the modern society which are expected to lead to electricity capacity shortages in the electricity grid network. This imbalance in supply and demand of electricity has thus emerged as one of the society's biggest infrastructure-related problems today. This gap may even widen further over time with upcoming developments on the industrial and technological fronts such as mass adoption of electrical vehicles, and fast electrical vehicle-charging stations, etc. Since electric cars often will be fast-charged with high demands on power and energy the load on the distribution centers will inevitably increase.

Accordingly, there is a need for solutions in the art that are capable of efficient and automated storage and delivery of electricity to electricity consumers in line with the needs of each electricity consumer. SUMMARY lt is therefore an object ofthe present disclosure to provide a control system, a distributed energy storage system, a method, a computer program carrier, and a computer program product which alleviate all or at least some of the drawbacks of presently known solutions.

More specifically, it is an object of the present disclosure to alleviate problems related to storage and optimized delivery of electricity in an electricity distribution network. 2 These objects are achieved by means of a control system, a distributed energy system, a method, a computer program carrier, and a computer program product, as defined in the appended independent claims. The term exemplary is in the present context to be understood as serving as an instance, example or illustration.

According to a first aspect of the present disclosure, there is provided a method for optimized delivery of electricity in an electricity distribution network. The method comprises obtaining from a sensor system, sensor data associated with electricity consumption of at least one electricity-consumer and/or sensor data associated with electricity production of at least one electricity-producer coupled to the electricity distribution network. Further, the method comprises predicting a probability of a future electricity need of the at least one electricity- consumer and/or predicting a probability of future electricity production of the at least one electricity-producer based on the obtained sensor data. The method further comprises optimizing, based on the predicted probability of the future electricity need ofthe at least one electricity-consumer and/or the predicted probability ofthe future electricity production of the at least one electricity-producer, any one of an electricity storage scheme for an operationally decentralized distributed energy storage system coupled to the electricity distribution network, and an electricity delivery scheme for the at least one electricity- consumer. Further, the method comprises delivering, by the distributed energy storage system to the at least one electricity-consumer, an electricity need ofthe at least one electricity-consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme.

The inventors have realized that one of the outstanding advantages of the presented solution is to decrease C02 emissions and increase share of renewable energy in the electric grid, to supply Distribution System Operators (DSO) and their consumers' industry, households and transport sector with dependable and secure energy and power capacities. This will most likely minimize any "range anxiety" for the electric vehicle owners and increase savings of additional C02 by the use of electric vehicles and thus reach the Paris Agreement's zero-emission target 3-5 years earlier than today's forecast. 3 According to several exemplary embodiments, the electricity distribution network may comprise an electricity grid network or may be in communication with or coupled to an electricity grid network.

According to several exemplary embodiments of the present disclosure the predicting of the probability of the future electricity production of the at least one electricity-producer may comprise predicting a probability of any one of a future power production capacity ofthe at least one electricity-producer at a certain time-point, a future energy production capacity of the at least one electricity-producer under a certain period of time and/or under a certain time interval, a future combination ofthe power and energy production capacity of the at least one electricity-producer, one or more future combination(s) of the power and energy production capacity of the at least one electricity-producer to be delivered under one or more certain time period(s), one or more future combination(s) ofthe power and energy production capacity ofthe at least one electricity-producer to be delivered under one or more certain set of conditions. ln some embodiments, the predicting ofthe probability of the future electricity production of the at least one electricity-producer may further comprise predicting a probability of a future over-production of electricity by the at least one electricity producer, wherein the over- production of electricity is originated from one or more renewable electricity production source(s). ln some embodiments, predicting the probability of the future electricity need of the at least one electricity-consumer may further comprise predicting a probability of any one of a future power need ofthe at least one electricity-consumer at a certain time-point, a future energy need of the at least one electricity-consumer under a certain period of time and/or under a certain time interval, a future combination ofthe power and energy need ofthe at least one electricity-consumer, one or more future combination(s) ofthe power and energy need ofthe at least one electricity-consumer to be delivered under one or more certain time period(s), one or more future combination(s) of the power and energy need ofthe at least one electricity-consumer to be delivered under one or more certain set of conditions. ln several embodiments, the method may further comprise predicting the probability of the future electricity need of the at least one electricity-consumer and/or predicting the 4 probability ofthe future electricity production of the at least one electricity producer based on any one of an obtained frequency and/or voltage and/or electrical current change in the electricity distribution network, an obtained weather forecast information, an obtained electrical current and/or voltage and/or frequency parameters of an electricity grid network, coupled to the electricity distribution network, and/or of the at least one electricity-consumer and/or electricity-producer, an obtained electricity consumption and/or production rate under certain time intervals and/or at certain time-points, an obtained previous trend of electricity consumption and/or production in the electrical grid network. ln several embodiments, the distributed energy storage system may be a mixed energy storage system comprising one or more operationally decentralized distributed mixed energy storage unit(s), each mixed energy storage unit comprising at least one energy storage module being of an energy type of a plurality of energy types. ln several embodiments, optimizing the electricity storage scheme for the distributed energy storage system, may comprise optimizing any one of a geographical location of the one or more distributed mixed energy storage unit(s), a time-point and/or time period and/or time interval for storing electricity in the one or more distributed mixed energy storage unit(s), an amount of electrical power and/or electrical energy and/or energy type to be stored in the one or more distributed mixed energy storage unit(s), obtaining and storing the over- production of electricity from the one or more renewable electricity production source(s) in the one or more distributed mixed energy storage unit(s), and life-time of each of the one or more distributed mixed energy storage unit(s). Further, optimizing the electricity delivery scheme for the at least one electricity-consumer may comprise optimizing any one of a time- point and/or time period and/or time interval for delivery of electricity, stored in the one or more distributed mixed energy storage unit(s), to the at least one electricity-consumer, an amount of electrical power and/or electrical energy and/or energy type stored in the one or more distributed mixed energy storage unit(s), to be delivered to the at least one electricity- consumer, delivery ofthe over-production of electricity from the one or more renewable electricity production source(s) stored in the one or more distributed mixed energy storage unit(s).

According to several embodiments, the method may further comprise selecting at least one distributed mixed energy storage unit of the one or more distributed mixed energy storage unit(s) for delivering the electricity need of the at least one electricity-consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme.

According to some embodiments, predicting the probability ofthe future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity-producer may comprise providing the sensor data as input to a trained machine-learning algorithm configured to use the obtained sensor data to predict the probability of the future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity producer. Further, the method may comprise obtaining an output signal ofthe machine-learning algorithm comprising the predicted probability of the future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity-producer. ln some embodiments, the method may further comprise optimizing, by the trained machine- learning algorithm, the electricity storage scheme for the distributed energy storage system, and the electricity delivery scheme for the at least one electricity-consumer based on the obtained output signal of the machine-learning algorithm. ln several embodiments, the trained machine-learning algorithm may comprise a decentralized federated machine learning algorithm arranged at each one ofthe one or more distributed mixed energy storage unit(s).

According to yet second aspect of the present disclosure there is provided a system for optimized delivery of electricity in an electricity distribution network, the system comprising processing circuity configured to obtain from a sensor system, sensor data associated with electricity consumption of at least one electricity-consumer and/or sensor data associated with electricity production of at least one electricity-producer coupled to the electricity distribution network. The processing circuitry may be further configured to predict a probability of a future electricity need of the at least one electricity-consumer and/or predicting a probability of future electricity production of the at least one electricity-producer based on the obtained sensor data. Further, the processing circuitry may be configured to 6 optimize, based on the predicted probability ofthe future electricity need ofthe at least one electricity-consumer and/or the predicted probability of the future electricity production of the at least one electricity-producer, any one of an electricity storage scheme for an operationally decentralized distributed energy storage system coupled to the electricity distribution network, and an electricity delivery scheme for the at least one electricity- consumer. The processing circuitry may further be configured to deliver, by the distributed energy storage system to the at least one electricity-consumer, an electricity need ofthe at least one electricity-consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme.

According to a further third aspect, there is provided a computer program carrier carrying one or more computer programs configured to be executed by one or more processors of a processing circuitry, the one or more programs comprising instructions for performing the method according to any one ofthe embodiments of the method herein, and wherein the computer program carrier is one of an electronic signal, optical signal, radio signal or a computer-readable storage medium.

According to yet another fourth aspect, there is provided a computer program product comprising instructions which, when the program is executed by one or more processors of a processing circuitry, causes the processing circuitry to carry out the method according to any one ofthe embodiments of the method herein.

According to a fifth aspect, there is provided a distributed energy system comprising one or more distributed mixed energy storage unit(s) configured to store and/or deliver electricity; and a system according to any one of the embodiments of the system according to the second aspect of the present disclosure configured to control storage of electricity in the one or more distributed mixed energy storage unit(s) and/or delivery of electricity to at least one electricity-consumer coupled to an electricity distribution network in communication with the distributed energy storage system.

Further embodiments of the different aspects are defined in the dependent claims. 7 lt is to be noted that all the embodiments, elements, features and advantages associated with the first aspect also analogously apply to the second, third, fourth and fifth aspects of the present disclosure.

These and other features and advantages ofthe present disclosure will in the following be further clarified in the following detailed description.

BRIEF DESCRIPTION OF THE DRAWINGS Further objects, features and advantages of embodiments of the disclosure will appear from the following detailed description, reference being made to the accompanying drawings. The drawings are not to scale.

Figs. 1a-b are schematic block diagrams illustrating an electricity distribution network according to the present disclosure; Fig. 2 is a schematic block diagram of a control system in accordance with several embodiments of the present disclosure; Fig. 3 is a schematic flowchart illustrating a method in accordance with several embodiments of the present disclosure; and Fig. 4 is a schematic illustration of a distributed energy system in accordance with an embodiment of the present disclosure. DETAILED DESCRIPTION Those skilled in the art will appreciate that the steps, services and functions explained herein may be implemented using individual hardware circuitry, using software functioning in conjunction with a programmed microprocessor or general purpose computer, using one or more Application Specific Integrated Circuits (ASICs) and/or using one or more Digital Signal Processors (DSPs). lt will also be appreciated that when the present disclosure is described in terms of a method, it may also be embodied in one or more processors and one or more memories coupled to the one or more processors, wherein the one or more memories store one or more programs that perform the steps, services and functions disclosed herein when executed by the one or more processors. 8 ln the following description of exemplary embodiments, the same reference numerals denote the same or similar components.

Fig. 1a illustrates a schematic view of an example of an optimized electricity distribution network 1 for optimized storage and delivery of electricity according to several aspects and embodiments of the present disclosure. According to several exemplary embodiments, the electricity distribution network 1 may comprise an electricity grid network 50 or may be in communication with or coupled to one or more electricity grid networks 50.

The optimized electricity storage and delivery network 1, which may simply be referred to as the network 1, comprises one or more electricity-producer(s) 30a-30c which in some embodiments may be coupled to the electricity grid network 50 via a plurality of power lines 50a. The network 1 further comprises one or more electricity-consumers 40a-40c which may similarly be coupled to the electricity grid network 50 via a plurality of power lines 50b. lt should be appreciated by the person skilled in the art that electricity-consumer in the present context is not only limited to the end users 40a-40c such as buildings as shown in Fig. 1a but depending on various circumstances, conditions and intended applications may include any entity which consumes any form of electricity such as the end users 40a-40c coupled to the grid network 50, the electricity grid 50 itself, other electricity grid networks (not shown) in connection with the electricity grid network 50, distributed storage units 100a-100m as described in the following, etc. ln several exemplary embodiments, the at least one electricity-consumer may be at least one of a chargeable electrical vehicle, a home charging station, a public charging station, a transmission system operator, TSO, a distribution system operator, DSO and a charging station operator, CSO, the electricity grid network owner, commercial building complexes, smart homes, various energy-intensive industrial entities, etc.

For aiding the reader however, hereinafter when discussing electricity consumers with respect to various aspects and embodiments, reference will be made to the end users 40a-40c as illustrated in Fig. 1a. Analogously, by an electricity-producer in the present context it is meant an entity capable of producing electrical power and electrical energy which may be consumed by at least one electricity-consumer. Accordingly, electricity-producer in the present context is not only limited to the power plants 30a-30c as shown in Fig.1a but depending on various 9 circumstances, conditions and intended applications may include several entities such as the end users 40a-40c coupled to the grid network 50 e.g. in installations involving battery-to-grid or vehicle-to-grid configurations providing their stored surplus electricity to the grid. Further, the electricity-producer may include the electricity grid 50 itself, other electricity grid networks (not shown) in connection with the electricity grid network 50, and the distributed energy storage units 100a-100m supplying the grid 50 and the one or more electricity consumers with electricity, etc. For aiding the reader however, hereinafter when discussing electricity producers with respect to various aspects and embodiments, reference will be made to the power plants 30a-30c illustrated in Fig. la.

The network 1 further comprises an operationally decentralized distributed energy storage system 100 as shown in the example of Fig. 4 comprising one or more operationally decentralized distributed mixed energy storage unit(s) 100a-100n, 100n-100m, wherein a the electricity grid network 50. ln various aspects and embodiments the transmission lines 101 for transmitting electricity may be implemented separately from transmission lines 101 for relaying information. However, in various aspects and embodiments the transmission of electricity and information between the energy storage units 100a-100m and the grid network 50 may be integrated in the same transmission lines 101. The transmission lines 101 may also be configured to enable both wired and wireless information transmission technologies. ln addition to this, each ofthe at least one distributed mixed energy storage units 100a-100m may be in communication with a communication network 20a-20m which may be an external communication network or a cloud network 20a-20m. The at least one electricity-consumer 40a-40c and the at least one electricity-producer 30a-30c may also be connected to the external communication networks 20a-20m. The external communication networks 20a-20m may be configured for transmission of information and data among the distributed energy storage units 100a-100m and the at least one electricity-producer 30a-30c and electricity-consumers 40a-40c as well as the grid network 50.

The electricity producers 30a-30c and/or electricity consumers 40a-40c may be directly e.g. via the at least one external communication network 20 and power transmission lines and/or indirectly e.g. via the grid network 50 and/or via a command center 200 be coupled to distributed energy storage system 100. For instance, in the example of Fig. 1a, the electricity- consumer 40a is connected to the distributed storage unit 100m via the external network 20m. The electricity-consumer 40b is similarly connected to the storage unit 100n via the external network 20n and the electricity-consumer 40c connected to the storage unit 100a via the external network 20a. Similarly, the electricity-producer 30a is connected to the storage unit 100a via the external network 20a, the electricity-producer 30b is connected to the storage unit 100n via the external network 20n and the electricity-producer 30c is connected to the energy storage unit 100m via the external network 20m. This way the electricity- consumers 40a-40c are enabled to communicate their electricity consumption such as historic and/or real-time electricity consumption data to the distributed energy storage system 100. Analogously, the one or more electricity-producers 30a-30b are also enabled to communicate the historic and/or real-time electricity production capacity data such as power and/or energy production capacity to the distributed energy storage system 100. The electricity producers and/or the electricity consumers in the example of Fig. 1a are also in communication with the distributed energy storage system 100 via the grid network 50 through the transmission lines 101. The energy storage units 100a-100m are enabled to obtain sensor data associated with electricity consumption of at least one electricity-consumer 40a-40c and/or sensor data associated with electricity production of at least one electricity-producer 30a-30c coupled to the electrical grid network 50. This way a variety of predictions, estimations, and optimizations 11 can be carried out by a control systems 10 of the distributed energy storage system 100 for optimized storage and delivery of electricity to the electricity-consumers based on the real- time and/or future electricity needs and/or available or future production capacity in the electricity grid network 50. The control system 10 ofthe distributed storage units 100a-100m may in several embodiments be in communication with the command center 200 as shown in the example of Fig. 4. The command center 200 may oversee the entire operation of the distributed energy storage system 100, be responsible to handle communications with the grid network 50, be responsible to handle communications with the at least one electricity- consumer 40a-40c and/or the at least one electricity-producer 30a-30c, decide over the operation standards, prediction and optimization models used by the energy storage units 100a-100m, etc. ln several aspects and embodiments, the electricity-producers 30a-30c and/or electricity- consumers 40a-40c may optionally be connected to several energy storage units e.g. to any one of energy storage units 100a-100m in Fig. 1a via the respective external networks 20a- 20m. This way, each electricity-producer/consumer may communicate electricity production and/or consumption to several energy storage units 100a-100m to maximize the opportunities of optimized delivery of power needs, energy needs or any combination of power and energy needs at certain points in time or over certain time periods. ln other words, each electricity- consumer will be served by the most suitable electricity storage unit 100a-100m, among the plurality of available energy storage units 100a-100m, matching the specific needs of each electricity consumer at any given time. ln several aspects and embodiments, the electricity- producers 30a-30c and/or electricity-consumers 40a-40c may be connected to several energy storage units e.g. to any one of energy storage units 100a-100m in Fig. 1a via their respective power transmission lines (not shown).

Alternatively or additionally as shown in Fig. 1a, each electricity-producer 30a-30c and/or electricity-consumer 40a-40c may transmit its information, sensor measurements, or parameters such as power and/or energy capacity or needs or any combination thereof to the grid network 50 via the power lines 50a, 50b and the grid network 50 will in turn communicate and transmit these information and data to the respective energy storage units via the transmission lines 101. 12 ln some embodiments, the grid network 50 may transmit the information obtained from the at least one electricity-consumer 40a-40c and/or from the at least one electricity producer 30a-30c to the distributed energy storage units 100a-100m via the external networks 20a- 20m. ln some embodiments, the grid network 50 may transmit the information received from each electricity-consumer 40a-40c to the electricity-producers 30a-30c and the respective electricity-producers 30a-30c will in turn communicate, e.g. via the external networks 20a- 20m, such information to the distributed energy storage system 100.

Clearly any of the above-mentioned entities may be connected to each other in other ways than the above examples based on the design and implementation requirements. For instance, as shown in Fig. 1b, the distribution network 1 may comprise one or more standalone units 210 wherein the at least one electricity-consumer and the distributed energy storage system 100 or one or more of the energy storage units 100a-100m comprised in the energy storage system 100 may be coupled together without the need to be connected to the electricity grid network 50. This exemplary embodiment enables implementation of self- sustaining energy storage and delivery units 210 to be deployed in so-called "island operation" configurations without the need to be connected to an electricity grid network 50. Each of the distributed energy storage unit(s)100a-100m, may be implemented as operationally decentralized units which in the present context is to be understood that each unit is independently operated by its own dedicated control system 10 configured to process the obtained electricity consumption and/or production data locally without any influence from the outside of each energy-storage hub, thus conforming with the prevailing user privacy standards.

Further, each distributed energy storage system 100a-100m may be implemented as a mixed energy storage unit meaning that various types of energy sources may be implemented in energy storage modules, such as the energy storage modules IVI1-IVIk, Mk-Mn shown in Fig. 4, 1 energy storage unit 100a-100m.

For instance, chemical battery modules, hydrogen energy storage modules, hydrogen carrier energy storage modules such as NH3, CH3OH-H2O and cycloalkanes for large-scale distribution and for on-site hydrogen generation and storage, biofuel energy storage modules, 13 fossil fuel-based energy storage modules such as diesel electricity generator modules, solar energy storage modules, wind power energy storage modules, etc. may be implemented and installed in each ofthe distributed storage units 100a-100m, providing a collection of different energy types and energy storage technologies ready to store and deliver electricity to the grid network 50 and/or electricity consumers. ln addition to installation of various energy types in each energy storage unit, the concept of mixed energy storage unit in the present context should also be understood as various combinations of electrical power and electrical energy which will be delivered to the electricity consumers. Accordingly, delivery of combinations of power and energy may be provided from different combinations of energy sources. For instance, if an electricity consumer requires a certain amount of power at a certain time-point, this power need may be provided from energy source IV|1 being of energy type 1 e.g. chemical battery modules. However, the same electricity-consumer may require delivery of electrical energy under a certain period of time. Accordingly, the selected mixed energy storage unit may provide the required energy need of the electricity-consumer from the energy source IVIk being of energy type k e.g. hydrogen energy module. ln other words, mixed energy storage unit in the present context not only includes a combination of various energy sources and types implemented in each of the distributed energy storage units but also comprises various combinations and ratios of power needs and energy needs of the at least one electricity-consumer which will be delivered by the mixed energy storage units. Similarly, some energy modules may be suitable for delivery of high power needs and some energy modules might be suitable for long-term storage and/or delivery of energy needs. ln the context of the present disclosure, when referring to "power need" of an electricity consumer, it is meant the rate at which the electricity consumer will consume electricity at a certain time-point or per unit of time having the SI unit "Watt".

By "energy need" in the present context it is meant the amount of electrical power consumed by the electricity-consumer over a certain period of time having the SI unit "Joule".

Accordingly the present inventors have realized that the proposed solution of the modular mixed energy storage system 100 comprising the modular energy-storage hubs 100a-100m enables to efficiently provide any one of power needs of an electricity consumer at a certain 14 instance and/or energy needs of an electricity consumer under a certain period of time and/or a combination of power and/or energy needs of the electricity consumer. Further, it is made possible to accurately predict what combination of the above will be required by a certain electricity consumer at a certain time point, under a certain period of time or under specific circumstances such as specific weather or traffic conditions.

Each distributed energy storage unit 100a-100m comprises a control system 10a-10m collectively referred to as the control system 10 hereinafter. The control system 10 comprises processing circuitry 11 which is configured for optimized delivery of electricity which in the present context encompasses any one of prediction, optimization, storage and delivery of electricity in an electrical grid network 50 in accordance with several aspects and embodiments of the present disclosure. As shown in Fig. 2, the control system 10 is configured to obtain from a sensor system 6, sensor data associated with electricity consumption of at least one electricity-consumer 40a-40c and/or sensor data associated with electricity production of at least one electricity-producer 30a-30c coupled to the electrical grid network 50.

The sensor system 6 may comprise any number of sensor devices 6a-6n, and any type of sensor devices configured to measure various parameters of the electricity network 1 such as voltage, current, frequency, temperature, power, etc. The sensor system 6 may be installed and implemented in various entities and nodes ofthe grid network 50, be connected to utility meters or smart meters for measuring and reporting the electricity usage by the at least one electricity consumer 40a-40c, be connected to several entities of the at least one electricity- producer 30a-30c to monitor and measure electricity production capacity, be connected to each distributed energy storage unit 100a-100m for measuring associated parameters such as voltage, current, frequency, temperature, power, state of charge or energy/power capacity of each unit 100a-100m, etc. ln some embodiments, the control system 10 may obtain the sensor data directly from the one or more electricity-consumers 40a-40c and/or from one or more electricity-producers 30a-30c. Alternatively or additionally, the control system 10 may obtain the sensor data via the electricity grid network 50 by the transmission lines 101 and/or via the respective external networks 20a-20m for each distributed unit 100a-100m. ln various embodiments, the obtained sensor data may comprise information about a state of charge of the at least one electricity-consumer 40a-40c, a charging duration ofthe at least one electricity-consumer, a power and/or energy consumption level of the at least one electricity- COHSUmeF, etC.

As mentioned earlier, the control system 10 of each distributed energy storage unit may be implemented as a stand-alone decentralized processing and control system which only has access to a predefined amount, or category of user data. Accordingly, the user data including the data obtained from the one or more electricity-consumers 40a-40c may be anonymized and utilized by the control system 10 without any user identification information. ln some embodiments, the data obtained from the grid network 50 and/or the data obtained from the at least one electricity-producer 30a-30c may also be anonymized by the control system 10. Thus, any consumer/producer information such as sensitive personal data will be adequately protected. ln some examples, a scheme of access rights may be defined to regulate the access rights of each entity to the data. ln various embodiments and aspects, federated learning algorithms may be implemented in each energy storage hub to ensure that the obtained data remains anonymized and is only shared with the parties having the necessary security access rights.

Consequently, the decentralized distributed energy storage units 100a-100m are prevented from sharing user information with other entities or energy units as well as with a central system such as the command center 200 without the proper access rights. Therefore, the distribution network 1 of the present disclosure operates in line with fulfilling the prevailing user data and privacy protection standards. Another advantage ofthe decentralized control system 10 is to delegate the processing and decision making based on the obtained user data to each of the distributed energy storage units 100a-100m which in turn makes the whole process considerably faster and computationally efficient compared to conventional system which centrally gather and process user data. The control system 10 of each distributed energy storage unit 100a-100m is configured to predict a probability of a future electricity need of the at least one electricity-consumer 40a-40c and/or predict a probability of future electricity production ofthe at least one electricity-producer 30a-30c based on the obtained sensor data from the sensor system 6.

According to several aspects and embodiments, the control system 10 may be configured to predict the probability of the future electricity production ofthe at least one electricity- 16 producer by predicting a probability of a future over-production of electricity by the at least one electricity producer 40a-40c, wherein the over-production of electricity is originated from one or more renewable electricity production source(s) 60. Thus, the renewable energy produced by the renewable electricity production sources could be injected into the grid network 50 and/or directly employed to address the needs of the one or more electricity consumers 40a-40c.

For instance, with reference to Fig. 1b, the exemplary unit 210 comprises the electricity consumers 40a-40c in communication with the distributed energy storage system 100, as well as the renewable energy production resources 60. ln this example the node 61a created from such an interaction is subject to various sensor measurement as mentioned above. Optionally node 61b may be created to monitor the over-production of the electricity ofthe renewable source 60 by the grid network 50. The sensor system 6 may be couple to nodes 61a, 61b and measure any one of frequency, voltage or current variations in the nodes 61a, 61b. Based on the obtained sensor data from nodes 61a, 61b the electricity needs of the one or more electricity-consumer 40a-40c may be provided by the distributed energy storage system 100. The electricity stored in the distributed energy storage system 100 may have been provided from the renewable sources 60 or from the electricity grid 50. ln some examples wherein the one or more standalone units 210 are in communication with the grid network 50, the control system 10 may be configured to set a cap on the peak amount of electricity which may be received from the grid network 50, so as to alleviate or prevent electricity price surcharges for the one or more electricity consumers. Thus, the one or more electricity consumers may advantageously obtain their electricity needs extending above the peak cap, from the distributed energy storage system 100 for a lower price. ln several embodiments and aspects the control system is configured to predict the probability of the future electricity need of the at least one electricity-consumer and/or predicting the probability ofthe future electricity production of the at least one electricity producer based on various parameters of the electricity grid network 50. The parameters may be obtained via real-time or historical sensor measurements ofthe sensor system 6 and/or from historical data regarding electricity consumption and production in the electricity grid network 50. The historical data may be stored on external servers or on cloud networks such as cloud network and be obtained by the control system 10 on demand. 17 ln various embodiments, the real-time and/or historical data and parameters may comprise any one of an obtained frequency and/or voltage and/or electrical current change in the electricity distribution network 1, an obtained weather forecast information, an obtained electrical current and/or voltage and/or frequency parameters of the electricity grid network 50, coupled to the electricity distribution network, and/or of the at least one electricity- consumer and/or producer, an obtained electricity consumption and/or production rate under certain time intervals and/or at certain time-points, an obtained previous trend of electricity consumption and/or production in the electrical grid network 50.

The control system 10 may be configured to predict the probability of the future electricity production of the at least one electricity-producer 30a-30c by predicting a probability of a future electrical power production capacity of the at least one electricity-producer at a certain time-point; further, by predicting a future electrical energy production capacity of the at least one electricity-producer 30a-30c under a certain period of time and/or under a certain time interval. Additionally or alternatively, the control system 10 may be configured to predict the probability of the future electricity production of the at least one electricity-producer 30a-30c by predicting a future combination of the electrical power and energy production capacity of the at least one electricity-producer 30a-30c. Further, the control system 10 may be configured to predict one or more future combination(s) of the electrical power and energy production capacity of the at least one electricity-producer to be delivered under one or more certain time period(s). Further, the control system 10 may be configured to predict one or more future combination(s) of the electrical power and energy production capacity of the at least one electricity-producer to be delivered under one or more certain set of conditions.

The control system 10 may also be configured to predict the probability ofthe future electricity need ofthe at least one electricity-consumer by predicting a probability of any one of a future electrical power need ofthe at least one electricity-consumer at a certain time- point, a future energy need ofthe at least one electricity-consumer under a certain period of time and/or under a certain time interval, a future combination of the power and energy need of the at least one electricity-consumer, one or more future combination(s) of the power and energy need ofthe at least one electricity-consumer to be delivered under one or more certain time period(s), one or more future combination(s) ofthe power and energy need of 18 the at least one electricity-consumer to be delivered under one or more certain set of conditions.

The certain time-points and or certain time periods in the present context may comprises examples such as a certain time of a day, a week, a month, a year, a certain time period such as a peak electricity demand period during a day, during a weeks, during a month, during a year, etc. Certain set of conditions in the present context may comprise examples such as certain weather conditions e.g. rainfall, snow conditions, wind or storm conditions, etc. Further, peak traffic conditions, traffic congestion states and similar in a geographical region, peaked usage of electrical appliances in commercial centers, office spaces, etc., certain times of day for certain periods of time correlated with worker commute information, etc. which may affect the electricity consumption of the at least one electricity consumer. lt should be appreciated by the persons skilled in the art that the above considerations regarding various time points, time durations and/or certain set of conditions are monitored and factored in dynamically by the control system 10. This is in contrast to conventional systems which may attempt to provide the grid network with additional resources at fixed peak usage or off-peak usage periods. Here, the control system 10 obtains information based on historic and/or real-time data of various parameters and in turn provides predictions based on such obtained data. This way real-time and/or future needs of each electricity-consumer is matched with the real-time and/or future production capacity of each electricity-producer and any off-balance in the production/consumption cycle could be compensated for by the distributed energy storage system 100. Further, even when there may be no off-balance in the grid network 50, the electricity needs ofthe at least one consumer may be delivered by the distributed energy storage system 100, e.g. by providing better electricity pricing, suitable matching of power/energy need combinations, etc. According to another example, instead of delivering a certain amount of power or energy to the electricity grid network at a fixed predefined peak usage hour during the day, the control system 10 predicts based on the obtained data and the above-mentioned parameters that the future peak usage time on a certain day may shift based on several factors such as specific traffic conditions on that specific day, weather conditions in an area on that specific day, planned construction work in an area under a certain time period during that specific day, affected electricity production rates by the electricity producers on that specific day, variations in the price of electricity, 19 variation of production and demand in different times ofthe year such as in the tourist season, consumer behavior changes, driver behavior changes in charging/driving electric vehicles, or the like. Thus, the control system 10 dynamically and efficiently optimizes and delivers the specific electricity demands of the electricity consumers at the right time based on the variations in multiple impacting factors as mentioned above. As such any shifts or variations in peak usage time and/or power and energy demands can be addressed with high accuracy.

Further, the dynamic prediction ofthe future electricity needs as well as electricity production based on the obtained data enables the system 10 to store and deliver electricity based on optimized storage and delivery schemes updated dynamically based on the conditions of the electricity network 1. This will be further elaborated on in the following. ln several aspects and embodiments the control system 10 may further be configured to optimize, based on the predicted probability ofthe future electricity need ofthe at least one electricity-consumer 40a-40c and/or the predicted probability of the future electricity production of the at least one electricity-producer 30a-30c, an electricity storage scheme for the operationally decentralized distributed energy storage system 100 coupled to the electrical grid network 50. ln several embodiments and aspects the control system 10 may further be configured to optimize, based on the predicted probability ofthe future electricity need ofthe at least one electricity-consumer 40a-40c and/or the predicted probability of the future electricity production of the at least one electricity-producer 30a-30c, an electricity delivery scheme for the at least one electricity-consumer 40a-40c. ln various exemplary embodiments and aspects, the processing circuitry 11 of the control system 10 may comprise a data processing unit 11a for receiving and processing the obtained real-time sensor data and/or historic data and information to be used for predicting the probability of the future electricity need of the at least one electricity-consumer and/or a the probability of the future electricity production of the at least one electricity-producer. The data processing unit 11a may employ any of available data processing methods and mathematical models known in the art such as simple logic or neural networks or trained learning algorithms to process the obtained data.

Further, the data processing unit 11a may be configured for optimizing the electricity storage scheme for the distributed energy storage system, and the electricity delivery scheme for the at least one electricity-consumer. ln several embodiments and aspects the data processing unit 11a may comprise a trained machine learning algorithm 11b or a trained artificial intelligence (Al) algorithm 11b such as a supervised and/or an unsupervised machine learning algorithm 11b for performing the prediction and optimization tasks. Thus, the control system 10 may be further configured for providing the sensor data as input to the trained machine- learning algorithm 11b configured to use the obtained sensor data to predict the probability of the future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity producer. Further, the control system 10 may be configured for obtaining an output signal of the machine-learning algorithm 11b comprising the predicted probability of the future electricity need of the at least one electricity-consumer and/or the probability ofthe future electricity production of the at least one electricity-producer. As mentioned above, the control system 10 may be further configured for optimizing, by the trained machine-learning algorithm 11b, the electricity storage scheme for the distributed energy storage system, and the electricity delivery scheme for the at least one electricity-consumer based on the obtained output signal of the machine- learning algorithm. ln several exemplary embodiments and aspects of the present disclosure, the trained machine-learning algorithm 11b may comprise a decentralized federated machine learning algorithm arranged at each one ofthe one or more distributed mixed energy storage unit(s) 100a-100m. The command center 200 may be configured to decide on which machine learning models and algorithms to be used by the distributed energy storage system 100 and the control system 10 in each energy-storage hub 100a-100m. For instance, the command center 200 may transmit a machine learning model to one or some or a subset of the energy- storage hubs 100a-100m, wherein the model may be trained, tested and verified with the real- time and historically obtained data in each of the elected hubs 100a-100m. The federated learning structure of the machine learning algorithms implemented in each energy storage hub 100a-100m ensures that the obtained data remains anonymized and is only processed locally without any influence from the outside of each energy-storage hub, thus conforming with the prevailing user privacy standards. At the same time, the results obtained from testing the proposed model by the command center 200 can be remitted to the command center 200 which in turn may decide to make improvements and modifications to the model and 21 communicate a fixed operational version to some or all ofthe energy storage units 100a- 100m. This process of training, testing and verification of the machine learning algorithm is an iterative and dynamic process leading to continuous improvements ofthe data processing and optimization by the control system 10. Further, considerably faster processing of the obtained data is provided. ln addition to obvious advantages of locally handling the obtained data such as increased security and data anonymity, by having the decentralized federated machine learning algorithms implemented in each of the distributed energy-storage hubs 100a-100m, the requirement of data transfer from the distributed energy units 100a-100m to a central data processing unit is also alleviated. ln several embodiments, the training process of the machine learning algorithm may comprise pre-processing, training, testing, and validating phases. The machine learning algorithm developed by the command center 200 may thus be trained and tested with training and testing datasets offline prior to transmission to the control systems 10a-10m of the distributed energy storage units 100a-100m to be trained or validated further with the obtained sensor data. ln other words the first trained version of the machine learning algorithm may be transmitted to the energy storage units 100a-100m where obtained real-time or historic data i.e. validation dataset obtained from energy consumptions and/or productions is input to the machine learning algorithm. The validation dataset should never be presented to the machine learning algorithm before the first trained version of the machine learning algorithm passes the performance evaluation by the command center 200. The outcome oftraining and validating the trained machine learning algorithm with the validation dataset may be transmitted to the command center 200 as mentioned above. The command center 200 may evaluate the performance ofthe machine learning algorithm and make adjustments and improvements to the model before arriving at a fixed machine leaning algorithm to be implemented in the distributed energy storage system 100. Various parameters ofthe electricity distribution network 1 and the electricity consumers and producers may be measured by the sensor system 6 and be used in training and validation of the machine learning algorithm. The parameters may include any one of sensor measurements of voltage, current, frequency, frequency fluctuations, voltage and/or current fluctuations under a variety of time units such as under duration ofa year, a month, a day, an hour, a minute, a second, a millisecond, etc. Since, the collected data based on the above data collections scheme 22 amounts to enormous data sizes, a pre-processing phase may be applied for data cleanout or data reduction to accurately extract the data which may then be fed to the machine learning algorithm. Further parameters which may be measured and processed may include power and energy limitations of the grid network 50, voltage and/or current and/or frequency of the grid network 50 at the coupling nodes to each ofthe energy storage units 100a-100m, input and output current and/or voltage and/or frequency at each of the energy storage units 100a- 100m, frequency and phase angles ofthe grid network 50 (which may be obtained from the voltage and current measurements), electricity prices in energy bidding marketplaces, probabilities of new electricity prices in the bidding markets which may be based on the previous predictions from the machine learning algorithms, etc. Other variables to consider may also include the wind conditions in different areas which affects the wind power productions, the amount of sunlight in different areas and under certain time periods leading up to variations in the solar power production, other weather conditions such as rain may also be considered. Further, state of charge of each energy-storage hub may be measured and processed, other services such as price support services by frequency and/or power control may be considered, temporary power limitations of the energy storage units may be measured and processed. The collective effect of processing the above obtained data and information may also lead to better decision making processes to identify what types of energy to store in certain energy storage units for which type of electricity consumers as well as providing valuable insights on different electricity delivery technologies.

The control system 10 may be configured to optimize the electricity storage scheme for the distributed energy storage system by optimizing a geographical location ofthe one or more distributed mixed energy storage unit(s) 100a-100m which may be decided based on the predictions of future electricity needs and/or production capacity. Further, the control system 10 may be configured to optimize a time-point and/or time period and/or time interval for storing electricity in the one or more distributed mixed energy storage unit(s) 100a-100m. Thus, based on the future predictions, the control system 10 will receive electricity from the grid network 50 and store in each or a selected number of distributed energy storage units 100a-100m based on the optimized parameters. Thus, electricity may be obtained from the grid network 50 and be stored in the distributed energy units e.g. during off-peak usage periods of the grid network 50, or during any appropriate time window and later on be 23 delivered to the electricity consumers according to specific needs. Further, the control system 10 may be configured to optimize an amount of electrical power and/or electrical energy and/or energy type to be stored in the one or more distributed mixed energy storage unit(s). Even further, the control system 10 may optimize obtaining and storing the over-production of electricity from the one or more renewable electricity production source(s) 60 in the one or more distributed mixed energy storage unit(s), as well as optimize a life-time of each of the one or more distributed mixed energy storage unit(s).

Further, the control system 10 may be configured to optimize the electricity delivery scheme for the at least one electricity-consumer by optimizing a time-point and/or time period and/or time interval for delivery of electricity, stored in the one or more distributed mixed energy storage unit(s), to the at least one electricity-consumer. Similarly, here based on the future predictions of the electricity needs of the at least one electricity consumer 40a-40c, the control system 10 may be configured to deliver the required amount or type of energy by means of the distributed energy storage units 100a-100m.

Moreover, the control system 10 may be configured to optimize an amount of electrical power and/or electrical energy and/or energy type stored in the one or more distributed mixed energy storage unit(s), and to be delivered to the at least one electricity-consumer. Even further, the control system 10 may be configured to optimize delivery of the over-production of electricity from the one or more renewable electricity production source(s) 60 stored in the one or more distributed mixed energy storage unit(s) to the at least one electricity-consumer 40a-40c. ln several embodiments and aspects, the control system 10 may also be configured for delivering, by the distributed energy storage system 100 to the at least one electricity- consumer 40a-40c, a real-time and/or future electricity need of the at least one electricity- consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme.

Accordingly, in some exemplary embodiments the control system 10 in communication with the grid network 50 or the command center 200 may be adapted to select at least one distributed mixed energy storage unit of the one or more distributed mixed energy storage unit(s) 100a-100m for delivering the real-time and/or a future electricity need of the at least 24 one electricity-consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme. The selection criteria may be based on the geographical location of the selected storage unit, the size i.e. delivery capacity, current state of charge, type of stored energy, etc. of the selected energy storage unit, specific needs of the respective electricity consumer e.g. the combination of power and energy needs, etc. Thus, the specific electricity needs of each electricity consumer is fulfilled by matching the most suitable energy storage unit capable of optimized delivery of the electricity to that electricity consumer.

Fig. 3 shows a flow chart of a method 300 according to various embodiments and aspects of the present disclosure for optimized storage and delivery of electricity in an electricity distribution network. According to several exemplary embodiments, the electricity distribution network 1 may comprise an electricity grid network 50 or may be in communication with or coupled to one or more electricity grid networks 50.

All the elements, features, and advantages explained in relation to the other aspects and embodiments also apply analogously to this aspect of the present disclosure.

The method comprises obtaining 301 from a sensor system, sensor data associated with electricity consumption of at least one electricity-consumer 30a-30c and/or sensor data associated with electricity production of at least one electricity-producer 40a-40c coupled to the electricity distribution network 1. The method further comprises predicting 303 a probability of a future electricity need of the at least one electricity-consumer and/or predicting a probability of future electricity production of the at least one electricity-producer based on the obtained sensor data. Furthermore, the method comprises optimizing 305, based on the predicted probability of the future electricity need of the at least one electricity- consumer and/or the predicted probability ofthe future electricity production of the at least one electricity-producer, any one of an electricity storage scheme 302 for an operationally decentralized distributed energy storage system 100 coupled to the electricity distribution network 1, and an electricity delivery scheme 304 for the at least one electricity-consumer. The method further comprises delivering 307, by the distributed energy storage system 100 to the at least one electricity-consumer, a real-time and/or future electricity need of the at least one electricity-consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme. Real-time and/or future electricity needs of the at least one electricity-consumer may be determined and be scheduled for delivery based on the predictions and optimizations performed by the systems and methods according to the present disclosure. ln some embodiments the method 300 may further comprise predicting 303 the probability of the future electricity need of the at least one electricity-consumer and/or predicting the probability ofthe future electricity production of the at least one electricity producer based on any one of an obtained frequency and/or voltage and/or electrical current change in the electricity distribution network, an obtained weather forecast information, an obtained electrical current and/or voltage and/or frequency parameters of the electricity grid network, coupled to the electricity distribution network, and/or of the at least one electricity-consumer and/or electricity-producer, an obtained electricity consumption and/or production rate under certain time intervals and/or at certain time-points, an obtained previous trend of electricity consumption and/or production in the electrical grid network. ln several embodiments, predicting 303 the probability of the future electricity production of the at least one electricity-producer 40a-40c may comprise predicting 303 a probability of any one of a future power production capacity of the at least one electricity-producer at a certain time-point, a future energy production capacity ofthe at least one electricity-producer under a certain period of time and/or under a certain time interval, a future combination of the power and energy production capacity of the at least one electricity-producer, one or more future combination(s) ofthe power and energy production capacity ofthe at least one electricity-producer to be delivered under one or more certain time period(s), one or more future combination(s) ofthe power and energy production capacity ofthe at least one electricity-producer to be delivered under one or more certain set of conditions.

Even further in some embodiments, predicting 303 the probability ofthe future electricity production of the at least one electricity-producer may further comprise predicting a probability of a future over-production of electricity by the at least one electricity producer, wherein the over-production of electricity is originated from one or more renewable electricity production source(s) 60. ln some embodiments, predicting 303 the probability of the future electricity need of the at least one electricity-consumer may further comprise predicting a probability of any one of a 26 future power need ofthe at least one electricity-consumer at a certain time-point, a future energy need ofthe at least one electricity-consumer under a certain period of time and/or under a certain time interval, a future combination of the power and energy need of the at least one electricity-consumer, one or more future combination(s) of the power and energy need ofthe at least one electricity-consumer to be delivered under one or more certain time period(s), one or more future combination(s) of the power and energy need ofthe at least one electricity-consumer to be delivered under one or more certain set of conditions.

According to several embodiments, the distributed energy storage system 100 may be a mixed energy storage system comprising one or more operationally decentralized distributed mixed energy storage unit(s) 100a-100m, each mixed energy storage unit comprising at least one energy storage module IVI1-IVIn of an energy type of a plurality of energy types. ln various embodiments, optimizing 305 the electricity storage scheme 302 for the distributed energy storage system and/or optimizing 305 the electricity delivery scheme 304 for the at least one electricity-consumer may comprise, for the electricity storage scheme, optimizing any one of a geographical location of the one or more distributed mixed energy storage unit(s), a time-point and/or time period and/or time interval for storing electricity in the one or more distributed mixed energy storage unit(s), an amount of electrical power and/or electrical energy and/or energy type to be stored in the one or more distributed mixed energy storage unit(s), obtaining and storing the over-production of electricity from the one or more renewable electricity production source(s) 60 in the one or more distributed mixed energy storage unit(s), and life-time of each of the one or more distributed mixed energy storage unit(s). For the electricity delivery scheme, optimizing 305 may comprise optimizing any one of a time-point and/or time period and/or time interval for delivery of electricity, stored in the one or more distributed mixed energy storage unit(s), to the at least one electricity-consumer, an amount of electrical power and/or electrical energy and/or energy type stored in the one or more distributed mixed energy storage unit(s), to be delivered to the at least one electricity-consumer, delivery ofthe over-production of electricity from the one or more renewable electricity production source(s) 60 stored in the one or more distributed mixed energy storage unit(s). 27 ln several embodiments, the method 300 may further comprise selecting 309 at least one distributed mixed energy storage unit of the one or more distributed mixed energy storage unit(s) for delivering the real-time and/or future electricity need of the at least one electricity- consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme. ln various embodiments, predicting 303 the probability of the future electricity need of the at least one electricity-consumer and/or the probability ofthe future electricity production of the at least one electricity-producer may comprise providing 311 the sensor data as input to a trained machine-learning algorithm 11b configured to use the obtained sensor data to predict the probability ofthe future electricity need of the at least one electricity-consumer and/or the probability ofthe future electricity production of the at least one electricity producer; and obtaining 313 an output signal of the machine-learning algorithm comprising the predicted probability of the future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity-producer. ln several embodiments, the method 300 may further comprise optimizing 305, by the trained machine-learning algorithm 11b, the electricity storage scheme 302 for the distributed energy storage system, and the electricity delivery scheme 304 for the at least one electricity- consumer based on the obtained output signal of the machine-learning algorithm. ln various embodiments, the trained machine-learning algorithm 11b may comprise a decentralized federated machine learning algorithm arranged at each one ofthe one or more distributed mixed energy storage unit(s) 100a-100m.

Executable instructions for performing the above functions and features of the embodiments of the methods may, optionally, be included in a non-transitory computer-readable storage medium or other computer program product configured for execution by one or more processors of the processing circuitry.

I\/|ore specifically, there is provided a computer program carrier carrying one or more computer programs configured to be executed by one or more processors of a processing circuitry, the one or more programs comprising instructions for performing any one of the embodiments of 28 the method 300 according to this disclosure. The computer program carrier may be one of an electronic signal, optical signal, radio signal or a computer-readable storage medium.

Even further, there is provided a computer program product comprising instructions which, when the program is executed by one or more processors of a processing circuitry, causes the processing circuitry to carry out any one of the embodiments of the method 300 according to this disclosure.

Fig. 4 is a schematic illustration of a distributed energy storage system 100 for optimized storage and delivery of electricity in an electricity distribution network 1 according to several aspects and embodiments of the present disclosure. The distributed energy storage system 100 may in some aspects and embodiments be coupled to or be in communication with an electricity grid system 50. The operationally decentralized distributed energy storage system 100 is a mixed energy storage system comprising one or more operationally decentralized distributed mixed energy storage unit(s) 100a-100m, each mixed energy storage unit comprising at least one energy storage module IVI1-IVIn of an energy type of a plurality of energy types. The distributed energy storage system 100 may comprise any combination of different operationally decentralized distributed mixed energy storage unit(s) 100a-100m having varying locations and placements, energy storage capacities, geographical footprints, number of modules IVI1-IVIn of different energy types, etc. The skilled person thus realizes that implementation ofthe distributed energy storage units 100a-100m is a design choice depending on the system requirements and intended applications and may be readily adapted to specific circumstances. Each operationally decentralized distributed energy storage unit 100a-100m comprises a control system 10a-10m or collectively referred to as the control system 10. The control system 10 is configured to operate the distributed energy storage units in conjunction with the command center 200 and perform any of the embodiments of the method 300 according to the present disclosure.

The control system 10 may further comprise one or more processors 11, a memory 8, a sensor and module connection interface 13 for connecting the control system 10 to various sensor devices 6a-6n and/or energy storage modules IVI1-IVIn. The control system 10 may further comprise a communication interface 14 for connecting each energy storage unit 100a-100m to its respective external network 20a-20m and/or to the grid network 50 via dedicated 29 transmission lines 101. The processor(s) 11 may also be referred to as a control circuit 11 or control circuitry 11 or processing circuitry 11. The control circuitry 11 is configured to execute instructions stored in the memory 8 to perform various embodiments ofthe method 300. The memory 8 of the control system 10 can include one or more (non-transitory) computer- readable storage mediums, for storing computer-executable instructions, which, when executed by one or more computer processors 11, for example, can cause the computer processors 11 to perform the techniques described herein. The memory 8 optionally includes high-speed random access memory, such as DRAM, SRAM, DDR RAM, or other random access solid-state memory devices; and optionally includes non-volatile memory, such as one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state storage devices.

The processing circuitry 11 ofthe control system 10 may comprise a data processing unit 11a for receiving and processing the obtained sensor data and/or historic data and information to be used for predicting the probability ofthe future electricity need ofthe at least one electricity-consumer and/or a the probability of the future electricity production of the at least one electricity-producer. Further, the data processing unit 11a may be configured for optimizing the electricity storage scheme for the distributed energy storage system, and the electricity delivery scheme for the at least one electricity-consumer. ln several embodiments and aspects the data processing unit 11a may comprise a trained machine learning algorithm 11b or a trained artificial intelligence (Al) algorithm 11b for performing the prediction and optimization tasks. Thus, the control system 10 may be further configured for providing the sensor data as input to the trained machine-learning algorithm 11b configured to use the obtained sensor data to predict the probability ofthe future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity producer. Further, the control system 10 may be configured for obtaining an output signal ofthe machine-learning algorithm 11b comprising the predicted probability of the future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity-producer. The control system 10 may be further configured for optimizing, by the trained machine-learning algorithm 11b, the electricity storage scheme for the distributed energy storage system, and the electricity delivery scheme for the at least one electricity-consumer based on the obtained output signal of the machine-learning algorithm. ln several exemplary embodiments and aspects of the present disclosure, the trained machine-learning algorithm 11b comprises a decentralized federated machine learning algorithm arranged at each one of the one or more distributed mixed energy storage unit(s) 100a-100m.

Further, the distributed energy storage system 100 may be connected to external network(s) 20 via for instance a wireless link or communication interface 14 via various technologies such as cellular long range or short range such as Wireless Local Area (LAN), WiFi, etc. communication technologies. Each distributed energy storage unit 100a-100m may accordingly be configured to be connected to its own external network 20a-20m.

The present disclosure has been presented above with reference to specific embodiments. However, other embodiments than the above described are possible and within the scope of the disclosure. Different method steps than those described above, performing the method by hardware or software, may be provided within the scope of the disclosure.

For instance, according to an exemplary embodiment a cloud computing system 20 can be configured to perform any one of or any combination ofthe embodiments ofthe method 300 presented herein. The cloud computing system may comprise distributed cloud computing resources that jointly perform the methods presented herein under control of one or more computer program products.

The processor(s) 11 (associated with the control system 10) may be or include any number of hardware components for conducting data or signal processing or for executing computer code stored in memory 8. The system 10 may have an associated memory 8, and the memory 8 may be one or more devices for storing data and/or computer code for completing or facilitating the various methods described in the present description. The memory may include volatile memory or non-volatile memory. The memory 8 may include database components, object code components, script components, or any other type of information structure for supporting the various activities of the present description. According to an exemplary embodiment, any distributed or local memory device may be utilized with the systems and methods of this description. According to an exemplary embodiment the memory 8 is communicably connected to the processor 11 (e.g., via a circuit or any other wired, 31 wireless, or network connection) and includes computer code for executing one or more of processes described herein.

As used herein, the term "if" may be construed to mean "when or "upon" or "in response to determining or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined' or "when it is determined" may be construed to mean "upon determining or "in response to determining" or "upon detecting and identifying occurrence of an event" or "in response to detecting occurrence of an event" depending on the context. The term "obtaining" is herein to be interpreted broadly and encompasses receiving, retrieving, collecting, acquiring, and so forth directly and/or indirectly between two entities configured to be in communication with each other or with other external entities. lt should be noted that the word "comprising" does not exclude the presence of other elements or steps than those listed and the words "a" or "an" preceding an element do not exclude the presence of a plurality of such elements. lt should further be noted that any reference signs do not limit the scope of the claims, that the disclosure may be at least in part |ll implemented by means of both hardware and software, and that severa means" or "units" may be represented by the same item of hardware.

Although the figures may show a specific order of method steps, the order of the steps may differ from what is depicted. ln addition, two or more steps may be performed concurrently or with partial concurrence. Such variation will depend on the software and hardware systems chosen and on designer choice. All such variations are within the scope ofthe disclosure. Likewise, software implementations could be accomplished with standard programming techniques with rule-based logic and other logic to accomplish the various connection steps, processing steps, comparison steps and decision steps. The above mentioned and described embodiments are only given as examples and should not be limiting to the present disclosure. Other solutions, uses, objectives, and functions within the scope of the disclosure as claimed in the below described patent embodiments should be apparent for the person skilled in the art.

Claims

1. A method for optimized delivery of electricity in an electricity distribution network, the method comprising: obtaining from a sensor system, sensor data associated with electricity consumption of at least one electricity-consumer and/or sensor data associated with electricity production of at least one electricity-producer coupled to the electricity distribution network; predicting a probability of a future electricity need of the at least one electricity- consumer and/or predicting a probability of future electricity production of the at least one electricity-producer based on the obtained sensor data; optimizing, based on the predicted probability of the future electricity need of the at least one electricity-consumer and/or the predicted probability of the future electricity production ofthe at least one electricity-producer, any one of: an electricity storage scheme for an operationally decentralized distributed energy storage system coupled to the electricity distribution network, and an electricity delivery scheme for the at least one electricity-consumer; delivering, by the distributed energy storage system to the at least one electricity- consumer, an electricity need of the at least one electricity-consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme.

2. The method according to claim 1, wherein predicting the probability ofthe future electricity production of the at least one electricity-producer comprises: predicting a probability of any one of: a future power production capacity of the at least one electricity-producer at a certain time-point, a future energy production capacity ofthe at least one electricity-producer under a certain period of time and/or under a certain time interval, a future combination of the power 33 and energy production capacity of the at least one electricity-producer, one or more future combination(s) of the power and energy production capacity of the at least one electricity- producer to be delivered under one or more certain time period(s), one or more future combination(s) of the power and energy production capacity of the at least one electricity- producer to be delivered under one or more certain set of conditions.

3. The method according to any one of claims 1 or 2, wherein predicting the probability of the future electricity production of the at least one electricity-producer further comprises: predicting a probability of a future over-production of electricity by the at least one electricity producer, wherein the over-production of electricity is originated from one or more renewable electricity production source(s).

4. The method according to claim 1, wherein predicting the probability ofthe future electricity need of the at least one electricity-consumer further comprises: predicting a probability of any one of: a future power need of the at least one electricity-consumer at a certain time-point, a future energy need of the at least one electricity-consumer under a certain period of time and/or under a certain time interval, a future combination of the power and energy need of the at least one electricity-consumer, one or more future combination(s) of the power and energy need of the at least one electricity-consumer to be delivered under one or more certain time period(s), one or more future combination(s) of the power and energy need ofthe at least one electricity-consumer to be delivered under one or more certain set of conditions.

5. The method according to any one of claims 1 - 4, wherein the method further comprises: predicting the probability of the future electricity need of the at least one electricity- consumer and/or predicting the probability of the future electricity production of the at least one electricity producer based on any one of: an obtained frequency and/or voltage and/or electrical current change in the electricity distribution network, an obtained weather forecast information, an obtained electrical current 34 and/or voltage and/or frequency parameters of an electricity grid network, coupled to the electricity distribution network, and/or of the at least one electricity-consumer and/or electricity-producer, an obtained electricity consumption and/or production rate under certain time intervals and/or at certain time-points, an obtained previous trend of electricity consumption and/or production in the electrical grid network.

6. The method according to any of the preceding claims, wherein the distributed energy storage system is a mixed energy storage system comprising one or more operationally decentralized distributed mixed energy storage unit(s), each mixed energy storage unit comprising at least one energy storage module of an energy type of a plurality of energy types.

7. The method according to any one of claims 1 - 6, wherein optimizing the electricity storage scheme for the distributed energy storage system and/or optimizing the electricity delivery scheme for the at least one electricity-consumer comprises: for the electricity storage scheme, optimizing any one of: a geographical location of the one or more distributed mixed energy storage unit(s), a time-point and/or time period and/or time interval for storing electricity in the one or more distributed mixed energy storage unit(s), an amount of electrical power and/or electrical energy and/or energy type to be stored in the one or more distributed mixed energy storage unit(s), obtaining and storing the over-production of electricity from the one or more renewable electricity production source(s) in the one or more distributed mixed energy storage unit(s), and life-time of each ofthe one or more distributed mixed energy storage unit(s); and for the electricity delivery scheme, optimizing any one of: a time-point and/or time period and/or time interval for delivery of electricity, stored in the one or more distributed mixed energy storage unit(s), to the at least one electricity- consumer, an amount of electrical power and/or electrical energy and/or energy type stored in the one or more distributed mixed energy storage unit(s), to be delivered to the at least one electricity-consumer, delivery of the over-production of electricity from the one or more renewable electricity production source(s) stored in the one or more distributed mixed energy storage unit(s).

8. The method according to any one of claims 6 or 7, wherein the method further comprises: selecting at least one distributed mixed energy storage unit of the one or more distributed mixed energy storage unit(s) for delivering the electricity need of the at least one electricity-consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme.

9. The method according to any one of the preceding claims wherein, predicting the probability ofthe future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity-producer comprises: providing the sensor data as input to a trained machine-learning algorithm configured to use the obtained sensor data to predict the probability of the future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity producer; and obtaining an output signal of the machine-learning algorithm comprising the predicted probability of the future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity-producer.

10. The method according to claim 9, wherein the method further comprises: optimizing, by the trained machine-learning algorithm, the electricity storage scheme for the distributed energy storage system, and the electricity delivery scheme for the at least one electricity-consumer based on the obtained output signal of the machine-learning algorithm.

11. The method according to any one of claims 9 or 10, wherein the trained machine- learning algorithm comprises a decentralized federated machine learning algorithm arranged at each one of the one or more distributed mixed energy storage unit(s).

12. A computer program carrier carrying one or more computer programs configured to be executed by one or more processors of a processing circuitry, the one or more 36 programs comprising instructions for performing the method according to any one of c|aims 1 - 11, and wherein the computer program carrier is one of an electronic signal, optical signal, radio signal or a computer-readable storage medium.

13. A computer program product comprising instructions which, when the program is executed by one or more processors of a processing circuitry, causes the processing circuitry to carry out the method according to any one of c|aims 1 -

14. A system for optimized delivery of electricity in an electricity distribution network, the system comprising processing circuity configured to: obtain from a sensor system, sensor data associated with electricity consumption of at least one electricity-consumer and/or sensor data associated with electricity production of at least one electricity-producer coupled to the electricity distribution network; predict a probability of a future electricity need of the at least one electricity-consumer and/or predicting a probability of future electricity production of the at least one electricity- producer based on the obtained sensor data; optimize, based on the predicted probability of the future electricity need of the at least one electricity-consumer and/or the predicted probability of the future electricity production of the at least one electricity-producer, any one of: an electricity storage scheme for an operationally decentralized distributed energy storage system coupled to the electricity distribution network, and an electricity delivery scheme for the at least one electricity-consumer; deliver, by the distributed energy storage system to the at least one electricity- consumer, an electricity need of the at least one electricity-consumer based on the optimized electricity storage scheme and/or the optimized electricity delivery scheme.

15. The system according to claim 14, wherein the processing circuitry is configured to predict the probability of the future electricity production of the at least one electricity- producer by predicting a probability of any one of: a future power production capacity of the at least one electricity-producer at a certain time-point, a future energy production capacity of the at least one electricity-producer under a certain period of time and/or under a certain time interval, a future combination of the power 37 and energy production capacity of the at least one electricity-producer, one or more future combination(s) of the power and energy production capacity of the at least one electricity- producer to be delivered under one or more certain time period(s), one or more future combination(s) of the power and energy production capacity of the at least one electricity- producer to be delivered under one or more certain set of conditions.

16. The system according to any one of claims 14 or 15, wherein the processing circuitry is further configured to predict the probability of the future electricity production of the at least one electricity-producer by predicting a probability of a future over-production of electricity by the at least one electricity producer, wherein the over-production of electricity is originated from one or more renewable electricity production source(s).

17. The system according to claim 14, wherein the processing circuitry is configured to predict the probability of the future electricity need of the at least one electricity-consumer by predicting a probability of any one of: a future power need of the at least one electricity-consumer at a certain time-point, a future energy need of the at least one electricity-consumer under a certain period of time and/or under a certain time interval, a future combination ofthe power and energy need ofthe at least one electricity-consumer, one or more future combination(s) of the power and energy need of the at least one electricity-consumer to be delivered under one or more certain time period(s), one or more future combination(s) of the power and energy need ofthe at least one electricity-consumer to be delivered under one or more certain set of conditions.

18. The system according to any one of claims 14 - 17, wherein the processing circuitry is further configured to: predict the probability of the future electricity need of the at least one electricity- consumer and/or predict the probability of the future electricity production ofthe at least one electricity producer based on any one of: an obtained frequency and/or voltage and/or electrical current change in the electricity distribution network, an obtained weather forecast information, an obtained electrical current and/or voltage and/or frequency parameters of an electricity grid network, coupled to the electricity distribution network, and/or of the at least one electricity- 38 consumer and/or electricity-producer, an obtained electricity consumption and/or production rate under certain time intervals and/or at certain time-points, an obtained previous trend of electricity consumption and/or production in the electrical grid network.

19. The system according to any one of c|aims 14 - 18, wherein the distributed energy storage system is a mixed energy storage system comprising one or more distributed mixed energy storage unit(s), each mixed energy storage unit comprising at least one energy storage module of an energy type of a plurality of energy types.

20. The system according to any one of c|aims 14 - 19, wherein the processing circuitry is further configured to: for the energy storage scheme, optimize any one of: a geographical location of the one or more distributed mixed energy storage unit(s), a time-point and/or time period and/or time interval for storing electricity in the one or more distributed mixed energy storage unit(s), an amount of electrical power and/or electrical energy and/or energy type to be stored in the one or more distributed mixed energy storage unit(s), obtaining and storing the over-production of electricity from the one or more renewable electricity production source(s) in the one or more distributed mixed energy storage unit(s), and life-time of each ofthe one or more distributed mixed energy storage unit(s); and for the electricity delivery scheme, optimize any one of: a time-point and/or time period and/or time interval for delivery of electricity, stored in the one or more distributed mixed energy storage unit(s), to the at least one electricity- consumer, an amount of electrical power and/or electrical energy and/or energy type stored in the one or more distributed mixed energy storage unit(s), to be delivered to the at least one electricity-consumer, delivery of the over-production of electricity from the one or more renewable electricity production source(s) stored in the one or more distributed mixed energy storage unit(s). 39

21. The system according to any one of claims 14- 20, wherein the processing circuitry is further configured to: provide the sensor data as input to a trained machine-learning algorithm configured to use the obtained sensor data to predict the probability of the future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity producer; and obtain an output signal of the machine-learning algorithm comprising the predicted probability of the future electricity need of the at least one electricity-consumer and/or the probability of the future electricity production of the at least one electricity-producer.

22. The system according to claim 21, wherein the processing circuitry is further configured to: optimize, by the trained machine-learning algorithm, the energy storage scheme for the distributed energy storage system, and the electricity delivery scheme for the at least one electricity-consumer based on the obtained output signal of the machine-learning algorithm.

23. The system according to any one of claims 21 or 22, wherein the trained machine-learning algorithm comprises a decentralized federated machine learning algorithm arranged at each one ofthe one or more distributed mixed energy storage unit(s).

24. A distributed energy storage system comprising: one or more distributed mixed energy storage unit(s) configured to store and/or deliver electricity; and a system according to any one claims 14 - 24 configured to control storage of electricity in the one or more distributed mixed energy storage unit(s) and/or delivery of electricity to at least one electricity-consumer coupled to an electricity distribution network in communication with the distributed energy storage system.