Optimization of an electrical energy production schedule by an electrical production park

Abstract

The invention relates to a technique for optimizing an electrical energy production schedule by an electrical production fleet comprising a plurality of production units. A multi-agent system (23), generated from a formal representation (10) of said production fleet, constructed from an ontology (11) and a knowledge graph (12), simulates, from a received production setpoint (16), an electrical power production by said production units and generates, for a reference period, an optimized electrical energy production schedule, comprising a production setpoint (18) adjusted as a function of the simulated electrical power production for said production units and taking into account operating states and values ​​representative of the operating parameters specific to each and updated (17) in said formal representation. Abstract figure: Figure 1

Description

Title of the invention: Optimization of an electrical energy production schedule by an electrical production park Technical field

[0001] The present disclosure relates to the field of management and optimization of energy systems, and more particularly to the optimization of the production of electrical energy by a production park comprising several power plants, such as hydraulic power plants, thermal power plants or even nuclear power plants. Prior art

[0002] In recent years, the energy sector has undergone a significant transformation, characterized by the decentralization of production and a substantial migration of electricity production methods towards renewable energy sources, involving a plurality of actors.

[0003] In addition, power plants are increasingly vulnerable to climatic hazards, which change frequently. For example, when it is too hot, some nuclear power plants are forced to suspend their production, which may require the network manager to reschedule the production demand in other power plants in the same valley to be able to meet the needs (e.g. an increase in the production and storage capacity of water in hydraulic power plants located upstream or downstream of the nuclear power plant).

[0004] This shift towards a complex and decentralized energy system poses increasing challenges in terms of managing the balance between supply and demand on electricity networks, as well as in the design of management and optimization algorithms adapted to companies in the energy sector.

[0005] The current model for forecasting and programming electricity production is based on a mathematical approach which assumes homogeneity of the different production plants. However, it no longer adequately responds to the current reality of the electricity sector, as described above. Indeed, this global mathematical model is based on the existence of several production models, each associated with a type of production unit, for example a model for nuclear power plants, a model for thermal power plants and a model for hydraulic power plants. However, these models do not take into account the local constraints affecting each of the plants (for example, a meteorological constraint or a constraint structural technique of the power plant), and also do not take into account regional constraints, linked for example to interactions between power plants resulting from their geographical location.

[0006] To resolve this drawback, the Applicant initially attempted to adjust the existing algorithms for creating electricity production call programs for power plants, by integrating, into the mathematical equations underlying their operation, fictitious values ​​intended to represent the specific characteristics of each power plant. It is recalled that a call program contains the active power chronicle of an electrical energy production source for a day D+1, and therefore contains the production time slots and the desired power levels during each of these slots for a production source, for this day D+1. Nevertheless, despite these attempts at numerical adjustment, the approach remains global and does not manage to exhaustively address the local and heterogeneous constraints specific to each power plant.This often results in a mismatch between call schedules and actual production capacity in a park, requiring frequent adjustments throughout the day.

[0007] Furthermore, to date, these call program creation algorithms are designed for a given type of power plant. In an electrical production park comprising power plants of different types, the coordination between these various productions therefore requires, for the park manager, the consultation of several distinct call program creation systems.

[0008] There is therefore a need for a technique for optimizing the programming of electrical energy production within a multi-sector production park (hydraulic, thermal, nuclear, etc.), which is integrated within a single system, and makes it possible to take into account the production constraints specific to each power station in the park.

[0009] There is also a need for such a technique that is scalable, and can adapt dynamically to changes in the behavior of the production fleet in the event of evolution. Summary

[0010] The present disclosure improves the situation.

[0011] A method is proposed for optimizing a schedule for the production of electrical energy by an electrical production park comprising a plurality of production units, comprising: a. receipt of an electrical energy production program, including an electrical power production instruction for the production units for a reference period; b. a simulation, based on the production instruction, of a production of electrical power by the production units, implemented by a multi-agent system modeling the fleet, i. the multi-agent system being generated from a formal representation of the production park, constructed from an ontology and a knowledge graph comprising a set of nodes each representing an element of one of the production units, and a set of edges each representing a functional relationship between two nodes which they connect, ii. the formal representation being updated: 1. according to a determined time step, from representative values ​​of operating parameters of the nodes, received from sensors placed in the park; 2. on the fly, in the event of a change affecting at least one operating state of one of the nodes; c. a generation, for the reference period, of an optimized electrical energy production program, including a production setpoint adjusted according to the simulated electrical power production for the production units and taking into account the operating states and the representative values ​​of the operating parameters updated in the formal representation.

[0012] According to another aspect, there is provided a system for optimizing a programming of production of electrical energy by an electrical production park comprising a plurality of production units, comprising: a. a communication module configured to: i. receive an electrical energy production program, including an electrical power production instruction for the production units for a reference period; ii. send, to the production units, an adjusted production instruction of an electrical energy production program optimized for the reference period; b. a semantic database configured to store a formal representation of the fleet, constructed from an ontology and a knowledge graph comprising a set of nodes each representing an element of one of the production units, and a set of edges each representing a functional relationship between two nodes that they connect; c. a set of sensors configured to provide, according to a determined time step, values ​​representative of operating parameters of the nodes, intended to feed the formal representation; d. a human-machine interface configured to allow the formal representation to be updated in the event of a change affecting at least one operating state of one of the nodes; e. a multi-agent system modeling the fleet, generated from the formal representation, and configured to simulate, from the production setpoint, a production of electrical power by the production units, the multi-agent system comprising a central programming entity configured to generate, for the reference period, the optimized electrical energy production program, comprising the production setpoint adjusted according to the simulated electrical power production for the production units and taking into account the operating states and the representative values ​​of the operating parameters updated in the formal representation.

[0013] According to another aspect, there is provided a computer program comprising instructions for implementing all or part of a method as defined herein when this program is executed by a processor. According to another aspect, there is provided a non-transitory, computer-readable recording medium on which such a program is recorded.

[0014] The features set out in the following paragraphs may, optionally, be implemented, independently of one another or in combination with one another:

[0015] Such an optimization method also comprises sending, to said production units, the adjusted production instruction of the optimized electrical energy production program for the reference period.

[0016] Such an optimization method also comprises a restitution on a human-machine interface of the simulated electrical power production and / or of the generated optimized electrical energy production program.

[0017] The park includes at least two production units belonging to the group comprising: - hydraulic power stations; - thermal power plants; - nuclear power plants; - photovoltaic energy sources; - wind energy sources; - hydroelectric energy sources; - hydraulic pumping stations; - batteries.

[0018] The nodes of the knowledge graph represent elements belonging to the group including: - water tanks; - pumping stations; - production facilities; - production generators (i.e., turbines or alternators); - production auxiliaries (i.e., internal production sources providing initial power at the start of the production process).

[0019] The operating parameters belong to the group comprising: - a volume of stored water; - a range of water flow required at the inlet; - a water flow at the outlet; - electrical power produced; - an inlet water temperature range; - a requested electrical power; - a maximum available power range; - a minimum duration of high level; - a minimum duration of low level; - a type of operating point; - a system status (i.e. a positioning of the power plant in the various adjustment mechanisms for the electricity transmission network manager, such as frequency, power or reserve adjustment); - a type of fuel (for example, fuel oil, nuclear, combined cycle gas (CCG), coal, dual-fuel gas, etc.); - a requested gas power.

[0020] The operating states belong to the group comprising: - an active operating state; - a breakdown condition; - a state of stopping; - a state of electrical consumption.

[0021] The electrical power production instruction takes into account a forecast of electrical consumption. Brief description of the drawings

[0022] Other characteristics, details and advantages will appear on reading the detailed description below, and on analyzing the attached drawings, in which: Fig.l

[0023] [Fig.l] presents a block diagram of a system for optimizing the programming of electrical production of a production park according to a method of rea- lization. Fig. 2

[0024] [Fig.2] shows in synoptic form the steps of construction of a formal representation of the production park and generation of a multi-agent simulation system included in the optimization system of [Fig.l] according to one embodiment. Fig. 3

[0025] [Fig.3] details the steps of automatic generation of an SMA code of [Fig.2] from three programming objects according to one embodiment. Fig. 4

[0026] [Fig.4] presents an example of graphic reproduction of an electrical production park of a hydraulic valley on the interface of the system of [Fig.l] according to one embodiment. Fig. 5

[0027] [Fig.5] illustrates the formal representation of the production park of [Fig.4] and the mapping of different classes of the ontology into Java classes according to one embodiment. Fig. 6

[0028] [Fig.6] shows an example of behavior of an agent of a multi-agent simulation system according to one embodiment. Fig. 7

[0029] [Fig.7] illustrates interactions between agents of a multi-agent simulation system of the park of [Fig.4] according to one embodiment. Description of the embodiments

[0030] The general principle of the invention is based on the design of a system for optimizing production scheduling for an electrical production park, based on the combined use of a multi-agent system and knowledge graphs representative of the operation of the power plants in the park, and on the use of such a system to optimize the electricity production scheduling of the park. Such a system advantageously makes it possible to simulate the operation of the electrical production park, taking into account in real time the production constraints specific to each power plant, whatever its type (hydraulic, nuclear, thermal, photovoltaic, etc.), and thus to optimize the electricity production programs, in an integrated and multi-sector approach.

[0031] We consider below an electrical production park, comprising a set of power plants of different types or of the same type. We recall that a power plant is an industrial site intended for the production of electricity, and which supplies electricity, by means of the electricity network, consumers, individuals or industrial, far from the power plant. Electricity production is ensured by the conversion into electrical energy of a primary energy which can be mechanical (wind force, force of river water, tides, etc.), chemical (combustion of fossil fuels or biomass), nuclear or even solar. Thus, the production park can include, for example, one or more hydraulic power plants, one or more thermal power plants, or one or more nuclear power plants or photovoltaic production sources. Throughout this document, such electricity production sites will be referred to interchangeably by the terms power plant, source, or production unit.

[0032] First of all, in relation to [Fig.l], the general block diagram of such a system according to one embodiment is described. Such a system comprises a database, in which a formal representation denoted KR and referenced 10 of the considered electricity production park is kept up to date. As will be seen in more detail later in relation to Figures 2 and 3, this formal representation KR 10 is constructed from an ontology referenced 11 and a knowledge graph referenced 12. It is updated regularly: - on the one hand, from operating parameter values ​​which are provided by a set of sensors 15 (electricity meters, flow meters, thermometers, anemometers, etc.) placed in the production park; - on the other hand, from updates referenced 17 relating to the operating states of the elements contributing to the production of electricity within the park (failure state, shutdown state, active state, etc.); these updates can be carried out by the professionals managing the production park, through an HMI referenced 24.

[0033] Such a system also comprises a multi-agent simulator SMA referenced 23, which is based on the formal representation KR 10, and which makes it possible to simulate the production of electricity within the park, from different input scenarios. One of these scenarios may be an electrical production setpoint referenced 16, imposed on the different production units of the park, for a reference period (for example, the next 24 hours), and received by a reception module Rx referenced 13. From this setpoint 16, the multi-agent simulation system SMA 23 simulates the production of electricity within the park, taking into account all the values ​​of the operating parameters and the operating states stored in the semantic database containing the formal representation KR 10.It thus acts as a digital twin of the production park, which makes it possible to take into account, in real time or almost, all the local and regional operating constraints likely to affect the production units.

[0034] Depending on the result of this simulation, the multi-agent system SMA 23 can adjust the electricity production program according to these different constraints so that it more faithfully reflects the actual production capacity of the different production units of the park. It thus generates an optimized production setpoint 18, which can be viewed via the HMI 24, and also transmitted by a transmission module Tx referenced 14 to the different production units. The production units then know the levels of electrical power to be produced, according to a determined time step of 5, 10 or 30 minutes for example, during the next reference period, e.g. the next 24 hours.

[0035] We now present in more detail, in relation to figures 2 and 3, the preliminary stages E1 and E2 of construction of a multi-agent system, SMA, from knowledge representations, KR, associated with the electricity production park.

[0036] As illustrated in [Fig.2], the business knowledge specific to each plant, as well as the values ​​associated with the elements which contribute to the operation of these plants can be systematically expressed through the use of a knowledge representation 10, combining an ontology 11 and a knowledge graph 12 (designated here by the acronym KR for the English “Knowledge Representation”, in French “representation of knowledge”).

[0037] The ontology 11 acts as a data schema containing concepts and semantic relationships to model a set of knowledge in a specific domain, facilitating their understanding by machines. In other words, an ontology defines concepts (principles, ideas, object category, potentially abstract notions) and relationships. It generally includes a hierarchical organization of the relevant concepts and the relationships that exist between these concepts, as well as rules and axioms that constrain them. It offers a representation of general properties of what exists in a formalism supporting rational processing. It is the result of an exhaustive and rigorous formulation of the conceptualization of a domain, in this case, that of an electrical production park.

[0038] The knowledge graph 12, for its part, represents a semantic network of the knowledge domain stored in a database in the form of a graph, where the nodes represent the data and the edges describe the relationships between these data. In the context of this document, the nodes depict the different elements involved in the production of electricity in a power plant (identified by a unique code). For example, a hydroelectric power plant is associated with several elements participating in its production of electricity, such as a water reservoir, a pumping station and a production facility. The links between these nodes symbolize the relationships between these elements and between the various entities within a production park at a specific scale.

[0039] A first step referenced El therefore consists of collecting and formalizing all the knowledge of the professionals in the management and operation of the production fleet, via a uniform method of formal representation KR. This step El therefore allows a formal representation of the production fleet, on which the professionals can act at any time to adapt it to an evolution of the production fleet (modification of a production installation, addition of a new plant, shutdown of equipment due to a breakdown or for regulatory reasons, etc. - updates referenced 17 in [Fig.l]). They can interact with the ontology experts or by directly manipulating the knowledge graph, without needing to manipulate the code of the multi-agent system which will be described below. In addition, the latter automatically adapts to changes in knowledge thanks to the queries made through the knowledge graph.

[0040] The formal representation KR 10, obtained at the end of step El, can take the form of symbols that the system can store and manipulate (for example, logical languages ​​and operations, graph structures and operations). This formal representation KR 10 is both understandable by humans and manipulable by systems, by applying manipulation rules defined on the symbols of these representations and the interpretation of which simulates, for example, reasoning.

[0041] The formal representation KR 10 is then used as input to the step referenced E2 of automatic generation of multi-agent systems, MAS. A Multi-Agent System, as described for example by C. Donzelli et al. in “Onto2MAS: An ontology-based framework for automatic multi-agent System generation”, 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), IEEE, 2016, pp. 381-388, can be defined as a complex system integrating a collection of autonomous agents with their own objectives and actions, capable of interacting, collaborating and exchanging knowledge through means of communication. Thus, by using a multi-agent system, one can numerically model the individual characteristics of each element of the electricity production system and observe how these elements interact to influence the overall operation of the production fleet.

[0042] The formal representation KR 10 feeds a tool referenced 20 for generating Java code. This tool makes it possible, on the one hand, to generate, from the ontology 11, a set of Java classes 21 corresponding to the different agents and objects of the SMA system to be created, and on the other hand, to assign behaviors and actions, referenced 22, to the different agents. This tool 20 integrates a conversion model between the ontology and the Java code, and therefore makes it possible to generate the source code in Java associated with all the agents with their behaviors, to form a multi-agent simulation platform, referenced 23. This platform 23 allows the user to visualize, thanks to a 24-referenced HMI, the simulation results according to the input scenarios (for example, different production instructions, or different variants of the call program).

[0043] Such a simulation platform 23 can thus be adapted to various types of power generation plants. By improving the precision of the generation of the powers to be called, it not only makes it possible to better reflect the actual operational capacity of the plants, but also to verify the feasibility of the call programs for each plant by taking into account their local and global constraints. It also makes it possible to anticipate and examine potential disruption scenarios, in particular failures of production units or events linked to natural disasters. Such an SMA system, based on a KR knowledge representation, makes it possible to better guarantee the stability, reliability, and efficiency of the electrical network, by avoiding the time losses associated with power adjustments and the loss of money.

[0044] Various attempts have been made in the prior art to combine multi-agent systems (MAS) and ontologies. However, none of these attempts relied, to the Applicant's knowledge, on the use of a knowledge graph that could be updated in real time. The MAS system construction scheme illustrated by [Fig. 2] relies on the joint use of ontologies and knowledge graphs, together called KR 10, as input or resource elements of the MAS, rather than as final results. Thus, the use of KRs makes it possible to define the internal functioning of the system's agents, which differs from certain prior art approaches that focus more on the general structure of an MAS.

[0045] The automatic generation of an SMA code illustrated by [Fig.2] can be detailed in two stages by passing through three programming objects called “Java class”, as illustrated by [Fig.3]: - a launcher of the algorithm, called Main, referenced 25; - an agent construction object, called ConstructorAgent, referenced 26; - a class creation object, called ClassBuilder, referenced 27.

[0046] The creation of classes from ontologies is under the direction of the so-called "ConstructorAgent" programming object referenced 26. This step combines the loading of ontologies into memory, referenced 261, and the generation of functional classes, referenced 262, through the so-called "ClassBuilder" utility class, referenced 27. The ontology files, extracted from the KR 10 resource repository, undergo a transformation into Java code. Notably, the main ontology is separated into a distinct model, while the ontologies to which it refers are encapsulated in a second model, thus preparing the ground for an informed selection of the relevant classes in the construction of the final SMA.

[0047] The conversion rule is based on the use of a “ConstructorAgent” 26 which relies on a “ClassBuilder” 27. This programming object plays an essential role in the sequential and methodical translation of ontological concepts into executable Java code.

[0048] Hierarchical links between classes are established by exploiting the "SubClass Of" properties, while respecting Java's inheritance constraints.

[0049] Ontological properties of data types (owkDatatypeProperty) are converted to variables according to the conversion rules from XSD to Java, while object properties (owkObjectProperty) are converted to variables using the class defined by the "range" property (rdfs:range) as the type. Cardinality constraints, in particular the "minimum 1" constraint, guide the algorithm by signaling the representation of properties as lists (ArrayList).

[0050] The ontology conversion function is invoked recursively for each object property when the variable type class is defined in external ontologies.

[0051] Finally, the algorithm analyzes all the classes and then uses an Apache FreeMarker® type engine (a template engine that automatically generates text files from an associative array data model) to efficiently translate the data into Java code, based on specific templates defined by the configuration file. The behaviors, initially coded manually, are integrated into the generated code via additional templates. After writing the source files, simultaneous compilation prevents potential problems with circular dependencies.The Java Compiler receives a "path" module with essential dependencies, allowing the SMA agents to take shape and be passed to an SMA modeling platform such as JADE (Java Agent DEvelopment Framework - open-source, Java-based multi-agent systems development framework), while Java's Reflection API (the process of analyzing and modifying all the characteristics of a class) instantiates objects with the compiled classes and enumerations.

[0052] Remember that an enumeration, or "enum", is a special data type, in which a variable can only take a limited number of values. An enumeration is in fact a class. The values ​​of an enumeration are the only possible instances of this class.

[0053] The rhythm of the algorithm is maintained by the programming object “ConstructorAgent” referenced 26, which oversees the final phase 263 of agent instantiation. This step relies on specific SparQL queries, offering the developer the flexibility to integrate constraints adapted to their context. For example, as we will see in more detail later with a specific example of implementation in the context of a valley’s production park, res restrictions are applied to select only the elements and entities of the production park belonging to this single valley.

[0054] Initially, a query is launched to obtain the complete list of classes present in the knowledge graph. Then, for each identified class, a new query is formulated to retrieve all related properties, including their cardinality where applicable. When the properties have a cardinality, a specialized function is called to significantly reduce the number of queries, thus ensuring optimal performance. Each property is then stored in a Java variable of type Map, where the name of the variable serves as the key and its type as the value. If the property corresponds to a class, a third SparQL query is deployed to obtain all the elements necessary for instantiating the agents. The instantiation phase 263 is completed by launching an agent of the appropriate class and passing it the Map of variables as an argument.The latter is used at agent startup to initialize its variables using the Reflection API. This pragmatic approach ensures efficient agent initialization, while taking into account the context-specific dependencies of the SMA.

[0055] A particular example of application of such a multi-agent system in the context of a valley producing electrical energy of hydraulic origin is now described in relation to Figures 4 to 7. The system for optimizing the programming of electrical production has the primary objectives of taking into account the local constraints of each power station in the valley 40 in order to produce the electrical power that best corresponds to the daily demand for electrical consumption in this valley.

[0056] A valley, in this context, represents all the power plants located on the same watercourse, with their respective upstream and downstream positions. [Fig.4] illustrates as an example the valley 40 of the Ain, which includes seven production plants, referenced 411 to 417, symbolized by two concentric circles.

[0057] A modeled power plant corresponds to a physical production site. It can include various types of elements participating in its electrical production. In the example of [Fig.4], three elements are modeled: (a) a water reservoir (symbolized by a triangle more or less grayed out depending on the volume of water contained in the reservoir, referenced 421 to 426)), (b) a pumping station (symbolized by a disc, referenced 431 and 432) and (c) a production installation (i.e. a hydraulic plant, symbolized by two concentric circles, references 411 to 417)). Each element is associated with a unique identifier. For example, in [Fig.4], the Vouglans hydraulic power station is modeled by three agents: VOUGLR designating a water reservoir 421, VOUGLP designating a pumping station 431 and VOUGLH designating the electricity production plant 411. Thus, an agent can be defined as the modeling of a equipment of the electricity production park, which is connected to other equipment of the park by a physical, functional and / or causal link. We understand in fact, by way of example, that the level of electrical power likely to be delivered at the output of the VOUGLH plant is directly dependent on the level of water contained in the VOUGLR reservoir. In [Fig.4], the direction of circulation of the water in the valley is symbolized by arrows.

[0058] The business knowledge on the operation of a hydraulic power plant has been conceptually modeled with an ontology, illustrated in [Fig.5], and the individuals of each concept are stored in the form of the knowledge graph.

[0059] These knowledge representation elements are used as resource generators for the multi-agent simulation system of [Fig.l]. For example, a “Production facility” class, referenced 51, is defined as a subcategory of the “Physical object” class, referenced 50, which is a general category encompassing the common characteristics between production units and water storage systems (for example, lakes, reservoirs), called “Reservoir” agents, referenced 52.

[0060] The local constraints are specifically modeled at the level of the Production Installation 51, which may be a hydroelectric production installation 511, or a nuclear production installation 512 for example. With regard to the “Reservoir” agents 52, the local constraints are mainly linked to their water volume. They are broken down for example according to the following operating parameters: - minimum water volume 520; - maximum water volume 521; - water volume 522; - rating 523.

[0061] The values ​​of these different parameters are provided by the sensors present in or near the reservoir, and stored in the database of the system of [Fig.l]: they are then used, in operation, to simulate the behavior of the “reservoir” agent 52.

[0062] The “Physical Object” 50 is for example associated with the operating parameters relating to an incoming water flow rate 501 and an outgoing water flow rate 502, as well as to a possible supply 503 from a pumping station or naturally via a river or its nearby tributaries. The values ​​of these parameters can be updated in the database of the formal representation KR 10 according to a determined time step, for example every five or ten minutes, from flow meter type sensors arranged upstream and downstream of the physical object 50.

[0063] In the example of the production park in [Fig.4], whose model focuses on hydraulic power stations, the following constraints are taken into account at the local level: - factory activation times, - the production power adjustment times (time to move to the upper operating point 514 and time to move to the lower operating point 515), - production capacities (“is available” 513), - the necessary water flow rates 517, - the initial water volumes 522, - the requested energy production 516.

[0064] At the regional level, more specifically in the context of Valley 40 in [Fig. 4], the constraints primarily revolve around the relative geographic position of each power plant relative to others in the valley, whether upstream or downstream. These spatial relationships exert a direct influence on entry and exit restrictions, ultimately determining the operational capacity and sequence of collaboration or independence of each power plant.

[0065] On a global scale, the multi-agent system contains an agent which plays a specific role, called “Central Programming Entity”, referenced 53. This entity plays a crucial role at two levels: as input and output of the simulation.

[0066] In one embodiment, this central programming entity 53 defines the production time slots and the desired power levels for each of these time slots for each power plant on day D+1. This constitutes an essential constraint in the entire model, managing the collective demand shared by all the power plants in a specific valley. This call program can constitute the input instruction of the optimization system of [Fig.1]. It defines, according to a determined time step of five minutes for example, the level of electrical power expected at the output of each production installation. It can in particular be established from a forecast of the electrical consumption in the valley of [Fig.4] during day D+1.

[0067] The Central Programming Entity 53 is also the agent which generates, at the final output of the optimization system of [Fig.l], the optimized electricity production program, comprising a production setpoint for each production installation associated with it, adjusted during the simulation to maximize the satisfaction of the specified overall demand. This adjustment is carried out by taking into account the local constraints of each power plant. Thus, the initial call program of each central programming entity 53 is modified according to the power and the water flow rate at the outlet of each associated power plant. An optimized call program is thus generated, adapted to the actual capacity of the electricity production plants.

[0068] This call program can be transmitted to the different production units, via a wired or wireless communication network, for example a fiber optic data transmission network, or a 4G, 5G or higher type radio communication network.

[0069] It will be noted that one or more central programming entities 53 can be provided per valley, each central programming entity determining the production instructions for one or more turbines associated with it.

[0070] [Fig. 6] illustrates a modeling, within the SMA system 23, of the behavior of a “Production Plant” agent 51. Everything starts with the “wake-up” state or reactivation 60 of the “Production Plant” agent 51, where the agent starts the production of electricity 61, communicates the information on its flow rate to the “physical objects” 50 upstream and downstream, then waits during the operating point rise period. During the “production phase” 61, the agent regularly records the electricity production and the flow rate used. When there is a change 62 of operating point on the call program, the agent transmits the yield information to the neighboring agents, then waits during the transition period after the change of operating point. In the event of a shutdown 63 of the plant, the agent informs the “physical objects” 50 of the new flow rates, then waits for the minimum shutdown duration.Finally, the agent remains inactive for certain periods 64, periodically reactivating itself to check whether it should resume activity.

[0071] The “reservoir” agents 52 have a simpler behavior. They update the water volume at each time step. They adjust the inlet and outlet flow rates based on the messages received and use this data to update the reservoir water volume. In addition, they make random adjustments to the water inputs to reflect natural fluctuations. Finally, they notify upstream agents if the water level exceeds a high threshold and downstream agents if it falls below a low threshold.

[0072] The "Central Scheduling Entity" agent 53 sends the call schedules to the plants that need them, generally once a day, to facilitate the coordination and planning of energy production. During the simulation, the call schedule is adjusted according to the actual power levels that each plant can achieve. The set of power levels for each hour then constitutes the new complete call schedule for the day in question.

[0073] It is important to note that the output of each agent is used to update the parameters of each node in the knowledge graph. In addition, for each calling program, the system saves a log file that contains all the information about the power schedule that can be called. Finally, the evolution of each agent during the simulation is also displayed visually via the platform's user interface 24. The plants present their status and the power produced, while the reservoir displays the volume of water at the currently simulated time step. In one embodiment, a time step is equivalent to 30 minutes.

[0074] The dynamic interaction and coordination between all these agents are illustrated by [Fig.7]. A volume of water that is too low or too high in a reservoir 52 induces a necessary adjustment of the level of electrical power produced by a plant 51, and therefore an adjustment of the flow rate of water leaving the reservoir 52. The central programming entity 53 controls and orchestrates all of these adjustments. It is thus possible to recreate the complex interactions within the energy system, which offers a realistic and detailed simulation of its operation.

[0075] In addition to the updating by the agents of the SMA 23 system during the simulation, the knowledge graph can also play a central role allowing business operators to report a change in an element of a power plant during the simulation by querying the graph. This possibility is facilitated by the standardization of the communication of the business concept with the system via the knowledge graph and its associated ontology. It is thus possible for the managers of the production fleet to report the loss of equipment due to breakdown or for regulatory reasons (for example the shutdown of a nuclear power plant due to a water temperature that is too high, or a water level that is too low upstream of the power plant).

[0076] The multi-agent system thus designed constitutes a digital twin of the electricity production fleet, which takes into account the specific operation of each multi-sector production installation. It is also perfectly synchronized with the knowledge graph, which allows it to adapt immediately to any changes in the production fleet reflected in the knowledge graph. This convergence of the different sources of electricity production within a unified system constitutes a remarkable innovation for the energy sector.

[0077] Although it has been described in the context of a particular example of a production park limited to a hydraulic valley, it is easily understood that it can be generalized to any type of energy system, and in particular to the European electricity system, in the sense of the market. This system is by nature scalable, in particular due to the evolution of regulations. The proposed technique makes it possible to express this regulatory evolution through a knowledge graph, the data and their values ​​of which are directly provided by all the sensors present within the energy system, and in particular the different electric meters placed on the different production plants, the water flow sensors at the inlet and outlet of the reservoirs, pumping stations and hydraulic plants, the temperature sensors, the anemometers, etc. List of reference signs

[0078] - 10: formal representation KR - 11: ontology; - 12: knowledge graph; - 13: reception module; - 14: transmission module; - 15: sensor; - 16: production instructions; - 17: updates; - 18: optimized production instructions; - 20: Java code generation tool; - 21: classes; - 22: set of behaviors and actions; - 23: multi-agent simulation system; - 24: man-machine interface; - El: stage of generation of a formal representation; - E2: step of generating a multi-agent system; - 25: “Main” programming object; - 26: “ConstructorAgent” programmatic object; - 27: ClassBuilder programmatic object; - 261: loading ontologies; - 262: creation of classes; - 263: instantiation of agents; - 40: valley; - 411-417: hydraulic plants; - 421-426: reservoirs; - 431-432: pumping stations; - 50: physical object; - 51: production facility; - 52: tank; - 53: central programming entity; - 501-503: operating parameters; - 520-523: operating parameters; - 511: hydraulic plant; - 512: nuclear plant; - 513-517: operating parameters; - 60: alarm clock; - 61: production; - 62: change of operating point; - 63: stop; - 64: inactivity phase. List of cited documents Patent documents

[0079] For all useful purposes, the following patent documents are cited: - patcitl: CN110445173A (publication number); - patcit2: US2017262007Al (publication number); and - patcit3: CN113991641A (publication number). Non-patent literature

[0080] For all useful purposes, the following non-patent elements are cited: - nplcitl: C. Donzelli, SA Kidanu, R. Chbeir, and Y. Cardinale, “Onto2MAS: An ontology-based framework for automatic multi-agent System generation”, in 2016 12th International Conference on Signal-Image Technology & Intemet-Based Systems (SITIS), IEEE, 2016, p. 381-388; - nplcit2: G. Poveda and R. Schumann, “An ontology-driven approach for modeling a multi-agent-based electricity market”, in Multiagent System Technologies: 14th German Conference, MATES 2016, Klagenfurt, Ôsterreich, September 27-30, 2016. Proceedings 14, Springer, 2016, p. 27-40; - nplcit3 : S. Marchenkov, “Automated Code Génération of Multi-Agent Interaction for constructing Semantic Services”, in Proc. 14th Int’l Conf. on Mobile Ubiquitous Computing, Systems, Services and Technologies (UBICOMM). IARIA XPS Press, 2020 ; - nplcit4 : Quynh-Nhu Numi Tran et Graham Low. « MOBMAS : A methodology for ontology based multi-agent Systems development ». In : Information and Software Technology, 50.7-8 (2008), p. 697-722; et - nplcit5:1. Stankov, Y. Yang, B. A. Langellier, J. Purtle, K. L. Nelson, and A. V. Diez Roux, “Dépréssion and alcohol misuse among older adults: Exploring me-chanisms and policy impacts using agent-based modelling”, Social psychiatry and psychiatrie epidemiology, vol. 54, pp. 1243-1253, 2019.

Claims

Claims

1. Method for optimizing a schedule of electrical energy production by an electrical production park comprising a plurality of production units (411-417; 51), comprising: a. a reception of a program (516) for the production of electrical energy, comprising an instruction (16) for the production of electrical power for said production units for a reference period; b. a simulation, from said production instruction (16), of a production of electrical power by said production units (411-417; 51), implemented by a multi-agent system (23) modeling said fleet, i. said multi-agent system (23) being generated from a formal representation (10) of said production park, constructed from an ontology (11) and a knowledge graph (12) comprising a set of nodes each representing an element of one of said production units (411-417; 51), and a set of edges each representing a functional relationship between two nodes which they connect, ii. said formal representation (10) being updated:

1. according to a determined time step, from values ​​representative of operating parameters of said nodes, received from sensors (15) arranged in said park; 2. on the fly, in the event of a change (17) affecting at least one operating state of one of said nodes; c. a generation, for said reference period, of an optimized electrical energy production program, comprising a production setpoint (18) adjusted according to the simulated electrical power production for said production units and taking into account said operating states and said representative values ​​of the operating parameters updated in said formal representation.

2. Optimization method according to claim 1, characterized in that it also comprises sending, to said production units, said production instruction (18) adjusted from the electrical energy production program optimized for said reference period.

3. Optimization method according to any one of claims 1 or 2, characterized in that it also comprises a restitution on a human-machine interface (24) of said simulated electrical power production and / or said generated optimized electrical energy production program.

4. Optimization method according to any one of claims 1 to 3, characterized in that said park comprises at least two production units (411-417; 51) belonging to the group comprising: - hydraulic power stations; - thermal power stations; - nuclear power stations; - photovoltaic energy sources; - wind energy sources; - hydro energy sources; - hydraulic pumping stations; - batteries.

5. Optimization method according to any one of claims 1 to 4, characterized in that said nodes of said knowledge graph represent elements belonging to the group comprising: - water reservoirs (421-426; 52); - pumping stations (431-432); - production installations (411-417; 51); - production generators; - production auxiliaries.

6. Optimization method according to any one of claims 1 to 5, characterized in that said operating parameters belong to the group comprising: - a volume of stored water; - a range of required inlet water flow rate; - an outlet water flow rate; - an electrical power produced; - a range of inlet water temperature; - a requested electrical power; - a maximum available power range; - a minimum high stage duration; - a minimum low stage duration; - an operating point type; - a system state; - a fuel type; - a requested gas power.

7. Optimization method according to any one of claims 1 to 6, characterized in that said operating states belong to the group comprising: - an active operating state; - a failure state; - a shutdown state; - an electrical consumption state.

8. Optimization method according to any one of claims 1 to 7, characterized in that said electrical power production setpoint (16) takes into account a forecast of electrical consumption.

9. Computer program comprising instructions for implementing the method according to one of claims 1 to 8 when this program is executed by a processor.

10. Non-transitory recording medium readable by a computer on which is recorded a program for implementing the method according to one of claims 1 to 8 when this program is executed by a processor.

11. System for optimizing an electrical energy production schedule by an electrical production park comprising a plurality of production units (411-417; 51), comprising: a. a communication module (13-14) configured to: i. receive an electrical energy production schedule, comprising an electrical power production setpoint (16) for said production units (411-417; 51) for a reference period; ii. send, to said production units (411-417; 51), an adjusted production setpoint (18) of an electrical energy production schedule optimized for the said reference period; b. a semantic database configured to store a formal representation (10) of said park, constructed from an ontology (11) and a knowledge graph (12) comprising a set of nodes each representing an element of one of said production units (411-417; 51), and a set of edges each representing a functional relationship between two nodes which they connect; c. a set of sensors (15) configured to provide, according to a determined time step, values ​​representative of operating parameters of said nodes, intended to supply said formal representation (10); d. a human-machine interface (24) configured to allow the updating (17) of said formal representation in the event of a change affecting at least one operating state of one of said nodes; e. a multi-agent system (23) modeling said fleet, generated from said formal representation (10), and configured to simulate, from said production setpoint (16), a production of electrical power by said production units (411-417; 51), said multi-agent system (23) comprising a central programming entity (53) configured to generate, for said reference period, said optimized electrical energy production program, comprising said production setpoint (18) adjusted as a function of the simulated electrical power production for said production units (411-417; 51) and taking into account said operating states and said representative values ​​of the operating parameters updated in said formal representation (10).

Images