Adaptive energy management system and method based on the use of tokenized energy profiles (TOE)

Abstract

Adaptive energy management system and method based on tokenized energy profiles (TEP) in a distribution network, comprising a data ingestion module configured to acquire, aggregate and encrypt structured and unstructured data in real time; a real-time intelligent analysis module based on neural networks and configured to detect patterns of energy consumption and generation, to classify these patterns by generating energy footprints associated with one or multiple users, to predict consumption or generation values and to obtain optimization actions in real time; an automated control and activation module configured to control elements of electricity generation and consumption using model-based predictive control (MPC) techniques and fuzzy algorithms; and a security module configured to encrypt communications using encryption techniques, role-based access control (RBAC), blockchain storage, and real-time monitoring of anomalies.

Description

[0001] ADAPTIVE ENERGY MANAGEMENT SYSTEM AND METHOD BASED ON THE USE OF TOKENIZED ENERGY PROFILES (TOE)

[0002] DESCRIPTION

[0003] OBJECT OF THE INVENTION

[0004] The present invention falls within data management systems, more particularly within the area of energy management systems.

[0005] The objective of the present invention is to develop an advanced adaptive energy management system that overcomes the technical limitations of the state of the art by providing the user with comprehensive, secure and traceable control of their energy data, and allowing a decentralized, efficient and scalable management, capable of dynamically adjusting to various energy conditions and operational contexts.

[0006] BACKGROUND TO THE INVENTION

[0007] Current energy management systems are centralized and limit active user participation. These solutions do not allow the user to manage their own data or optimise their consumption, which affects efficiency and sustainability.

[0008] Existing solutions often keep the user in a passive role, without providing tools to manage their own energy data or to participate in decisions about its consumption and generation. This lack of empowerment limits the adoption of sustainable practices and personalized optimization of energy use, affecting both operational efficiency and environmental sustainability.

[0009] Despite advances in artificial intelligence and information technologies applied to energy management, current systems have the following limitations:

[0010] 1 . Data Centralization and Vulnerability: o Data Accumulation at Central Points: Centralization creates bottlenecks that prevent efficient processing and increases vulnerability to cyberattacks. o Lack of User Control: Users lack access and control over their energy data, which prevents informed and personalized decisionmaking.

[0011] 2. Rigidity and Lack of Adaptability: o Static Systems: Traditional systems are inflexible and do not adapt quickly to changes such as the integration of renewable energy sources or fluctuations in energy demand. o Outdated Architectures: The adoption of emerging technologies is hindered by architectures that do not support the efficient integration of new tools and methodologies.

[0012] 3. Limitations in Interoperability and Collaboration: o Lack of Common Standards: The absence of unified standards prevents efficient interoperability between different energy systems and devices. o Restricted Collaboration: Limited collaboration between users and actors in the energy ecosystem restricts collective optimization and sharing of resources and data.

[0013] 4. Passive User Approach: o Lack of Active Management Tools: Users do not have the tools to actively participate in their energy management, which reduces the ability to adopt efficient consumption practices. o Demand for Transparency and Security: There is a growing demand for control, transparency and security in the management of energy data, aspects that are not adequately addressed by traditional systems.

[0014] DESCRIPTION OF THE INVENTION

[0015] The present invention focuses on an adaptive energy management system based on the use of tokenized energy profiles (TEPs), which are nodes in a distribution network, called Hybrid Data Mesh Architecture (HDMA). The invention's system aims to overcome the limitations of existing management systems and contribute to the efficiency, sustainability and democratization of the energy sector.

[0016] Thus, the adaptive energy management system of the invention comprises:

[0017] - a Data Ingestion and Preprocessing Module (DIPM), configured to acquire and aggregate structured and unstructured data in real time and to encrypt the data;

[0018] - a real-time intelligent analysis module, called Intelligent Analysis and Processing Module (IAPM), based on the use of neural networks and configured to detect patterns of energy consumption and generation, to classify these patterns according to specific characteristics, generating energy footprints associated with one or multiple users, to predict future consumption or generation values and to obtain optimization actions in real time through a multivariate analysis between the patterns obtained and historical, environmental and user behavior data;

[0019] - an automated control and activation module, called the Control and Action Module (CAM), configured to control elements of electricity generation and consumption in an automated manner by translating instructions obtained from the intelligent analysis module into commands, and implementing model-based predictive control (MPC) techniques and fuzzy algorithms for automated decision-making; and

[0020] - a security module called Security and Transactions System (STS), configured to encrypt communications between system modules by incorporating communications encryption techniques, role-based access control (RBAC), storage of actions in blockchain and real-time monitoring of anomalies to detect intrusions.

[0021] Preferably, the Data Ingestion module can be configured to fetch data from selected data sources from: loT sensors, smart meters, historical records, environmental data, unstructured data such as images, sounds, videos, or documents, and user behavior data. As for structured data, it can be processed by compression algorithms that make use of unsupervised autoencoder-type neural networks and are stored in distributed databases. Unstructured data can be processed using machine learning techniques by performing stages of classification, filtering and extraction of relevant features using natural language processing (NLP) and convolutional neural network (CNN) techniques.

[0022] The Data Ingestion module can also be configured to pre-process the obtained structured and unstructured data. To this end, the data ingestion module can apply stages of format standardization, correction of inconsistencies, elimination of duplicates, incorporation of semantic geolocation, temporal and / or categorization data and applying machine learning techniques for the detection of anomalies and inconsistent patterns.

[0023] On the other hand, the intelligent analysis module can, preferably, make use of clustering algorithms, such as K-means for detecting patterns and DBScan for detecting atypical behaviors, classification algorithms, decision tree type to categorize elements and vector support machines (SVM) to increase classification accuracy, and / or linear or nonlinear regression algorithms to predict consumption or generation values.

[0024] More particularly, the intelligent analytics module can make use of algorithms to predict consumption or generation values such as ARIMA, to forecast trends, Prophet to incorporate seasonality and trend considerations, Long Short-Term Memory (LSTM) algorithms to capture long-term dependencies, and convolutional neural networks (CNNs) for spatial data analysis and optimization of consumption patterns.

[0025] More preferably, the intelligent analytics module can be configured to perform proactive optimization and efficient planning by predicting energy demand, for which it makes use of stochastic optimization algorithms, of the genetic type and simulated annealing, to avoid local minimums, and deep reinforcement learning algorithms, which train intelligent agents for automated reward-based decisionmaking. In addition, to detect anomalies, the intelligent analysis module can make use of unsupervised autoencoder-type neural networks and isolation forest algorithms for the identification of outliers.

[0026] As for the security module, this module can make use of machine learning algorithms for threat detection, biometric authentication systems, dynamic access policies, detailed log logging on blockchain, smart contracts and consensus mechanisms to validate transactions, forensic analysis, digital signatures and real-time access permission management.

[0027] The system of the invention may also include a user interaction module, called the User Interaction Module (UIM), which, in turn, comprises: intelligent agents that make use of multimodal language models (LLMs), natural language processing (NLP) algorithms and machine learning algorithms to make proactive notifications based on predictive analysis and to adapt to the user's preferences.

[0028] On the other hand, the system of the invention may also include an interface module, called User Interface (III), configured to provide data in a format understandable by the user by updating it in real time with the data received by the data ingestion module and with the analysis performed by the intelligent analysis module.

[0029] Also, an integration and development module, called the Integration and Development Platform (IDP), configured to connect with external applications and devices, can be added to the invention's system, which implements standard APIs to ensure compatibility and common communication protocols.

[0030] The energy management system described may also comprise a resilience and continuity module, called the Resilience and Continuity Module (RCM), configured to implement the nodes of the distribution network in a microservices architecture orchestrated by a distributed system for the distribution and scaling of resources and for replication and automatic recovery in case of failure.

[0031] Finally, the system can also include a technological monitoring and optimization module, called Supervision and Technological Optimization Module (STOM), configured to monitor, optimise and automate the application of optimization actions, which makes use of performance analysis algorithms and inefficiency detection, algorithms for evaluating the technology used and proactively updating, and process optimization automation algorithms using machine learning.

[0032] With the characteristics described, the objective of the system of the invention is:

[0033] 1 . Empower the user by giving them ownership and detailed control over their energy data, through blockchain-based tokenization techniques that guarantee the security, privacy, and integrity of information. This is achieved through the implementation of the Tokenized Energy Profile (TEP) and the security module, called Security and Transactions System (STS), which enable secure and verifiable management of energy data.

[0034] 2. Optimise energy consumption and generation in a personalized and adaptive way through advanced artificial intelligence and machine learning algorithms, which allow identifying patterns, predicting needs, and applying energy optimization strategies in real time. This functionality is carried out through the intelligent analysis module, called the Intelligent Analysis and Processing Module (IAPM), which is responsible for analysing the data stored in the TEP and implementing the optimisation of energy consumption and generation.

[0035] 3. Improve interoperability and collaboration by integrating with heterogeneous devices and systems, using standardized APIs and open protocols that ensure effective interaction within the energy ecosystem. This is facilitated through the integration and development module, called the Integration and Development Platform (IDP) (107), which enables integration with external applications and services.

[0036] 4. Increase resilience and scalability through the proposed architecture, called Hybrid Data Mesh Architecture (HDMA), which integrates centralized and decentralized elements, facilitating an efficient distribution of data processing and storage, eliminating single points of failure and allowing horizontal scalability. HDMA ensures that each node in the system operates autonomously, thus improving the overall resilience of the system.

[0037] 5. Ensure operational continuity even in high-demand scenarios or system failure situations, through advanced replication, load balancing, and disaster recovery strategies. This capability is implemented through the Resilience and Continuity Module (RCM), which guarantees the availability and integrity of data at all times.

[0038] Thus, through the synergistic integration of all these technologies, personalized, secure and decentralized energy management is provided, which overcomes the shortcomings of traditional systems and sets a new standard in the energy sector, aligning operational efficiency, sustainability and user protection.

[0039] On the other hand, the system of the invention also introduces a general energy model, called the General Energy World Model (GEWM), which allows the aggregation of the Tokenized Energy Profile (TEP) at the macro level. This model enables advanced simulation and optimization of entire energy grids, benefiting energy communities, industries, and smart grids by enabling detailed and predictive analysis of collective energy behavior.

[0040] Thus, the invention's adaptive energy management system sets a new standard in comprehensive energy management, aligning with global sustainability and efficiency goals, and promoting a user-centric approach that empowers individuals and communities to proactively and safely manage their energy consumption and generation.

[0041] The invention also refers to an adaptive energy management method based on the use of tokenized energy profiles (TEPs) that function as nodes in a distribution network. The method of invention comprises the stages of:

[0042] - data ingestion: acquiring and aggregating structured and unstructured data in real time, ensuring data encryption;

[0043] - Intelligent real-time analysis: using neural networks to detect patterns of energy consumption and generation, to classify these patterns according to specific characteristics, generating energy footprints associated with a user, to predict future consumption or generation values and to obtain real-time optimization actions through a multivariate analysis between the patterns obtained and historical data, environmental and user behavior;

[0044] - automated control and activation: controlling elements of electricity generation and consumption in an automated way by translating instructions obtained from the intelligent analysis module into commands, implementing model-based predictive control (MPC) techniques and using fuzzy algorithms for automated decision-making; and

[0045] - Implementation of security mechanisms: encrypting communications between system modules by incorporating encryption techniques, rolebased access control (RBAC), storage of actions on blockchain, and realtime monitoring of anomalies to detect intrusions.

[0046] The invention described is distinguished by its focus on data security and governance, using advanced cryptographic algorithms and blockchain technologies to ensure the privacy, integrity, and traceability of energy information. This ensures compliance with regulations such as the General Data Protection Regulation (GDPR).

[0047] In addition, the system operates as an adaptive digital energy ecosystem, capable of learning and dynamically adjusting to the changing conditions of the energy environment, setting a new standard in comprehensive energy management and aligning with global goals of sustainability, efficiency, and user protection.

[0048] The system and method of the invention provide through the technical characteristics described the advantages of:

[0049] • User Empowerment: User control and ownership of energy data allows for informed and personalized decisions, encouraging sustainable practices.

[0050] • Scalability and Flexibility: Hybrid architecture makes it easy to adapt to different scales, from individual users to energy communities.

[0051] • Security and Regulatory Compliance: The implementation of advanced security technologies ensures data protection and regulatory compliance. • Personalized Energy Optimization: The application of artificial intelligence allows an adaptive and efficient optimization of energy consumption and generation.

[0052] • Interoperability and Collaboration: IDP facilitates integration with devices and systems through standardized APIs and open protocols to ensure effective interaction in the energy ecosystem.

[0053] The management system described can be applicable in various contexts:

[0054] • Smart Homes: Efficient management of energy consumption in homes, with control of connected devices and optimization of distributed generation (e.g.: solar panels, domestic batteries).

[0055] • Buildings and Offices: Optimization of energy use in commercial environments, including HVAC systems, automated lighting, and efficient management of high-consumption equipment, such as servers or heavy machinery.

[0056] • Energy Communities: Coordination and optimisation of energy consumption and generation at the community level, facilitating the exchange of energy between users and maximising the use of shared renewable sources, such as solar or community wind farms.

[0057] • Electric Vehicle Fleets: Management of the charging and discharging of electric vehicles in business or municipal fleets, optimizing energy use based on hourly rates and reducing operating costs, as well as balancing demand in the grid.

[0058] • Smart Grid Integration: Collaboration with smart grid operators to improve the stability and efficiency of the electricity system as a whole, adjusting demand in real-time and enabling user participation in demand response programs.

[0059] • Industrial Infrastructure: Monitoring and optimization of energy consumption in industrial facilities, adjusting the use of heavy machinery and production processes to reduce demand peaks and improve operational efficiency.

[0060] • Data Centers: Optimization of energy consumption in data centers, through the dynamic management of the use of servers and cooling systems, ensuring that consumption is aligned with operational needs in real time.

[0061] • Distributed Energy Storage: Management and optimization of energy storage in distributed batteries, whether in homes, buildings, or electric vehicle fleets, to maximize efficiency and enable participation in energy markets.

[0062] • Smart Agriculture: Optimization of energy use in agriculture through automated control of irrigation systems, greenhouse lighting, and agricultural machinery, all synchronized with environmental conditions and operational needs.

[0063] • Critical Infrastructures: Energy management in hospitals, water treatment plants or security facilities, ensuring an uninterrupted and optimised energy supply, especially in critical or emergency times.

[0064] EXPLANATION OF THE FIGURES

[0065] To complement the description that is being made and with the aim of helping a better understanding of the characteristics of the invention, a set of figures, represented for illustrative and non-limiting purposes, detailing the key components and flows of the proposed system, is attached as an integral part of this description.

[0066] • Figure 1 : Shows a general schematic of the architecture of the adaptive energy management system, highlighting the different modules that interact with each other to efficiently manage the energy of users and devices.

[0067] • Figure 2: Presents the data flow and analysis process between key modules of the system, detailing how data is captured, processed, and optimised to improve energy efficiency.

[0068] Figure 3: Illustrates how users can interact with the system through the User Interaction Module (UIM) (102), showing the customization of energy recommendations based on the Tokenized Energy Profile (TEP) and how the data is fed back into the system to improve future optimizations.

[0069] • Figure 4: Represents a use case focused on system integration with a Smart Grid, where the system dynamically adjusts power consumption in response to grid signals, optimizing both cost savings and grid stability.

[0070] • Figure 5: Describes an example of participation in Demand Response programs through integration with the smart grid. It details how the system can automatically adjust the energy consumption of connected devices based on prices and the availability of energy on the grid.

[0071] • Figure 6: Illustrates the transition from Personalized Energy Models (PEWM) to a General Energy Model (GEWM), showing how individual energy profiles, grouped into Energy Footprint Families, contribute to a macro view of collective energy behavior and allow for global optimization.

[0072] PREFERENTIAL REALIZATION OF THE INVENTION

[0073] The present invention offers a comprehensive and adaptive solution for energy management, focused on user empowerment and the efficient utilization of advanced technologies.

[0074] The invention focuses on an adaptive energy management system that overcomes the limitations of traditional approaches, bringing significant advantages in terms of efficiency, safety, flexibility and sustainability.

[0075] The invention's system empowers the user by providing secure and dynamic control over their energy data.

[0076] The system of the invention is based on the use of a Tokenized Energy Profile (TEP (100), which acts as a personalized and dynamic repository of energy data for each user or entity (consumer, producer or prosumer). Through the use of blockchain technologies and advanced cryptographic algorithms, the TEP (100) guarantees the privacy, integrity and traceability of energy information, allowing the user to manage in a granular way the access and use permissions of their data.

[0077] In addition, the TEP (100) facilitates the identification and analysis of multiple specific energy footprints, such as the carbon, thermal, mobility and electricity consumption footprint, and industrial processes, generating a unique energy footprint that characterises the integral energy behaviour of the user or entity. These footprints allow for adaptive and personalized energy optimization.

[0078] The system can also include a General Energy World Model (GEWM) (114) that aggregates tokenized energy profiles at the macro level, allowing simulations and optimizations at the collective level, benefiting both energy communities and smart grids.

[0079] In addition, the system of the invention also incorporates the use of a Hybrid Data Mesh Architecture (HDMA) (105) that integrates the advantages of centralized and decentralized architectures, allowing each TEP (100) to function as a standalone node within a distributed network.

[0080] This architecture uses a combination of relational and NoSQL databases, realtime data processing, and container orchestration, significantly improving the scalability and resiliency of the system. HDMA (105) facilitates secure collaboration between users and entities, ensuring user ownership and control of data.

[0081] The system also comprises several interconnected modules that work synergistically to provide comprehensive and adaptive energy management:

[0082] 1. Data Ingestion and Preprocessing Module (DIPM) (106): Captures, normalizes and enriches energy data from structured and unstructured sources, ensuring the quality and security of data transmission. 2. Intelligent Analysis and Processing Module (IAPM) (101 ): The IAPM (101 ) uses artificial intelligence to identify patterns, predict behaviors, optimise energy, and detect anomalies.

[0083] 3. User Interaction Module (UIM) (102): Facilitates two-way communication with the user using intelligent agents and chatbots, providing personalized notifications and allowing the configuration of energy preferences.

[0084] 4. User Interface (III) (103): Provides graphical and functional tools for visualizing and managing the energy profile, controlling permissions, and ensuring data security.

[0085] 5. Integration and Development Platform (IDP) (107): Allows integration with external applications and services through standardized APIs and common protocols, promoting interoperability.

[0086] 6. Control and Action Module (CAM) (104): Implements optimised actions in real time on devices and energy systems, automating energy management.

[0087] 7. Security and Transactions System (STS) (110): The STS (110) ensures security and regulatory compliance through blockchain and access management, ensuring the traceability of all data transactions.

[0088] 8. Resilience and Continuity Module (RCM) (108): Ensures operational availability and data integrity through replication, load balancing, and disaster recovery.

[0089] 9. Supervision and Technological Optimization Module (STOM) (109): Continuously monitors and optimises automated tasks and the technology used, establishing a technology development plan.

[0090] 10. General Energy World Model (GEWM) (114): Enables the aggregation of energy profiles at the macro level, generating a global view of collective energy performance and facilitating the optimization of entire energy networks.

[0091] Each of the modules of the system is described in more detail below:

[0092] 1. TOKENIZED ENERGY PROFILE (TEP) (100) The TEP (100) is the central core of the system, acting as a personalized and dynamic repository of energy data for each user or entity (consumer, producer or prosumer). This module addresses key technical issues in today's energy management, such as data centralization, lack of user control over their energy information, and limitation in comprehensive analysis of heterogeneous data. Its main characteristics are:

[0093] • Heterogeneous Data Storage

[0094] The TEP (100) collects and stores energy data from various sources, providing a unified platform for the management of heterogeneous information:

[0095] • loT Devices and Smart Sensors: Real-time data on energy consumption and generation.

[0096] • Smart Meters: Detailed information on electricity, gas and water usage.

[0097] • Historical Records: Historical consumption data for trend and pattern analysis.

[0098] • Environmental Data: Weather and environmental information that influences energy consumption.

[0099] • User Preferences and Behaviors: Data on individual energy habits and preferences.

[0100] This data can be structured or unstructured, and TEP (100) uses a combination of relational databases (SQL) and NoSQL to handle it efficiently. This architecture enables flexible and scalable management of large volumes of diverse data.

[0101] Once the data is stored in the TEP (100), it is continuously processed and prepared to be sent to the Intelligent Analysis and Processing Module (IAPM) (101 ). This flow is managed through a series of internal APIs that facilitate the secure and real-time transfer of relevant data to the IAPM (101 ) for analysis. This communication allows energy data to be evaluated and optimised without significant latencies, ensuring fast and efficient decision-making. Likewise, the TEP (100) updates the data according to the changes detected by the IAPM (101 ) dynamically adjusting to energy needs.

[0102] Technical Problem Solved: Traditional systems face difficulties handling data from multiple sources and formats, which limits the ability to analyze and optimise energy. The TEP (100) solves this problem by efficiently integrating and managing heterogeneous data, allowing a complete and detailed view of the user's energy profile.

[0103] • Real-time update

[0104] The TEP (100) allows a continuous and coordinated update of data in real time, integrating multiple sources of energy information:

[0105] • It uses streaming data processing systems such as Event Buses or Complex Event Processors (CEPs), guaranteeing the immediate reception and processing of data.

[0106] • Each data source uses timestamps synchronized using protocols such as NTP (Network Time Protocol) or PTP (Precision Time Protocol), ensuring accurate chronological alignment.

[0107] • Data is processed directly into memory, eliminating latencies and facilitating real-time decision-making.

[0108] • The use of sliding time windows allows data to be grouped and analyzed at predefined intervals, immediately detecting consumption patterns and optimizing the system automatically.

[0109] Technical Problem Solved: The inability of conventional systems to process and react to real-time data limits energy efficiency and responsiveness to rapid change. The TEP (100) overcomes this limitation, allowing dynamic and adaptable energy management.

[0110] • Energy Fingerprint Identification (HE)

[0111] The TEP (100) employs advanced data analysis techniques and machine learning algorithms to create a unique energy footprint for each user or entity, composed of multiple specific sub-footprints. The energy footprints generated can be grouped into energy families that represent not only the profile of an individual user, but of broader groups, such as energy communities or commercial networks. This grouping allows for simultaneous optimization of multiple users, providing energy-saving recommendations that benefit both individuals and entire networks, facilitating greater efficiency and collaboration in energy management. Some of these traces can be: • Carbon Footprint: CO2emissions associated with energy consumption.

[0112] • Thermal Footprint: Consumption related to heating and cooling.

[0113] • Mobility Footprint: Energy use in transport and travel.

[0114] • Electricity Consumption Footprint: Use of electricity in devices and systems.

[0115] • Other Sub-footprints: Any other metrics relevant to energy decisionmaking.

[0116] These sub-footprints are collected and synchronized using temporal coordination protocols, allowing their combination and joint analysis within the TEP (100). The multidimensional integration of these footprints makes it easier to:

[0117] • Comprehensive Characterization of Energy Behavior: Provides a holistic and detailed view of the user's energy use in all relevant areas.

[0118] • Detection of Synergies and Cross-Efficiencies: Identifies interactions between different energy areas, allowing multiple aspects of consumption to be optimised simultaneously. For example, it can suggest the best time to charge an electric vehicle considering the availability of renewable energy and the user's mobility needs.

[0119] • Advanced Scenario Simulation: It acts as a digital twin of the energy system, allowing the impact of changes in behavior or external conditions to be simulated and evaluated using predictive algorithms and machine learning models.

[0120] Technical Problem Solved: Current systems do not offer an integrated and multidimensional view of energy behavior, which limits the optimization and customization of solutions. The TEP (100) solves this problem by combining and analysing multiple energy footprints in real time, providing deep and actionable insights.

[0121] • Data Tokenization

[0122] TEP (100) uses blockchain and cryptographic algorithms to tokenize energy data, ensuring its security, integrity, and traceability: • Robust Cryptographic Algorithms: Employs SHA-256 or RSA to ensure that data cannot be altered or accessed without authorization.

[0123] • Granular Data Management: Each token represents a specific piece of information, allowing users or external systems to access only the relevant data based on the permissions set.

[0124] • Blockchain Registration: Each token is recorded on an immutable blockchain, ensuring traceability of all interactions with the data.

[0125] • Smart Contracts: They automate access rules and conditions of use, ensuring that only authorized parties can transact with tokenized information.

[0126] Technical Problem Solved: The security and privacy of energy data are critical. Traditional systems lack robust mechanisms to protect sensitive information. The tokenization and use of blockchain in the TEP (100) provide a secure and reliable environment, ensuring integrity, confidentiality and traceability. Blockchain technology not only ensures the tokenization of energy data, but also provides real-time traceability of all energy transactions and decisions. This immutable ledger architecture ensures that every change or interaction within the system is secured and complies with international cybersecurity and regulatory compliance standards.

[0127] • User Ownership and Control

[0128] Tokenization enables a model in which the user is the absolute owner of their energy data:

[0129] • Access Permissions Management: Users can grant or revoke access to third parties in a granular manner and in real-time using key management interfaces.

[0130] • Regulatory Compliance: Ensures compliance with regulations such as GDPR, giving users full control over their information and how it is used.

[0131] • Transparency and Trust: Blockchain technology allows for transparent audits, strengthening trust between users and energy suppliers.

[0132] Technical Problem Solved: In conventional systems, users have limited control over their data, which can lead to privacy and legal compliance concerns. The TEP (100) empowers the user, allowing a proactive and secure management of their energy information.

[0133] • Open-Source Architecture

[0134] TEP (100) adopts an open-source architecture, fostering innovation and collaboration:

[0135] • Continuous Evolution: The community can contribute to development, ensuring that the system adopts the latest technologies and best practices in cybersecurity and data management.

[0136] • Interoperability: Facilitates integration with other systems and standards, ensuring adaptability to new energy market demands.

[0137] • Transparency: Open source allows for independent audits and reviews, increasing trust in the system.

[0138] Technical Problem Solved: Proprietary systems can limit flexibility and adaptation to new technologies. An open-source architecture ensures that TEP (100) remains at the forefront of technology and can evolve rapidly.

[0139] The TEP (100) introduces an innovative technical solution that combines several technologies and concepts in a non-obvious way to solve specific technical problems:

[0140] • User Empowerment: Grants full and secure control over energy data, something not evident in the state of the art.

[0141] • Comprehensive and Personalized Analysis: The identification and combination of multiple energy footprints allow an adaptive and efficient optimization of energy consumption and generation.

[0142] • Enhanced Security and Privacy: Tokenization and blockchain ensure the integrity, confidentiality, and traceability of data, overcoming the limitations of traditional systems.

[0143] • Flexibility and Scalability: The ability to update and process data in real time, together with an open architecture, allows it to adapt to different scales and energy contexts.

[0144] • Continuous Innovation: Open-source architecture promotes the development and adoption of new technologies and best practices. The combination of real-time heterogeneous data management, multidimensional energy fingerprint identification, data tokenization, and user empowerment using blockchain is not apparent to a subject matter expert. This integration innovatively solves specific technical problems, providing an advanced and effective technical solution that overcomes the limitations of existing systems.

[0145] 2. HYBRID DATA MESH ARCHITECTURE (HDMA) (105)

[0146] The Hybrid Data Mesh Architecture (HDMA) (105) is an innovative solution designed to address specific challenges in distributed energy management, combining the benefits of centralized and decentralized architectures. HDMA (105) integrates advanced technologies that allow each TEP (100) to function as a standalone node within a distributed network. This architecture uses relational and NoSQL databases, real-time processing, and efficient orchestration using a Container Orchestrator, ensuring flexibility, scalability, and resiliency.

[0147] Traditional energy management systems face several technical problems:

[0148] • Scalability Limitations: Centralized architectures can create bottlenecks and not scale efficiently with increasing devices and data.

[0149] • Lack of Resilience: Dependence on a single point of failure, which affects operational continuity in the event of failures or attacks.

[0150] • Restricted Interoperability: Difficulties in integrating multiple data sources and heterogeneous devices.

[0151] • Complex Data Management: Efficiently handling structured and unstructured data is a challenge in conventional systems.

[0152] HDMA (105) addresses these issues by providing a distributed infrastructure that combines the benefits of centralization and decentralization, enabling efficient and secure management of energy data in changing and scalable environments. o Key features

[0153] Scalability and Flexibility HDMA (105) distributes the processing and storage load among the TEP nodes (100) using a combination of:

[0154] • Relational Databases and NoSQL: Allows efficient management of structured data (e.g., energy consumption history) and unstructured data (e.g., loT sensor data), providing flexibility and performance.

[0155] • Real-Time Processing: Uses technologies such as Event Buses or Complex Event Processors (CEPs) to process data streams in real-time, enabling immediate responses to energy events.

[0156] • Orchestration: The orchestrator dynamically manages the TEP nodes (100), automating the deployment, load balancing, and restart of nodes in case of failures, ensuring high availability and operational continuity.

[0157] Technical Problem Solved:

[0158] Traditional systems can't scale efficiently with the growth of devices and data. HDMA (105) solves this problem by enabling dynamic scale-out, ensuring that performance is not compromised and avoiding bottlenecks.

[0159] - Improved resiliency

[0160] The decentralization inherent in HDMA (105) improves system resilience:

[0161] • Single Point of Failure Elimination: If one TEP node (100) fails or experiences technical problems, the rest of the network continues to operate autonomously, ensuring operational continuity.

[0162] • High Availability: Container Orchestration allows for automatic replication and redistribution of TEP nodes (100), maintaining system availability even in cases of failure.

[0163] Technical Problem Solved:

[0164] Centralized systems are vulnerable to failures that can disrupt service. HDMA (105) improves resiliency by eliminating reliance on a single point of failure, ensuring uninterrupted operations.

[0165] - Collaboration and Secure Data Sharing

[0166] HDMA (105) facilitates the interaction and sharing of data between TEP nodes (100) and external entities:

[0167] • Controlled Access Policies: Implement authorization mechanisms that allow data to be shared in a secure and controlled manner. • Blockchain Technology: Ensures that shared data is protected, and only authorized parties can access it. It provides traceability and transparency in data transactions.

[0168] • Open APIs and Common Standards: Ensure interoperability between different systems and devices, facilitating large-scale collaboration and data sharing without compromising data security or integrity.

[0169] Technical Problem Solved:

[0170] The difficulty of sharing data securely and efficiently limits collaboration in energy systems. HDMA (105) solves this problem by providing secure and standardized mechanisms for data sharing.

[0171] - Federated Governance

[0172] The HDMA (105) implements a federated governance model that ensures:

[0173] • TEP Node Autonomy (100): Each node can operate independently, but under a set of global rules and policies that ensure consistency and regulatory compliance.

[0174] • Regulatory Compliance: Compliance with regulations such as GDPR is guaranteed, allowing users to set permissions and access restrictions according to their preferences.

[0175] • Audit and Compliance Mechanisms: Using blockchain, the traceability of data transactions and compliance with privacy and security regulations are ensured.

[0176] Technical Problem Solved:

[0177] Centralized systems make it difficult to implement flexible governance tailored to the needs of each user. HDMA (105) enables federated governance that balances autonomy and consistency, facilitating regulatory compliance and customization.

[0178] 3. DATA INGESTION AND PREPROCESSING MODULE (DIPM) (106)

[0179] This module is responsible for the acquisition and aggregation of energy data from various sources, both structured (1 ) and unstructured (4), employing advanced technologies to ensure the integration, availability and governance of this data in real time for further processing and analysis. It includes encryption and authentication mechanisms to protect data from its source. o Technical Problem Solved

[0180] Traditional energy management systems face challenges by:

[0181] • Integrate Data from Multiple Sources and Formats: The diversity of devices and protocols makes unified data collection difficult.

[0182] • Process Large Volumes of Data in Real-Time: Latency and inefficient processing limit the responsiveness of the system.

[0183] • Ensure Data Quality and Security: The presence of inconsistent, duplicate, or erroneous data affects the accuracy of the analysis.

[0184] • Protect Data Transmission: The risks of interception or alteration of data during transmission can compromise the integrity of the system.

[0185] DIPM (106) addresses these issues by implementing advanced technologies and techniques for energy data ingestion, preprocessing, and security.

[0186] Its functions include:

[0187] • Multi-Source Data Integration: The DIPM (106) collects energy data from a variety of sources, both structured and unstructured:

[0188] 1. loT Devices and Smart Sensors: Real-time data on energy consumption and generation.

[0189] 2. Smart Meters: Detailed information about electricity, gas and water usage.

[0190] 3. External Databases and Public APIs: Environmental data, energy prices, weather information, etc.

[0191] 4. Storage Services: Integration with both Cloud Provider and n- premise storage platforms through an abstraction layer on top of the device or storage technology.

[0192] 5. It uses technologies for data ingestion, enabling efficient orchestration and management of complex data flows.

[0193] Technical Problem Solved: The difficulty in integrating and managing data from multiple sources and formats is overcome by using specialized tools that facilitate the ingestion and normalization of heterogeneous data. • Data Normalization and Cleansing: DIPM (106) applies ETL (Extract, Transform, Load) processes to ensure data quality:

[0194] 1 . Format Standardization: Converts data to common formats for easy processing.

[0195] 2. Inconsistencies Correction: Detects and corrects erroneous or out- of-range data.

[0196] 3. Deduplication: Ensures that each event or data is recorded only once.

[0197] 4. Data Enrichment: Add additional context to the data, such as geolocation or categorization.

[0198] 5. Machine Learning algorithms are used to detect anomalies and inconsistent patterns during preprocessing.

[0199] Technical Problem Solved: The presence of low-quality data affects the accuracy of the analysis. DIPM (106) ensures that only clean and consistent data reaches the analysis modules, improving the reliability of the system.

[0200] • Transmission Security: DIPM (106) guarantees security from the source of the data:

[0201] 1. Secure Communication Protocols: Uses TLS / SSL to encrypt data transmission from devices to the system.

[0202] 2. Authentication and Authorization: Implements secure and scalable Authentication Protocols such as OAuth 2.0, OpenlD through an identity manager (IAM) and Tokenization to verify the identity of devices and data sources.

[0203] 3. Intrusion Detection: Monitors data traffic to identify suspicious or unauthorized activity.

[0204] Technical Problem Solved: Protects the integrity and confidentiality of data during transmission, preventing unauthorized access and possible attacks. o DIPM Architecture (106)

[0205] DIPM (106) consists of three key subsystems: 4. Unstructured Data Capture Subsystem

[0206] • Data Sources: FTP, SFTP, APIs, cloud services, event buses, and Data Lakes among others.

[0207] • Data Types: Event logs, logs, social networks, images.

[0208] • Technologies Used: Indexing and categorization using semantic databases, preprocessing with real-time data processing technologies.

[0209] • Al Agents: Uses Natural Language Processing (NLP) and Convolutional Neural Networks (CNNs) to extract relevant features.

[0210] Technical Problem Solved: Facilitates the management and analysis of large volumes of unstructured data, which are difficult to process with traditional techniques. b) Structured Data Capture Subsystem

[0211] • Data Sources: loT devices, smart meters, monitoring systems.

[0212] • Connectivity: Short-range networks such as Bluetooth, Zigbee, LoRaWAN.

[0213] • Distributed Databases: Use solutions such as non-relational databases for efficient storage.

[0214] • Compression and Replication: Improve data efficiency and availability in distributed environments.

[0215] Technical Problem Solved: Efficiently manages structured data in real time, ensuring fast and reliable access. c) Al Agents Subsystem for Data Extraction and Preprocessing

[0216] • Machine Learning Algorithms: For classification, filtering, and extraction of features.

[0217] • Distributed Processing: Uses technology that enables and manages distributed storage such as Apache Hadoop and Spark to handle large volumes of data.

[0218] • Security: Implements encryption and Role-Based Access Control (RBAC). Technical Problem Solved: Automates and optimises data preprocessing, reducing manual loading and improving accuracy.

[0219] 4. INTELLIGENT ANALYSIS AND PROCESSING MODULE (IAPM) (101) The Intelligent Analysis and Processing Module (IAPM) (101 ) is a central component of the system that is responsible for processing and analysing the energy data stored in the Tokenized Energy Profile (TEP) (100). To achieve advanced and adaptive optimization of energy consumption and generation, IAPM (101 ) employs various neural network architectures that enable deep and predictive data analysis. o Technical Problem Solved

[0220] Traditional energy management systems have limitations in:

[0221] • Limited Data Analysis: Inability to process large volumes of heterogeneous data in real time and extract meaningful patterns.

[0222] • Lack of Custom ization: They offer generic solutions without adapting to the specific needs and behaviors of each user.

[0223] • Slow Response to Changes: They cannot dynamically adjust energy strategies to variations in the environment or in the user's behavior.

[0224] • Late Anomaly Detection: Faults or inefficiencies are identified late, impacting system reliability and efficiency.

[0225] The IAPM (101 ) addresses these issues by implementing advanced algorithms that enable in-depth, real-time analysis of energy data, providing customized and adaptive optimizations.

[0226] The IAPM (101 ) makes continuous and dynamic adjustments on the energy profiles, learning from historical behavior and current conditions. This adaptive approach is made possible by an optimization engine that adjusts energy configurations in real time, allowing the system to react to changes in demand, prices, or other external variables. o Key Functions of IAPM (101 )

[0227] 1. Identification of Energy Fingerprints

[0228] The IAPM (101 ) uses clustering and classification algorithms to identify specific energy patterns and behaviors. For pattern identification, the system employs recurrent neural networks (RNNs) and time-series models that capture the complex interactions between various energy variables, such as climate and occupancy. In addition, the implementation of Transformers architectures allows large volumes of data from multiple sources to be analyzed simultaneously, improving accuracy in predicting future demands and identifying inefficiencies:

[0229] • Clustering Algorithms: o K-means: Groups similar data to detect common patterns in energy consumption and generation. o DBSCAN: Identifies structures in data, including arbitrary shapes, to uncover atypical or emergent energetic behaviors.

[0230] • Classification Algorithms: o Decision Trees: Classify energy use into categories based on specific characteristics. o Vector Support Machines (SVM): They separate data into different classes with maximum margins, allowing for accurate classification.

[0231] • Regression Models: o Linear and Nonlinear Regression: Predict continuous values of energy consumption or generation based on independent variables.

[0232] These techniques allow you to generate detailed energy fingerprints, such as:

[0233] • Electricity Consumption Footprint: Electricity use patterns in devices and systems.

[0234] • Thermal Footprint: Consumption related to heating and cooling.

[0235] • Mobility Footprint: Energy use in transport and travel.

[0236] The combination of these footprints provides a comprehensive view of the user's energy behavior, allowing specific optimization opportunities to be identified.

[0237] Technical Problem Solved: Current systems do not offer a detailed and personalized characterization of energy behavior. The IAPM (101 ) solves this by identifying specific energy footprints, allowing for targeted and effective optimization.

[0238] 2. Prediction and Prognosis

[0239] The IAPM is responsible for processing and analysing the energy data stored in the TEP. To offer adaptive optimization of energy consumption and generation, it uses a variety of advanced algorithms that are grouped into the following key categories:

[0240] 1. Predictive Analytics: o It uses time series models and neural networks to predict patterns of energy consumption and demand. Examples include ARIMA, Prophet, and recurrent neural networks (RNNs, LSTMs), which allow fluctuations in energy use to be anticipated.

[0241] 2. Classification and Pattern Detection: o Algorithms such as k-means and decision trees are used to group data and classify consumption patterns. This makes it easier to identify specific energy behaviors and personalize solutions.

[0242] 3. Anomaly Detection: o Networks such as autoencoders and techniques such as Isolation Forest detect anomalies in energy behavior, allowing proactive correction of faults or inefficiencies.

[0243] 4. Energy Optimization: o Stochastic optimization algorithms such as genetic algorithms and reinforcement learning techniques determine optimal strategies for the use and generation of energy, dynamically adjusting to the conditions of the environment.

[0244] Technical Problem Solved: The inability to accurately predict future energy demands limits the efficiency of systems. IAPM (101 ) improves forecasting, allowing for timely adjustments and proactive optimizations.

[0245] 3. Energy Optimization

[0246] The IAPM (101 ) applies optimization algorithms to determine optimal energy management strategies:

[0247] • Stochastic Optimization Algorithms: o Genetic algorithms: They mimic evolutionary processes to find optimal solutions in complex search spaces. o Simulated Annealing: Seeks optimal solutions through a simulated cooling process that avoids local minimums.

[0248] • Deep Reinforcement Learning: o Smart Agent Training: Agents make decisions based on long-term rewards, adjusting consumption and generation configurations to maximize efficiency and use of renewable sources.

[0249] Once the IAPM optimization algorithms (101 ) have processed the energy data, the optimised decisions are fed back into the system via the Control and Action Module (CAM) (104). This module is responsible for implementing the necessary adjustments in real time on connected devices, such as smart thermostats, distributed generation systems, and electric vehicle chargers. The adjustments made depend on the predictions and analyses made by the IAPM (101 ), allowing the devices to act autonomously and efficiently, following the objectives established by the user.

[0250] These algorithms consider:

[0251] • TEP data (100): Detailed and up-to-date information on the user's energy profile.

[0252] • Constraints and Objectives: User preferences, energy costs, carbon emissions.

[0253] Optimization is performed in an environment:

[0254] • Distributed and Decentralized: Uses scalable resources in the cloud, allowing customization for each user without sacrificing performance.

[0255] • Adaptive: Adjusts strategies in real time in the face of changes in the environment or user behavior.

[0256] Technical Problem Solved: Traditional systems cannot adapt energy strategies in an optimal and personalized way. IAPM (101 ) provides advanced energy optimization that maximizes efficiency and reduces costs.

[0257] 4. Anomaly Detection

[0258] The IAPM (101 ) implements algorithms to identify atypical energy behaviors:

[0259] • Autoencoders: Neural networks that learn compact representations of data, detecting significant deviations that indicate anomalies.

[0260] • Isolation Forest: A tree-based model that isolates anomalies by randomly dividing data, identifying outliers with few partitions.

[0261] Early detection of anomalies allows: • Identify Equipment Failures: Detect device problems before they cause further damage or inefficiencies.

[0262] • Correct System Inefficiencies: Adjust settings to improve performance and reduce waste.

[0263] • Fraud Prevention: Identify suspicious activity that may indicate tampering or misuse of energy systems.

[0264] Technical Problem Solved: Late detection of anomalies affects the reliability and efficiency of the system. IAPM (101 ) improves resilience by proactively identifying and addressing anomalies.

[0265] 5. Integration and Operation

[0266] The IAPM (101 ) is designed to operate in orchestrated containers, which guarantees:

[0267] • Scalability: Ability to handle increases in workload by distributing resources efficiently.

[0268] • Resiliency: Fault tolerance through replication and automatic recovery of services.

[0269] • Compliance with Data Protection and Privacy Policies: Ensures that data processing and storage comply with regulations such as GDPR.

[0270] IAPM 's internal APIs (101 ) enable:

[0271] • Seamless Integration: With other TEP subsystems (100) and system modules, ensuring that Al models can access and process data efficiently.

[0272] • Process Automation: They facilitate real-time decision-making without manual intervention, improving operational efficiency.

[0273] Technical Problem Solved: Integration and scalability are often challenges in complex systems. The design of the IAPM (101 ) ensures efficient and adaptable operation, overcoming the limitations of current systems.

[0274] 6. Neural Network Architecture at IAPM (101 )

[0275] IAPM (101 ) uses multiple advanced machine learning techniques to continuously adjust to variations in the energy environment and the specific needs of each user. Among the most prominent techniques is Deep Reinforcement Learning, where intelligent agents learn from their past decisions to optimise future actions. This continuous learning capability allows the system to become increasingly efficient as it processes larger volumes of data. In addition, the implementation of clustering algorithms, such as K-means and DBSCAN, improves the classification and segmentation of complex energy patterns, facilitating the personalization and optimization of consumption strategies.

[0276] To enhance its analysis and prediction capabilities, IAPM (101 ) integrates various neural network architectures, each designed to address different aspects of energy data processing:

[0277] 1. Recurrent neural networks (RNN): o Description: RNNs are suitable for processing data streams, making them ideal for analysing time series of power consumption. o Applications in IAPM (101 ):

[0278] ■ Energy Demand Forecasting: Analyze historical consumption patterns to predict future energy demands.

[0279] ■ Anomaly Detection: Identify deviations in energy behavior that could indicate failures or unusual uses.

[0280] 2. Long Short-Term Memory (LSTM): o Description: A variant of RNNs designed to handle long-term dependencies and mitigate the problem of gradient fading. o Applications in IAPM (101 ):

[0281] ■ Energy Behavior Modeling: Captures complex, long-term patterns in energy consumption and generation.

[0282] ■ More Accurate Forecasting: Improves accuracy in predicting future energy trends.

[0283] 3. Convolutional Neural Networks (CNNs): o Description: Used primarily for the processing of structured and unstructured data, such as images or spatial data. o Applications in IAPM (101 ):

[0284] ■ Spatial Data Analysis: Processes data from geographically distributed loT sensors.

[0285] ■ Optimization of Consumption Patterns: Identifies areas with high energy efficiency or inefficiency within a building or community.

[0286] 4. Transformers Neural Networks: o Description: Designed to handle large volumes of data and capture complex relationships between different variables. o Applications in IAPM (101 ):

[0287] ■ Multivariate Analysis: Captures interactions between multiple factors that affect energy consumption, such as weather, occupancy, and energy rates.

[0288] ■ Real-Time Optimization: Facilitates fast, adaptive decisionmaking based on comprehensive data analysis.

[0289] 5. Autoencoders: o Description: Unsupervised neural networks used for dimensionality reduction and anomaly detection. o Applications in IAPM (101 ):

[0290] ■ Energy Anomaly Detection: Identifies atypical patterns in consumption that could indicate inefficiencies or fraud.

[0291] ■ Data Compression: Reduces data complexity for more efficient analysis. o Integration of Neural Networks in the IAPM (101 ):

[0292] IAPM (101 ) integrates these neural network architectures into a modular workflow that allows:

[0293] • Data Preprocessing: Cleansing, normalization, and transformation of energy data prior to analysis.

[0294] • Training and Validation: Continuous training of models using real-time and historical data to improve accuracy and adaptability.

[0295] • Model Deployment: Deployment of trained models to perform predictions and optimizations in real time.

[0296] • Feedback and Continuous Learning: Incorporation of new data and adjustments in the models to maintain the relevance and effectiveness of the analysis. o Benefits of Neural Network Implementation in IAPM (101 ):

[0297] • Greater Accuracy in Predictions: Advanced architectures allow for a deeper and more accurate understanding of energy patterns. • Adaptability and Scalability: Models can adapt to changes in user behavior and the incorporation of new data sources.

[0298] • Operational Efficiency: Automation and optimization based on artificial intelligence reduces costs and improves sustainability.

[0299] 5. USER INTERACTION MODULE (UIM) (102)

[0300] The User Interaction Module (UIM) (102) facilitates seamless two-way communication between the system and the user, employing advanced natural language processing and machine learning technologies to enhance the user experience and anticipate user needs. The system continuously learns from the user's preferences and behaviors, allowing recommendations and settings to be adjusted based on their energy profile. Users have the ability to customize not only their energy consumption, but also the way they interact with the system, ensuring a tailor-made experience aligned with their energy goals. o Technical Problem Solved

[0301] Traditional systems present challenges such as:

[0302] • Limited and Non-Personalized Interaction: Rigid interfaces that do not adapt to the user's preferences.

[0303] • Lack of Anticipation: Inability to anticipate the user's needs and offer proactive solutions.

[0304] • Fragmented User Experience: Difficulty integrating multiple communication channels in a coherent way.

[0305] The UIM (102) addresses these issues by providing an intelligent and adaptive interface that learns from user behavior. o Key features

[0306] Intelligent Agents and Chatbots

[0307] • Multimodal Language Models (LLMs): Use advanced models such as GPT-4, Gemini, or Claude. • Multichannel Interaction: Supports text, voice, and other forms of communication (e.g., gestures, images).

[0308] • Natural Language Processing (NLP): Understands and generates human language in a consistent manner.

[0309] • Continuous Learning: The system improves with each interaction, adapting to the user's preferences.

[0310] Technical Problem Solved: Improves user-system interaction, offering natural and personalized communication that is not possible with traditional interfaces. o Personalized Notifications and Proactive Anticipation

[0311] • Predictive Analytics: Uses historical data and current context to anticipate needs.

[0312] • Proactive Notifications: Informs the user about consumption peaks, savings opportunities or relevant events.

[0313] • Dynamic Personalization: Adjusts recommendations based on user behavior and preferences.

[0314] Technical Problem Solved: The system goes from being reactive to proactive, improving energy efficiency and user satisfaction. o Setting Preferences and Adaptive Learning

[0315] • Preference Management: Allows the user to set savings goals, priorities, and restrictions.

[0316] • Adaptive Learning: The system adjusts its models based on changes in user preferences or behavior.

[0317] • Continuous Monitoring: Observe interactions to improve personalization and anticipation.

[0318] Technical Problem Solved: Facilitates a personalized and adaptable experience, overcoming the rigidity of conventional systems.

[0319] 6. USER INTERFACE (Ul) The User Interface (Ul) (103) is the direct point of contact between the user and the system, designed to offer an intuitive and efficient experience that facilitates the management and visualization of the energy profile and interactions with the different modules. o Technical Problem Solved

[0320] Users often face difficulties in:

[0321] • Understanding Complex Energy Data: Traditional interfaces do not present information in a clear and understandable way.

[0322] • Manage Permissions and Security: Difficulty controlling who accesses your data and how it is used.

[0323] • Interacting from Multiple Devices: Inconsistent experiences between web and mobile platforms.

[0324] The Ul addresses these issues by providing advanced visualization and control tools. o Key features

[0325] ■ Web & Mobile Apps

[0326] • Cross-Platform Development: Use hybrid development frameworks to ensure a consistent experience and effective source code management.

[0327] • Access from Multiple Devices: Allows you to manage the energy profile from smartphones, tablets and computers.

[0328] • Real-Time Synchronization: Updates and changes are instantly reflected on all devices.

[0329] Technical Problem Solved: Offers a unified and accessible experience, facilitating energy management anytime, anywhere.

[0330] ■ Data Visualization

[0331] • Interactive Charts: Use specialized libraries to create dynamic visualizations.

[0332] • Custom Dashboards: Allows the user to configure dashboards according to their interests and needs.

[0333] • Detailed Reports: Generation of customized reports on consumption, efficiency and energy savings. Technical Problem Solved: Facilitates the understanding of complex data through clear and interactive visual representations.

[0334] ■ Permission Control and Security

[0335] • Granular Access Management: The user can assign or revoke permissions to third parties in real time.

[0336] • STS Integration (110): Ensures that all interactions comply with security and privacy policies.

[0337] • Security Alerts: Notifies the user about unusual access or activity. Technical Problem Solved: Empowers the user to manage the security and privacy of their data in a simple and effective way.

[0338] 7. INTEGRATION AND DEVELOPMENT PLATFORM (IDP) (107)

[0339] The Integration and Development Platform (IDP) (107) is a key component that facilitates integration with external applications and services, promoting interoperability and expansion of the energy ecosystem. o Technical Problem Solved

[0340] Traditional energy systems face challenges such as:

[0341] • Difficulty in Integrating Heterogeneous Systems: The lack of common standards and protocols limits collaboration.

[0342] • Limitations in the Expansion of the Ecosystem: Closed systems that do not allow the incorporation of new functionalities or services.

[0343] • Integration Security: Risks associated with connecting to untrusted external systems.

[0344] The IDP (107) addresses these issues by providing a flexible and secure platform for integration and development. o Key features

[0345] ■ Standard APIs

[0346] • Support for Multiple Formats: JSON, XML, Protocol Buffers among others.

[0347] • Modern Architectures: RESTful APIs, GraphQL for efficient queries. • Version Management: Allows multiple versions of APIs to be maintained for compatibility.

[0348] • Secure Authentication: Implements OAuth 2.0, API Keys, JWT (JSON Web Tokens).

[0349] • Interoperability Contracts: To ensure that the integration between platforms complies with interoperability standards and norms.

[0350] Technical Problem Solved: Facilitates integration with external systems in a standard and secure way, promoting interoperability.

[0351] ■ Support for Common Protocols

[0352] • Communication Protocols: MQTT, AMQP, WebSockets for real-time communications.

[0353] • loT Device Compatibility: Integration with devices from various manufacturers and standards.

[0354] • Messaging Management: Use event buses to handle data streams in publish / subscribe mode and standards-based APIs for synchronous communication, as well as interoperability contracts to manage communication.

[0355] Technical Problem Solved: Allows for smooth and efficient communication with a wide range of devices and services.

[0356] ■ Development Sandbox

[0357] • Secure Environment: Isolates development and testing from production infrastructure.

[0358] • Developer Tools: Documentation, SDKs, test environments.

[0359] • Community and Collaboration: Encourages contribution to the open- source system, allowing continuous improvements.

[0360] Technical Problem Solved: Promotes system innovation and expansion without compromising its security or stability.

[0361] 8. CONTROL AND ACTUATION MODULE (CAM)

[0362] The Control and Action Module (CAM) (104) is an essential component that connects the digital and physical worlds within the energy management system. Its main function is to execute in real time the optimised actions on devices and energy systems, based on the informed decisions generated by the Intelligent Analysis and Processing Module (IAPM) (101 ). CAM ensures that energy recommendations are translated into concrete adjustments in connected devices, such as smart thermostats, lighting systems, EV chargers, and distributed generation systems. o Technical Problem Solved

[0363] Traditional energy management systems face limitations such as:

[0364] • Lack of Effective Automation: Energy recommendations do not translate into physical actions, requiring manual intervention.

[0365] • Real-Time Response Failure: Systems cannot dynamically adapt to rapid changes in the energy environment.

[0366] • Limited Interoperability: Difficulty connecting and controlling a variety of devices and energy systems from different manufacturers.

[0367] • Security in the Transmission of Signals: Risks of interference or unauthorized access that compromise the control of devices.

[0368] The Control and Action Module (CAM) not only acts on connected devices, but also dynamically adjusts its decisions based on feedback received from the Intelligent Analysis and Processing Module (IAPM) in real time. This adaptive cycle ensures that each adjusted device is optimised according to consumption needs, changes in energy prices, or climatic variations, maximizing efficiency and reducing costs. o Key features

[0369] 1 . Device Automation

[0370] CAM controls and manages physical devices in real time:

[0371] • Controlled Devices: o Smart Thermostats: Automatic temperature adjustment according to conditions and preferences. o Lighting Systems: Lighting control based on occupancy, natural light and schedules. o Electric Vehicle Chargers: Optimization of charging schedules to take advantage of low rates and renewable energy. o Distributed Generation Systems: Management of solar panels, wind turbines and energy storage.

[0372] • Execution of Optimised Instructions: o It receives instructions from the IAPM (101 ) and translates them into commands for devices. o Adjust settings in real-time to maximize efficiency and reduce costs.

[0373] • Interoperability and Standard Protocols: o It supports protocols such as Zigbee, Z-Wave, Modbus, BACnet, KNX. o Use APIs and SDKs provided by manufacturers to integrate proprietary devices. o Implements OPC UA (OLE for Process Control Unified Architecture) for interoperability in industrial systems.

[0374] Technical Problem Solved: CAM overcomes the lack of effective automation by directly connecting optimised decisions with physical actions, enabling autonomous and efficient energy management.

[0375] 2. Real-time event response

[0376] The CAM is designed to react immediately to changes in the energy environment:

[0377] • Continuous Monitoring: o Receive up-to-date data from the IAPM (101 ) on energy conditions, prices, weather, and demand.

[0378] • Dynamic Settings: o Modify the operation of devices to adapt to:

[0379] ■ Variations in Energy Prices: Adjust consumption to take advantage of lower rates.

[0380] ■ Climate Changes: Modifies HVAC systems in response to variations in temperature or climate.

[0381] ■ Consumption Alerts: Reduce or redistribute load to avoid peaks in demand.

[0382] Real-Time Control Algorithms: o It uses Model-Based Predictive Control (MPC) techniques. o Implements Neural Networks and Fuzzy Algorithms for adaptive decisions.

[0383] Technical Problem Solved: The inability to respond in real time is solved by allowing immediate adjustments that optimise consumption and protect systems against sudden changes.

[0384] 3. Secure Communication Protocols

[0385] Security in communication between the CAM and the devices is a priority:

[0386] • Safe Protocols: o TLS (Transport Layer Security): Encrypts communications to ensure confidentiality and integrity. o MQTT with OAuth 2.0 Authentication: Lightweight protocol for loT with authentication and authorization mechanisms. o SNMPv3: Secure protocol for active monitoring.

[0387] • Integration with STS (110): o Identity and Access Management: Verifies device and user identities. o Traceability: Records all actions on a private blockchain for auditing and compliance.

[0388] • Interference Prevention: o Implements Anti-Jamming Measures and Intrusion Detection in wireless networks. o Use Digital Signatures to ensure that commands come from authorized sources.

[0389] Technical Problem Solved: The reliability and security in the transmission of control signals is guaranteed, avoiding unauthorized access and possible external threats.

[0390] 9. SECURITY AND TRANSACTIONS SYSTEM (STS) (110)

[0391] The STS (110) is critical to ensuring the safety, integrity, and regulatory compliance of the energy management system. It is crucial to detail its components, technologies used, and how it interacts with other modules to strengthen its inventability. Blockchain integration not only provides an immutable record of energy transactions, but also allows for the implementation of granular governance mechanisms for the management of tokenized data. This ensures that both users and external entities can interact with energy data in a transparent and controlled manner, managing access permissions through smart contracts. In addition, the system has proactive security measures such as real-time auditing of all interactions with energy data, ensuring constant monitoring of compliance with international data protection regulations. o Technical Problem Solved

[0392] Traditional energy systems face risks such as:

[0393] • Security Vulnerabilities: Exposure to cyberattacks and unauthorized access to sensitive data.

[0394] • Lack of Regulatory Compliance: Failure to comply with regulations such as the GDPR, which can result in penalties.

[0395] • Difficulty in Traceability: Lack of immutable records that allow auditing transactions and events.

[0396] The STS (110) addresses these issues by implementing robust security measures and advanced traceability mechanisms. The use of blockchain ensures that every access to data is automatically audited, guaranteeing an immutable and traceable record of all transactions. This integration allows both users and external entities to operate in an environment of total trust and security. o Components and Functionalities:

[0397] 1 . Security Architecture: o Firewalls and Intrusion Detection Systems (IDS): Implementation of advanced firewalls and IDS systems to monitor and protect network traffic against external threats. o Data Encryption: Use of robust encryption protocols such as AES- 256 to protect data at rest and in transit.

[0398] 2. Advanced Security Algorithms: o Biometric Authentication: Integration of biometric authentication methods (such as facial recognition or fingerprints) to improve access security. o Machine Learning for Threat Detection: Employing machine learning algorithms to identify and respond to suspicious behavior patterns in real time.

[0399] 3. Identity and Access Management: o Identity Federation: Implementation of standards such as SAML or OpenlD Connect to facilitate identity management across multiple domains. o Dynamic Access Policies: Use of context-based policies that adjust access permissions based on factors such as location, time of day, and device type.

[0400] 4. Audit and Traceability: o Detailed Log Logging: Storage of detailed logs of all transactions and accesses, facilitating internal and external audits. o Forensics: Integrated tools to perform forensic analysis in the event of security incidents, enabling rapid identification and mitigation of vulnerabilities. o Key features

[0401] ■ Blockchain Technologies

[0402] • Immutable Ledger: Uses private blockchain with technologies such as Hyperledger Fabric.

[0403] • Smart Contracts: Automate access policies and conditions of use using smart contracts.

[0404] • Consensus Mechanisms: Ensure that all transactions are validated by authorized nodes.

[0405] Technical Problem Solved: Provides immutable and transparent traceability of all interactions and transactions, increasing trust in the system.

[0406] Identity and Access Management

[0407] Role-Based Access Control (RBAC): Defines granular permissions for users and systems. • Multi-Factor Authentication (MFA): Adds additional layers of security for access to sensitive data.

[0408] • Certificate and Key Management: Uses public key infrastructure (PKI) to secure communications.

[0409] Technical Issue Solved: Protects against unauthorized access and ensures that only legitimate users interact with the system.

[0410] ■ Compliance

[0411] • GDPR and Privacy Laws: Implement policies and procedures to comply with international regulations.

[0412] • Audits and Reports: Generate detailed records to demonstrate compliance with authorities.

[0413] • ISO 27001 : Follows internationally recognized information security standards.

[0414] Technical Problem Solved: Ensures that the system operates within the legal framework, avoiding penalties and protecting the rights of users.

[0415] 10. RESILIENCE AND CONTINUITY MODULE (RCM) (108)

[0416] RCM (108) ensures operational availability and data integrity, even in situations of high demand or system failures, ensuring that the system remains operational and reliable. o Technical Problem Solved

[0417] Traditional energy systems can suffer:

[0418] • Service Interruptions: Due to failures in critical components or overloads.

[0419] • Data Loss: Due to storage errors or catastrophic events.

[0420] • Slow Recovery: Difficulty in restoring operations after a failure.

[0421] The RCM (108) addresses these issues by implementing advanced resilience and recovery strategies. o Key features

[0422] Data Replication • Distributed Storage: Uses both relational and non-relational databases to replicate data across multiple nodes.

[0423] • Real-Time Synchronization: Ensures that all data copies are up to date.

[0424] • Data Loss Prevention: Ensures that information is protected against individual failures.

[0425] Technical Problem Solved: Prevents data loss and ensures continuous availability.

[0426] ■ Load Balancing and High Availability

[0427] • Microservices Architecture: Distributes functions into independent services to improve fault tolerance.

[0428] • Container Orchestration: Automatically manages resource distribution and scaling.

[0429] • Node redundancy: Ensures that backup components are ready to take on loads in the event of failures.

[0430] Technical Problem Solved: Maintains system performance and availability even under high demand or failures.

[0431] ■ Disaster Recovery

[0432] • Automated Recovery Plans: Predefined procedures to restore operations quickly.

[0433] • Proactive Monitoring: Use tools like Prometheus to detect and respond to incidents.

[0434] • Regular Testing: Failure simulations to ensure the effectiveness of recovery plans.

[0435] Technical Problem Solved: Minimizes downtime and the impact of catastrophic events.

[0436] 11 . SUPERVISION AND TECHNOLOGICAL OPTIMIZATION MODULE (STOM)

[0437] (109)

[0438] The STOM (109) is an essential component of the system that is responsible for the continuous monitoring and technological optimization of all automated operations and technologies used in energy management. The STOM (109) ensures that the system not only operates efficiently, but also constantly evolves to adapt to new technologies and improve its operational performance. o Technical Problem Solved

[0439] Traditional systems face:

[0440] • Technological Obsolescence: Lack of adaptation to new technologies and methodologies.

[0441] • Operational Inefficiencies: Processes that are not optimised over time, affecting performance.

[0442] • Lack of Visibility: Difficulty identifying areas for improvement or emerging problems.

[0443] STOM (109) addresses these issues through continuous monitoring and proactive planning. o Key features

[0444] ■ Real-Time Monitoring

[0445] • Monitoring Tools: Employs specialized data visualization and analysis libraries to monitor key system metrics, such as module performance, resource usage, and energy efficiency. These libraries allow the creation of personalized dashboards, interactive graphs and detailed reports that facilitate the interpretation and analysis of energy information.

[0446] • Performance Analysis: Evaluates the efficiency of the processes and technologies implemented through the continuous monitoring of performance indicators (KPIs). This analysis allows us to identify areas for improvement, optimise the operation of the modules and ensure that the system operates within the established parameters.

[0447] • Inefficiency Detection: Identifies bottlenecks and areas that require optimization through real-time data analysis. It uses advanced data analysis techniques to detect unusual patterns and propose adjustments that improve the operational efficiency of the system.

[0448] Technical Problem Solved: Provides complete visibility of the system, improving its performance and allowing for more efficient and effective energy management.

[0449] Continuous Technology Optimization • Technology Assessment: Analyzes the effectiveness of the tools and technologies implemented through periodic reviews and performance evaluations. This analysis ensures that the system adopts the most advanced and appropriate solutions to maintain its competitiveness and efficiency.

[0450] • Proactive Update: Proactively implement improvements and adopt new emerging technologies. This includes the integration of technological innovations that optimise the performance of the system and expand its functional capabilities.

[0451] • Strategic Planning: Develops and maintains a technological roadmap based on data and market trends. This strategic planning guides the future development of the system towards efficiency, sustainability and adaptability objectives, ensuring that the system remains aligned with the changing needs of the energy sector.

[0452] Technical Problem Solved: Avoids technological obsolescence and ensures that the system takes advantage of the best available technologies, maintaining its competitiveness and effectiveness in the long term.

[0453] ■ Automated Task Management

[0454] • Process Optimization: Adjusts and improves automated tasks to maximize operational efficiency. This includes automating workflows that reduce execution times, minimize human error, and optimise resource usage.

[0455] • Machine Learning: Uses algorithms that learn and improve over time, allowing automated tasks to continuously adapt to changing system conditions and user needs. This machine learning makes it easier to identify patterns and predict future behaviors, improving the system's ability to respond proactively.

[0456] • Coordination with Other Modules: Ensures that optimizations are implemented consistently across the system. This facilitates integration and synergy between the different modules, allowing unified and efficient energy management that responds comprehensively to the needs of the user and the energy environment. Technical Problem Solved: Improves the operational efficiency and quality of automated tasks, reducing the need for manual intervention and increasing the system's ability to dynamically adapt to power conditions.

[0457] The described system introduces a new standard in comprehensive energy management, capable of learning and dynamically adjusting to the changing conditions of the energy environment. Its proactive adaptability and user-centric approach solve specific technical problems in ways not evident in today's prior art, representing a significant breakthrough in the field of energy management and establishing a new paradigm for smart and adaptive energy solutions.

[0458] A detailed example of realization is shown below through figures 1 to 6.

[0459] Figure 1 represents the overall architecture of the system, highlighting the different levels of energy management from an individual user to an energy community. The figure illustrates how the Tokenized Energy Profile (TEP) (100) is positioned as the core of the system, storing heterogeneous energy data from each user. The TEP (100) acts as a dynamic repository, powered by devices connected via the Control and Action Module (CAM) (104).

[0460] In Figure 1 the lines connecting the elements: HDMA (105) with RCM (108), STOM (109) with RCM (108) and STS (110) with TEP (100), IAPM (101 ), Ul (103), DIPM (106), IDP (107), RCM (108) and STOM (109) represent the safety and monitoring functions. HDMA (105), STOM (109), and STS (110) modules and connections are responsible for system monitoring, security, and regulatory compliance and ensure data integrity, traceability, and security throughout the system.

[0461] On the other hand, the lines connecting the TEP elements (100) with CAM (104), IAPM (101 ), DIPM (106), IDP (107) and STOM (109), CAM (104) with IAPM (101 ), DIPM (106), IDP (107) and STOM (109) and IAPM (101 ) with DIPM (106), IDP (107) and STOM (109) represent data processing and optimization functions. The IAPM (101 ), DIPM (106) and IDP (107) modules and the aforementioned connections allow the collection, preprocessing, analysis, and optimization of energy data. These modules allow the processing of data flows, performing advanced analyses and optimizing energy consumption and generation.

[0462] Finally, the lines connecting the UIM (102) elements with IAPM (101 ), III (103), CAM (104), and TEP (100) with UIM (102) and Ul (103) represent user interaction and control functions. The UIM (102), Ul (103), and CAM (104) modules interact with the user, manage power preferences, and control system actions in real time. These modules manage user feedback, visualization data, and the execution of energy management strategies.

[0463] Level zero is defined as the fundamental layer that stores and manages personalized energy data of users through the Tokenized Energy Profile (TEP), which is used for the analysis, optimization and automation of the system. It interacts directly with the user, providing an energetic profile that powers all subsequent operations.

[0464] Level 1 is determined to be the layer that processes the basic energy data. The IAPM module (101 ) analyzes the PET data (100) and generates recommendations. The UIM (102) facilitates interaction, while the CAM (104) automates energy-saving actions based on system recommendations. These modules transform raw data into actionable insights.

[0465] Modules that operate across multiple layers of the system, facilitating data flow, communication, and optimization between levels 1 and 2, are determined as part of an intermediate level. These modules are HDMA (105) and STOM (109) and ensure a smooth interaction between core data processing operations and external integrations, technology upgrades, and system resiliency. They enable real-time adjustments and continuous improvement of system performance on both short-term and long-term targets.

[0466] Level 2 is defined as the layer that allows technological optimization, the integration of external data and the resilience of the system. The HDMA module (105) ensures distributed data flow between modules, the DIPM (106) provides external data sources, the STOM (109) optimises performance and resiliency.

[0467] Also at this level are the IDP (107) and RCM (108) modules.

[0468] Level 3 is defined as the layer containing the STS module (110) which manages the security and compliance of the system, ensuring that data flows securely and complies with regulatory standards. Monitor interactions between modules, protecting sensitive data and safeguarding the entire ecosystem.

[0469] Figure 1 also shows the TEP's ability (100) to manage data in real time, combining a scalable hybrid architecture, which solves the technical problem of data centralization in traditional systems, ensuring greater flexibility and security.

[0470] Figure 2 presents a detailed diagram of the flow of data within the system. Here we can see the interactions between the Data Ingestion and Preprocessing Module (DIPM) (106), which is responsible for capturing, normalizing and enriching energy data from various sources, and processing modules such as IAPM (101 ).

[0471] The diagram shown in Figure 2 highlights how the data, once processed, is sent to the CAM (104) to execute automatic adjustments in real time on the connected devices, thus ensuring an efficient response to fluctuations in demand or energy prices. It can also be seen how the system uses this data to continuously update the TEP (100), adjusting energy management to the user's preferences.

[0472] More specifically, this use case describes the process of creating a tokenized energy profile (TEP) (100) of new users within the adaptive energy management system. It encompasses user onboarding, identity verification, data collection from various energy-related devices, personalization of energy preferences, and establishing a secure and comprehensive energy profile.

[0473] This profile allows for optimised energy management tailored to the user's specific needs, behaviors, and preferences.

[0474] Thanks to the system of invention, the following advantages are obtained: 1. User registration and authentication: Using the UIM (102) and IDP (107) modules, new users are securely registered and verified with their identities. This ensures that only authenticated users can create and manage their TEPs.

[0475] 2. Seamless data capture and pre-processing: Using the DIPM module (106) it captures and pre-processes data from various sources, including smart meters and loT sensors, ensuring secure, high-quality data transmission to the tokenized energy profile (TEP) (100).

[0476] 3. User interaction and preference settings: Using the UIM (102), users enter their preferences and energy goals. These preferences are incorporated into the TEP (100), allowing the system to generate customized energy optimization strategies using the IAPM module (101 ).

[0477] 4. Robust data protection: Using the STS module (110) it ensures that all data interactions are secure and comply with regulatory standards. The RCM module (108) maintains system availability and data integrity, even during high demand or failures.

[0478] The system's ability to capture and process heterogeneous data in real-time allows for adaptive optimization that is not evident in conventional systems. This improves accuracy and speed in energy decision-making.

[0479] Figure 3 shows the user's interaction with the system through the User Interaction Module (UIM) (102). Thus, the system allows the personalization of energy consumption through intuitive user interfaces, both on mobile devices and on web platforms. The user can configure their energy preferences, such as savings priorities or maximizing the use of renewable energies.

[0480] The UIM (102), through the use of intelligent agents and chatbots, facilitates two- way communication, adjusting the system's recommendations based on the user's behavior and habits. In addition, it shows how the system feeds back the data received to improve its predictive and adaptive capacity in the long term. This use case, in particular, describes how the adaptive energy management system integrates and optimises energy consumption and generation in a smart home. By capturing real-time data from loT sensors, solar panels, and smart meters, the system personalizes the user experience, executes automated actions to improve energy efficiency, and ensures safety and regulatory compliance through automated action monitoring and authorization.

[0481] Thanks to the system of invention, the following advantages are obtained:

[0482] 1. Real-time data processing: The system captures data from loT sensors, smart meters, and solar panels in real-time, allowing for immediate energy adjustments and battery storage management.

[0483] 2. User Interaction and Customization: The UIM module (102) allows owners to easily monitor energy consumption and generation, while providing realtime control over energy preferences, such as when to prioritize battery usage or grid dependency.

[0484] 3. Autonomous optimization: By using the IAPM module (101 ) and the CAM module (104), the system autonomously adjusts consumption based on energy availability, user preferences, and cost-effectiveness.

[0485] 4. Security and compliance: STS (110) and STOM (109) ensure that automated actions, such as connecting or disconnecting to the network, are executed securely and compliant.

[0486] 5. Scalability: HDMA (105) allows the system to seamlessly adapt to larger homes with more energy sources (e.g., solar panels or electric vehicles) without sacrificing efficiency or safety.

[0487] The personalization of energy recommendations based on historical data and user preferences introduces hyper-personalized energy optimization that is not present in traditional systems, improving efficiency and user satisfaction.

[0488] Figure 4 depicts the integration of the system with a Smart Grid, highlighting the system's ability to optimise energy consumption in response to external signals. The figure details how CAM (104) dynamically adjusts devices such as smart thermostats, EV chargers, and distributed generation systems (e.g., solar panels), based on dynamic electricity prices and the availability of renewable energy on the grid.

[0489] This scheme highlights the interoperability of the system with grid operators, allowing for active participation in the stability and efficiency of the electricity grid as a whole.

[0490] This particular use case, the system focuses on managing and optimizing energy usage within a data center environment. Given the critical nature of uptime, the system addresses cooling management, energy consumption, and load balancing, while integrating renewables to minimize operating costs and environmental impact.

[0491] Thanks to the system of invention, the following advantages are obtained:

[0492] 1. Load balancing and predictive analytics: The IAPM (101 ) module uses predictive load analytics to forecast power demand peaks, ensuring preemptive optimization of cooling and power distribution between servers.

[0493] 2. Critical Power Management: The CAM module (104) manages real-time actions to reduce power consumption by regulating cooling systems and redirecting power distribution as needed to critical workloads.

[0494] 3. High availability and resiliency: The RCM module (108) ensures that energy-critical operations remain uninterrupted through data replication and load balancing through the HDMA architecture (105).

[0495] 4. Administrator customization: Administrators can customize power and cooling priorities through the UIM module (102), and the system automatically applies those settings for maximum energy efficiency.

[0496] 5. Security: STS (110) enforces security policies that ensure that power consumption actions, such as load shedding or redistribution, comply with data center protocols. Interoperability with smart grids allows the system to not only receive price and demand signals, but also respond in real-time to critical events in the grid, such as demand peaks or fluctuations in the supply of renewable energy.

[0497] The CAM (104), in conjunction with the IAPM (101 ), is responsible for adjusting the operation of key devices, such as HVAC systems, electric vehicle chargers, and distributed generation sources, ensuring that the system remains aligned with the objectives of energy efficiency and grid stability. This level of integration solves one of the key problems of traditional systems, which do not have the ability to adapt in real time.

[0498] The system's ability to interface with smart grids and optimise energy consumption based on external signals introduces an innovation in the way users can participate in the stability and efficiency of the power grid.

[0499] Figure 5 shows a use case focused on participation in Demand Response programs. The grid-connected system automatically adjusts energy consumption based on grid incentives, such as lower rates at off-peak times.

[0500] It is observed how the IAPM (101 ) analyzes historical consumption patterns and predicts the best strategy to reduce costs or maximize the use of renewable energies. Participation in demand-side programmes responds to the system's ability to optimise the use of resources autonomously, both at the individual and community levels.

[0501] This particular use case focuses on how the system integrates with a smart grid to participate in demand response programs. Homes and commercial buildings can dynamically adjust their energy consumption based on real-time signals from the grid to optimise both cost savings and grid stability.

[0502] Thanks to the system of invention, the following advantages are obtained:

[0503] 1. Demand response flexibility: The system's real-time communication with the smart grid via HDMA architecture (105) allows it to quickly adapt to fluctuations in energy prices or changes in supply and demand, effectively optimizing both grid performance and household energy costs.

[0504] 2. Dynamic Consumer Control: Through the UIM module (102), users can accept or modify the recommendations of the automated system to adjust their energy consumption during periods of peak demand. Preferences are seamlessly integrated into the Tokenized Energy Profile (TEP) (100) to improve future responses.

[0505] 3. Automated network participation: Using signals processed by the IAPM module (101 ), the system autonomously reduces or increases the load based on network demands, without sacrificing user comfort or system efficiency.

[0506] 4. Security and compliance in interaction with the grid: The STS (110) ensures that the data exchanged between the smart grid and the home energy systems is processed and verified securely and complies with regulatory standards, ensuring safe participation in the grid.

[0507] 5. Long-term adaptation: System integration with the grid allows you to forecast and prepare for future demand response events through historical data analysis, ensuring better load management for future scenarios.

[0508] The system allows users to participate in demand response programs autonomously, which solves the technical problem of the lack of capacity of traditional systems to dynamically adapt to external incentives.

[0509] Figure 6 details the transition from custom energy models (PEWM) to a general energy model (GEWM). It shows how the Tokenized Energy Profiles of individual users are grouped into families of energy fingerprints, which allows generating a macro view of collective energy behavior.

[0510] This scheme is essential to enable the global optimisation of entire energy networks, facilitating planning at the level of energy communities and smart grids, and enabling advanced predictive analytics that benefit both individual users and grid operators. The flow of information from the individual Tokenized Energy Profiles (TEPs) to the overall energy model (GEWM) occurs through a multi-level aggregation of data. The individual data of each user or entity is organized into families of energy footprints that group similar profiles.

[0511] This structure allows the system to obtain a global view of energy behaviour, facilitating planning and prediction at the community level. Each TEP directly contributes to the creation of a large-scale predictive and collaborative model, enabling more accurate and effective optimization of entire energy networks.

[0512] Figure 6 shows how the PEWMs (111 ), which represent individual energy profiles (A-F), combine to form the GEWM (114). Each PEWM reflects the energy interactions and assets of a single user, such as solar panels, factories, and vehicles. The Energy Fingerprints (112) illustrate different energy profiles, which are grouped into Energy Fingerprint Families (113) based on shared characteristics. When these custom models are aggregated, they create the GEWM (114), which provides a broader understanding of collective energy use and optimization among users.

[0513] The creation of collective energy models based on tokenized profiles allows for advanced simulation and optimization of entire energy networks, something that is not possible in traditional individualized energy management approaches.

Claims

1. CLAIMS1. Adaptive energy management system based on the use of nodes in a distribution network, called tokenized energy profiles (TEPs), and comprising:- a data ingestion module configured to acquire and aggregate structured and unstructured data in real-time and to encrypt the data;- a real-time intelligent analysis module based on the use of neural networks and configured to detect patterns of energy consumption and generation, to classify such patterns according to specific characteristics, generating energy footprints associated with a user, to predict future consumption or generation values and to obtain real-time optimization actions through a multivariate analysis between the patterns obtained and historical data, environmental and user behavior;- an automated control and activation module configured to control elements of electricity generation and consumption in an automated way by translating instructions obtained from the intelligent analysis module into commands, and the implementation of model-based predictive control (MPC) techniques and fuzzy algorithms for automated decision-making; and- a security module configured to encrypt communications between system modules by incorporating communications encryption techniques, rolebased access control (RBAC), storage of actions on blockchain, and realtime monitoring of anomalies to detect intrusions.

2. Adaptive energy management system in accordance with claim 1 , where the data ingestion module is configured to obtain data from selected data sources from: loT sensors, smart meters, historical records, environmental data, and user behavior data.

3. Adaptive energy management system according to claim 1 , where structured data is processed by compression algorithms that make use of unsupervised autoencoder-type neural networks and stored in distributed databases and unstructured data is processed using machine learning techniques performing stages of classification, filtering and extraction ofrelevant features using natural language processing (NLP) techniques and convolutional neural networks (CNNs).

4. Adaptive energy management system in accordance with claim 1 , where the data ingestion module is configured to pre-possess the data, structured and unstructured, applying stages of format standardization, correction of inconsistencies, elimination of duplicates, incorporation of geolocation, temporal and / or categorization semantic data and applying machine learning techniques for the detection of anomalies and inconsistent patterns.

5. Adaptive energy management system in accordance with claim 1 , where the intelligent analysis module makes use of clustering algorithms, K-means type for pattern detection and DBScan for the detection of atypical behaviors, classification algorithms, decision tree type for categorizing elements and vector support machines (SVM) to increase classification accuracy, and linear or nonlinear regression algorithms to predict consumption or generation values.

6. Adaptive energy management system according to claim 1 , where the intelligent analysis module makes use of algorithms to predict consumption or generation values such as ARIMA, to forecast trends, Prophet to incorporate seasonality and trend considerations, Long Short-Term Memory (LSTM) algorithms to capture long-term dependencies, and convolutional neural networks (CNNs) for spatial data analysis and optimization of patterns of consumption.

7. Adaptive energy management system in accordance with claim 1 , where the intelligent analysis module is configured to perform proactive optimization and efficient planning by predicting energy demand, for which it makes use of stochastic, genetic-type and simulated annealing optimization algorithms, to avoid local minimums, and deep reinforcement learning algorithms, that trains intelligent agents for automated, reward-based decision-making.

8. Adaptive energy management system in accordance with claim 1 , where the intelligent analysis module is configured to detect anomalies by usingunsupervised autoencoder-type neural networks and isolation forest algorithms for the identification of outliers.

9. Adaptive energy management system in accordance with claim 1 , which further comprises a user interaction module comprising: intelligent agents making use of multimodal language models (LLMs), natural language processing (NLP) algorithms and machine learning algorithms to make proactive notifications based on predictive analytics and to adapt to user preferences.

10. Adaptive energy management system in accordance with claim 1 , which further comprises an interface module configured to provide data in a user- understandable format by updating it in real time with the data received by the data ingestion module and with the analysis performed by the intelligent analysis module.

11. An adaptive energy management system in accordance with claim 1 , which further comprises an integration and development module configured to connect with external applications and devices, which implements standard APIs to ensure compatibility and common communication protocols.

12. Adaptive energy management system in accordance with claim 1 , where the security module makes use of machine learning algorithms for threat detection, biometric authentication systems, dynamic access policies, detailed log logging on blockchain, smart contracts, and consensus mechanisms to validate transactions, forensics, digital signatures, and real-time access permission management.

13. Adaptive energy management system in accordance with claim 1 , which further comprises a resilience and continuity module configured to implement distribution network nodes in a microservices architecture orchestrated by a distributed system for resource distribution and scaling and for replication and automatic recovery in case of failure.

14. Adaptive energy management system in accordance with claim 1 , which also comprises a technology monitoring and optimization module configured tomonitor, optimise and automate the application of optimization actions, which makes use of performance analysis and inefficiency detection algorithms, algorithms for evaluating the technology used and proactively updating, and process optimization automation algorithms using machine learning.

15. An adaptive energy management method based on the use of nodes in a distribution network, called tokenized energy profiles (TEPs), which includes the stages of:- data ingestion: acquiring and aggregating structured and unstructured data in real time, ensuring data encryption;- Intelligent real-time analysis: using neural networks to detect patterns of energy consumption and generation, to classify these patterns according to specific characteristics, generating energy footprints associated with a user, to predict future consumption or generation values and to obtain real-time optimization actions through a multivariate analysis between the patterns obtained and historical data, environmental and user behavior;- automated control and activation: controlling elements of electricity generation and consumption in an automated way by translating instructions obtained from the intelligent analysis module into commands, implementing model-based predictive control (MPC) techniques and using fuzzy algorithms for automated decision-making; and- Implementation of security mechanisms: encrypting communications between system modules by incorporating encryption techniques, rolebased access control (RBAC), storage of actions on blockchain, and realtime monitoring of anomalies to detect intrusions.

Images