Method and system for monitoring energy consumption of user equipment (UE) in real-time

Abstract

The disclosure relates to a method (600) and system (108) for monitoring energy consumption of user equipment (UE) (104) in real-time. The method (600) involves collecting (602), by a monitoring unit, real-time network data corresponding to one or more network parameters from one or more data sources. The method (600) further involves collecting (604) energy utilization data under different network conditions from the UE (104). The method (600) includes generating (606), by a processing unit, an energy consumption pattern using an AI / ML model. The processing unit determines (608) energy consumption information and evaluates (610) whether abnormal energy consumption exists by comparing with predefined thresholds. The method (600) includes identifying (612) one or more potential issues and displaying (614), by a display unit, the issues on at least one electronic device. The processing unit communicates (616) recommendations to the UE (104) for corrective measures.

Description

METHOD AND SYSTEM FOR MONITORING ENERGY CONSUMPTION OF USER EQUIPMENT (UE) IN REAL-TIMERESERVATION OF RIGHTS

[0001] A portion of the disclosure of this patent document contains material, which is subject to intellectual property rights such as, but are not limited to, copyright, design, trademark, Integrated Circuit (IC) layout design, and / or trade dress protection, belonging to Jio Platforms Limited or its affiliates (hereinafter referred as owner). The owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all rights whatsoever. All rights to such intellectual property are fully reserved by the owner.TECHNICAL FIELD

[0002] The present disclosure relates to a field of telecommunications network. In particular, the present disclosure relates to a method and a system for monitoring energy consumption of user equipment (UE) in real-time.DEFINITION

[0003] As used in the present disclosure, the following terms are generally intended to have the meaning as set forth below, except to the extent that the context in which they are used to indicate otherwise.

[0004] The term ‘Machine Learning (ML) model’ as used herein in the specification refers to a mathematical representation or algorithm that is trained using data to make predictions, classifications, or decisions without being explicitly programmed for specific tasks. The ML model is designed to learn patterns, relationships, and trends from a given dataset and use this knowledge to generalize and make predictions on new, unseen data.

[0005] The term ‘Radio Access Network (RAN)’ as used herein in the specification refers to a component of telecommunications systems that connects user Equipments (UEs) (like smartphones, tablets, loT devices) to a core network.The RAN primarily handles the wireless communication between the UEs and the network infrastructure, enabling data transmission and reception.

[0006] The term ‘Fifth Generation (5G) core network’ as used herein in the specification refers to a 5G core that manages the control and data planes, providing connectivity, mobility management, and the delivery of services to users. The 5G core (5GC) is built on a cloud-native architecture, offering significant advancements over previous generations in terms of flexibility, scalability, and support for diverse applications such as loT, enhanced mobile broadband (eMBB), ultra-reliable low-latency communication (URLLC), and massive machine-type communication (mMTC).

[0007] The term ‘signalling overhead’ as used herein in the specification refers to an additional network resources, data traffic, and time consumed by control and management messages that do not directly carry user data but are necessary for the operation, coordination, and maintenance of a network. The signalling overhead is a critical aspect that can impact network efficiency, latency, and overall performance.

[0008] The term ‘Signal strength’ as used herein in the specification refers to a measure of the power level that a radio signal has at a specific point, typically at the receiving end, such as a UE in a telecommunications network. The signal strength indicates how strong or weak a signal is and directly affects the quality of communication, data transmission speed, and connectivity reliability.

[0009] The term ‘frequency band’ as used herein in the specification refers to a specific range of electromagnetic spectrum frequencies used for transmitting signals in telecommunications and broadcasting. Each frequency band is defined by its lower and upper frequency limits and is allocated for specific types of communication, such as cellular networks, radio, television broadcasting, satellite communication, and Wi-Fi.

[0010] The term ‘Uplink (UL) / Downlink (DL) traffic’ as used herein in thespecification refers to uplink (UL) and downlink (DL) traffic in a telecommunications network, describing the direction in which data is transmitted between the UE and the network.

[0011] The term ‘Throughput’ as used herein in the specification refers to an amount of data successfully transmitted from one point to another within a specific time period in a network or communication system. The throughput is a key performance indicator that measures the efficiency of data transfer in terms of bits per second (bps), commonly expressed in megabits per second (Mbps) or gigabits per second (Gbps).

[0012] The term ‘Handover’ as used herein in the specification refers to a process of transferring an ongoing call or data session from one cell tower or base station to another without interruption. The handover ensures continuous service as a mobile device moves through different coverage areas.

[0013] These definitions are in addition to those expressed in the art.BACKGROUND

[0014] The following description of related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section be used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of prior art.

[0015] Fifth Generation (5G) and upcoming Sixth Generation (6G) wireless communication systems have introduced transformative capabilities in telecommunications, including enhanced mobile broadband, ultra-reliable low- latency communications, and massive machine-type communications. These advancements have enabled the deployment of a wide range of real-time and high- throughput applications such as augmented reality (AR), virtual reality (VR),industrial automation, remote healthcare, and autonomous transportation systems. To deliver these services, 5G and 6G networks employ advanced radio technologies and operate in higher frequency bands including millimeter wave (mmWave) and terahertz (THz) spectrum, which allow for larger bandwidth allocations and significantly increased data rates.

[0016] While these high-frequency operations offer notable performance benefits, they also lead to increased power requirements at both network infrastructure and user terminal levels. In particular, User Equipment (UE) such as smartphones, tablets, laptops, and loT-enabled devices must operate continuously across wide bandwidths and under varying radio conditions, contributing to substantial energy consumption. The energy demand of UEs is further amplified by advanced signal processing functions, increased antenna arrays, and higher uplink transmission power necessitated by challenging radio propagation characteristics in higher frequency bands.

[0017] Energy consumption by UEs in a 5G / 6G ecosystem is a subject of growing concern. Given the scale of device deployment across global networks, the aggregate energy drawn by end-user terminals constitutes a significant portion of the total energy budget of a wireless communication system. This situation presents multiple challenges including reduction in battery lifespan, frequent device charging cycles, operational inefficiencies, and an adverse impact on the environmental sustainability of the communication sector. The cumulative effect is a notable contribution to the overall carbon footprint of digital infrastructure.

[0018] Existing network management frameworks, although capable of managing Quality of Service (QoS) and traffic scheduling, lack visibility into the fine-grained energy consumption behaviors of individual UEs. In current network architectures, energy-related telemetry at the device level is either unavailable or inaccessible to the network operator. Moreover, the energy usage profile of a UE can vary significantly depending on a multitude of dynamic parameters including radio signal strength, network congestion, service type, frequency band allocation,modulation scheme, device hardware configuration, software stack, and user behavior patterns. Consequently, the absence of actionable insights into these variables limits the ability of network operators to implement targeted energy optimization strategies.

[0019] Some research efforts have focused on introducing energy-efficient communication protocols, power-saving modes, and energy-aware scheduling algorithms. However, these solutions often rely on aggregate statistical models rather than real-time individualized measurements. As a result, they may fail to capture abnormal energy usage patterns or localized inefficiencies specific to certain users, devices, or geographical zones. Additionally, the increasing heterogeneity of end-user devices — each with distinct chipset architectures, battery capacities, and operating systems — further complicates the task of implementing uniform energy-saving strategies.

[0020] From a network planning and optimization perspective, the lack of energy usage data at the UE level also constrains the operator’s ability to detect and rectify systemic inefficiencies. For instance, devices located in areas with poor signal coverage may exhibit disproportionately high energy usage due to elevated transmission power levels required to maintain connectivity. Without visibility into such patterns, network operators cannot effectively deploy solutions such as cell densification, beamforming enhancements, or dynamic spectrum reallocation to alleviate energy drain conditions.

[0021] In view of these technical constraints, there exists a recognized need within the telecommunications domain for improved techniques and frameworks that can facilitate energy-aware network intelligence. Solutions that enable the monitoring, profiling, and analysis of UE energy usage in a scalable and operator- friendly manner are imperative for achieving long-term energy efficiency and sustainability goals in next-generation networks.OBJECTIVES OF THE DISCLOSURE

[0022] Some of the objectives of the present disclosure, which at least one embodiment herein satisfies, are as follows:

[0023] An objective of the present disclosure is to provide a system and a method for monitoring the real-time energy consumption of user equipment (UE) in a network.

[0024] Another objective of the present disclosure is to provide a system and a method that leverages an Artificial Intelligence (AI)ZMachine Learning (ML) model for analyzing energy usage patterns, generating energy consumption patterns, and allowing the identification of inefficiencies in the UE and the network configurations.

[0025] Another objective of the present disclosure is to provide a system and a method that suggests corrective actions based on analyzed energy consumption data, such as optimizing the UE settings, network tuning, and improving radio conditions.

[0026] Another objective of the present disclosure is to provide a system and a method that improves network reliability and performance by identifying and rectifying issues that lead to abnormal energy consumption in the UEs.

[0027] Another objective of the present disclosure is to provide a system and a method that enables the network operators to visualize and analyse energy consumption data on a Graphical User Interface (GUI).

[0028] Another objective of the present disclosure is to provide a system and a method that influences user behaviour by making the users aware of their energy usage patterns and encouraging more sustainable and efficient energy consumption practices.

[0029] Other objectives and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.SUMMARY

[0030] The disclosure relates to a method for monitoring energy consumption of at least one user equipment (UE) in real-time. The method comprises collecting, by a monitoring unit, real-time network data corresponding to one or more network parameters associated with the at least one UE from one or more data sources. The method further comprises collecting, by the monitoring unit, energy utilization data under different network conditions from the at least one UE. Based on the received real-time network data and the energy utilization data, an energy consumption pattern for the at least one UE is generated by a processing unit using an Artificial Intelligence (AI)ZMachine Learning (ML) model. The processing unit then determines an energy consumption information for the at least one UE based on the energy consumption pattern, wherein the energy consumption information comprises at least one value corresponding to each of one or more energy consumption metrics. The method further includes determining, by the processing unit, whether an abnormal energy consumption is detected in the at least one UE based on the energy consumption information and a predefined energy consumption range present for the at least one UE. The method includes identifying, by the processing unit, one or more potential issues leading to the abnormal energy consumption for the at least one UE based on analysis of the energy consumption information. The identified one or more potential issues are displayed, by a display unit, on at least one electronic device, wherein the at least one electronic device is associated with at least one network operator. Finally, the method includes communicating, by the processing unit, recommendations to the at least one UE to perform one or more corrective measures to address the one or more potential issues.

[0031] In one embodiment, the method further comprises training and testing, by a model training unit, the A EM L model using the real-time network data and the energy consumption data to generate a context-aware energy prediction AI / ML model.

[0032] In another embodiment, the step of training, by the model training unit, the AI / ML model to obtain the trained AI / ML model further comprises processing, by the processing unit, the energy utilization data from each UE of the at least one UE, wherein the energy utilization data is collected for each of a plurality of network conditions. The training step further comprises processing, by the processing unit, the real-time network data corresponding to the one or more network parameters for each network condition of the plurality of network conditions. The AI / ML model is trained, by a model training module, for predicting energy consumption pattern for each UE using the processed energy utilization data and the processed real-time network data. The method further comprises applying, by the model training module, the network data to the trained AI / ML model to determine an energy consumption profde corresponding to each UE, and validating, by the model training module, the trained AI / ML model based on the predicted energy consumption pattern obtained for each UE and the energy utilization data collected for the respective UE. Upon successful validation, the trained AI / ML model is provided by the model training module.

[0033] In another embodiment, the method further comprises determining, by the processing unit, the one or more corrective measures for each of the one or more potential issues identified for the at least one UE, wherein the one or more corrective measures are selected based on a mapping between identified energy consumption issues and corresponding corrective actions stored in a database. The method further includes communicating, by the processing unit, the one or more corrective measures to one of the at least one UE.

[0034] In another embodiment, the method further comprises displaying, by the display unit, the energy consumption chart created for the at least one UE.

[0035] In another embodiment, the one or more energy consumption metrics comprises total energy used per session, energy per data volume, energy per frequency band, energy per access type, and energy per UE type.

[0036] In another embodiment, the one or more network parameterscomprises signalling overhead, data transfer rates, access type, session duration, service type, and network slice.

[0037] In another embodiment, the plurality of network conditions comprises frequency band used by the at least one UE, signal strength received at the at least one UE, Signal-to-Noise Ratio (SNR) received at the at least one UE, uplink and / or downlink throughput, handover frequency or events, network congestion level, access type, network slice type, and transmission power of the UE.

[0038] The disclosure further relates to a system for monitoring energy consumption of at least one user equipment (UE) in real-time. The system comprises a memory storing instructions, one or more communication interfaces, and one or more hardware processors coupled to the memory via the one or more communication interfaces. The one or more hardware processors are configured to perform the method as described above.

[0039] The disclosure further relates to a user equipment communicatively coupled to a system, wherein the coupling comprises steps of receiving a connection request, sending an acknowledgment of the connection request to the system, and transmitting data from the user equipment to the system. The system is configured to monitor energy consumption of the user equipment in real-time as described above.

[0040] The disclosure further relates to a computer program product comprising a non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to execute the method for monitoring energy consumption of at least one user equipment (UE) in real-time as described above.BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS

[0041] The accompanying drawings, which are incorporated herein, andconstitute a part of this disclosure, illustrate exemplary embodiments of the disclosed methods and systems in which like reference numerals refer to the same parts throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure of such drawings includes the disclosure of electrical components, electronic components or circuitry commonly used to implement such components.

[0042] FIG. 1 illustrates an exemplary network architecture of a system for monitoring energy consumption of at least one user equipment (UE) in real-time, in accordance with an embodiment of the present disclosure.

[0043] FIG. 2 illustrates an exemplary block diagram of the system, in accordance with an embodiment of the present disclosure.

[0044] FIG. 3 illustrates an exemplary system architecture for monitoring the energy consumption of the UE in a network, in accordance with an embodiment of the present disclosure.

[0045] FIG. 4 illustrates an exemplary flow chart for training an Artificial Intelligence (AI) / machine learning (ML) model to monitor the energy consumption of the UE, in accordance with an embodiment of the present disclosure.

[0046] FIG. 5 illustrates an exemplary flow chart of a method of monitoring the energy consumption of the UE in real-time, in accordance with an embodiment of the present disclosure.

[0047] FIG. 6 illustrates an exemplary flow chart of a method of monitoring the energy consumption of the UE in real-time, in accordance with an embodiment of the present disclosure.

[0048] FIG. 7 illustrates an exemplary computer system in which or withwhich the embodiments of the present disclosure may be implemented.

[0049] The foregoing shall be more apparent from the following detailed description of the disclosure.LIST OF REFERENCE NUMERALS100 - Network architecture102 - User(s)104 -User Equipments (UEs)106 - Network108 - System200 - Block diagram202 - Processor(s)204 - Memory206 -Interface(s)208 - Processing Engine210 - Database300 - System Architecture302 - 5G network core304 - Data collector306 - Management dashboard308 - Artificial Intelligence (AI)ZMachine Learning (ML) Model310 - gNodeB400 - Flow Diagram500 - Flow Diagram600 - Flow Diagram700 -Computer System710 - External Storage Device720 - Bus730 - Main Memory740 - Read Only Memory750 - Mass Storage Device760 - Communication Port770 - ProcessorDETAILED DESCRIPTION

[0050] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address any of the problems discussed above or might address only some of the problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein. Example embodiments of the present disclosure are described below, as illustrated in various drawings inwhich like reference numerals refer to the same parts throughout the different drawings.

[0051] The ensuing description provides exemplary embodiments only, and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.

[0052] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it will be understood by one of ordinary skill in the art that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the embodiments.

[0053] Also, it is noted that individual embodiment may be described as a process that is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination can correspond to a return of the function to the calling function or the main function.

[0054] The word “exemplary” and / or “demonstrative” is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt,the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and / or “demonstrative” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms “includes,” “has,” “contains,” and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive like the term “comprising” as an open transition word without precluding any additional or other elements.

[0055] Reference throughout this specification to “one embodiment” or “an embodiment” or “an instance” or “one instance” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0056] The terminology used herein is to describe particular embodiments only and is not intended to be limiting the disclosure. As used herein, the singular forms “a”, “an”, and “the” are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein, the term “and / or” includes any combinations of one or more of the associated listed items. It should be noted that the terms “mobile device”, “user equipment”, “user device”, “communication device”, “device” and similar terms are used interchangeably for the purpose of describing the invention. These terms are not intended to limit the scope of the invention or imply any specificfunctionality or limitations on the described embodiments. The use of these terms is solely for convenience and clarity of description. The invention is not limited to any particular type of device or equipment, and it should be understood that other equivalent terms or variations thereof may be used interchangeably without departing from the scope of the invention as defined herein.

[0057] As used herein, an “electronic device”, or “portable electronic device”, or “user device” or “communication device” or “user equipment” or “device” refers to any electrical, electronic, electromechanical, and computing device. The user device is capable of receiving and / or transmitting one or parameters, performing function / s, communicating with other user devices, and transmitting data to the other user devices. The user equipment may have a processor, a display, a memory, a battery, and an input-means such as a hard keypad and / or a soft keypad. The user equipment may be capable of operating on any radio access technology including but not limited to IP-enabled communication, Zig Bee, Bluetooth, Bluetooth Low Energy, Near Field Communication, Z-Wave, Wi-Fi, Wi-Fi direct, etc. For instance, the user equipment may include, but not limited to, a mobile phone, smartphone, virtual reality (VR) devices, augmented reality (AR) devices, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, mainframe computer, or any other device as may be obvious to a person skilled in the art for implementation of the features of the present disclosure.

[0058] Further, the user device may also comprise a “processor” or “processing unit” includes processing unit, wherein processor refers to any logic circuitry for processing instructions. The processor may be a general-purpose processor, a special purpose processor, a conventional processor, a digital signal processor, a plurality of microprocessors, one or more microprocessors in association with a Digital Signalling Processing (DSP) core, a controller, a microcontroller, Application Specific Integrated Circuits, Field Programmable Gate Array circuits, any other type of integrated circuits, etc. The processor may perform signal coding data processing, input / output processing, and / or any other functionality that enables the working of the system according to the presentdisclosure. More specifically, the processor is a hardware processor.

[0059] While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment, as well as other embodiments of the disclosure, will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.

[0060] User Equipment (UE) energy consumption monitoring within a network is essential for several reasons. Firstly, the UE energy consumption monitoring supports environmental sustainability by reducing the carbon footprint associated with high energy use, aligning with global efforts to minimize environmental impact. Secondly, the UE energy consumption monitoring ensures network reliability by preventing issues such as overheating and potential failures, thus maintaining consistent and stable network operations. Monitoring energy consumption also provides a significant competitive advantage by enabling the network operators to reduce operational costs, leading to lower service prices or improved service quality, setting them apart in a competitive market. Additionally, the UE energy consumption monitoring fosters technological advancement by identifying opportunities for improvements and innovations in network infrastructure to handle increasing energy demands efficiently. By analyzing energy usage (energy consumption) patterns, the network can identify and diagnose potential issues leading to increased or abnormal energy consumption by the UEs. This analysis enables the network to recommend corrective actions, such as optimizing UE configurations, tuning network parameters, and improving radio conditions to enhance energy efficiency.

[0061] In the context of 5G communication, signal strength and Signal-to-Noise Ratio (SNR) are pivotal factors affecting device power usage. The UE increases its transmission power in response to weak signal strength to sustain a reliable connection. By examining energy consumption patterns in conjunction with UE locations, the network operators may pinpoint users experiencing higher power consumption due to poor signal conditions.

[0062] When the users in specific locations exhibit higher energy usage and degraded signal strength while utilizing 5G / 6G services, the network operator may address these issues by strategically placing and optimizing macro cells. This optimization improves coverage and signal quality, thereby reducing energy consumption.

[0063] Furthermore, by informing the users about their energy consumption patterns, the network may influence and encourage more efficient energy usage behaviours. This awareness may drive the users to adjust their UE usage to be more energy efficient. Additionally, identifying UEs and services that are particularly energy intensive facilitates the implementation of corrective measures to address these inefficiencies.

[0064] The present disclosure provides a comprehensive UE energy usage monitoring and analytics system to address these issues. The present disclosure allows the network to continuously monitor and analyze UE energy consumption in real-time. Through advanced analytics, the present system identifies patterns and anomalies in energy usage (energy consumption), enabling the network to suggest corrective actions. These actions may include optimizing UE configurations to improve energy efficiency, tuning network parameters to balance performance and power consumption, and enhancing radio conditions to reduce the energy required for maintaining connectivity. The network can effectively manage and reduce overall energy usage by leveraging the present system, contributing to greater efficiency and sustainability.

[0065] The present system includes a monitoring platform comprising specialized probes (receiving units) that systematically collect and analyze dataaffecting energy usage energy usage data. These probes are strategically deployed within the network infrastructure to gather comprehensive data on one or more parameters, including but not limited to service usage, frequency band, signal strength, Signal-to-Noise Ratio (SNR), access type, device type, chipset characteristics, activity periods, and network congestion.

[0066] The probes may include a data collection engine that interfaces with the 5G / 6G core network and Radio Access Network (RAN) nodes. The data collection engine aggregates data corresponding to the one or more parameters and streams the aggregated data to an Artificial Intelligence (AI) / machine learning (ML) model for further processing. The data is collected continuously to ensure up- to-date monitoring and analysis.

[0067] The AI / ML engine is configured to predict energy consumption based on the collected data. Before deployment, the AI / ML engine undergoes a rigorous training utilizing historical data (training dataset) collected from a diverse range of UEs and the network conditions. This training dataset is used to accurately refine the ability of the model to predict energy usage (energy consumption) under various scenarios.

[0068] After the training, the AI / ML model is configured to be tested using a test data to validate accuracy and precision of the trained AI / ML engine. This step ensures that the AI / ML engine performs reliably and provides accurate predictions of power consumption.

[0069] The AI / ML engine is configured to generate energy consumption patterns, which may be presented through a Graphical User Interface (GUI) integrated into the system. The GUI allows the network operators to visualize and analyze the energy consumption patterns for individual devices and user scenarios. Through the GUI, the network operators may access detailed insights into UE power usage, which facilitates the application of targeted configurations and planning strategies to reduce overall power consumption.

[0070] The detailed insights derived from the GUI enable the network operators to make informed decisions regarding the network optimization, configuration adjustments, and planning interventions to enhance energy efficiency. The present system thereby supports the objective of minimizing power usage while maintaining optimal network performance and user experience.

[0071] The various embodiments throughout the disclosure will be explained in more detail with reference to FIG. 1- FIG. 7.

[0072] FIG. 1 illustrates an exemplary network architecture 100 of a system 108 for monitoring energy consumption of at least one user equipment (UE) 104 in real-time, in accordance with an embodiment of the present disclosure. As illustrated in FIG. 1 , the network architecture 100 may include one or more User Equipments (UEs) 104-1, 104-2... 104-N associated with one or more users 102-1, 102-2... 102-N in an environment. A person of ordinary skill in the art will understand that one or more users 102-1, 102-2... 102-N may be collectively referred to as the users 102. Similarly, a person of ordinary skill in the art will understand that one or more UEs 104-1, 104-2... 104-N may be collectively referred to as the UE 104 or the UEs 104. Although only three UEs 104 are depicted in FIG. 1, however, any number of the UE 104 may be included without departing from the scope of the ongoing description.

[0073] In an embodiment, the UE 104 may include smart devices operating in a smart environment, for example, an Internet of Things (loT) system. In such an embodiment, the UE 104 may include, but are not limited to, smartphones, smart watches, smart sensors (e.g., a mechanical, a thermal, an electrical, a magnetic, etc.), networked appliances, networked peripheral devices, networked lighting system, communication devices, networked vehicle accessories, networked vehicular devices, smart accessories, tablets, a smart television (TV), computers, a smart security system, a smart home system, other devices for monitoring or interacting with or for the users 102 and / or entities, or any combination thereof. A person of ordinary skill in the art will appreciate that the UE 104 may include, butnot limited to, intelligent, multi-sensing, network-connected devices, that may integrate seamlessly with each other and / or with a central server or a cloudcomputing system or any other device that is network-connected.

[0074] Additionally, in some embodiments, the UE 104 may include, but not limited to, a handheld wireless communication device (e.g., a mobile phone, a smartphone, a phablet device, and so on), awearable computer device (e.g., aheadmounted display computer device, a head-mounted camera device, a wristwatch computer device, and so on), a Global Positioning System (GPS) device, a laptop computer, a tablet computer, or another type of portable computer, a media playing device, a portable gaming system, and / or any other type of computer device with wireless communication capabilities, and the like. In an embodiment, the UE 104 may include, but is not limited to, any electrical, electronic, electromechanical, or equipment, or a combination of one or more of the above devices, such as virtual reality (VR) devices, augmented reality (AR) devices, a laptop, a general-purpose computer, a desktop, a personal digital assistant, a tablet computer, a mainframe computer, or any other computing device. Further, the UE 104 may include one or more in-built or externally coupled accessories including, but not limited to, a visual aid device such as a camera, an audio aid, a microphone, a keyboard, and input devices for receiving input from the user 102 or an entity such as a touchpad, a touch-enabled screen, an electronic pen, and the like. A person of ordinary skill in the art will appreciate that the UE 104 may not be restricted to the mentioned devices and various other devices may be used.

[0075] In FIG. 1, the UE 104 may communicate with system 108 through the network 106 to send or receive various types of data. In an embodiment, the network 106 may include at least one of a 5G network, a 6G network, or the like. The network 106 may enable the UE 104 to communicate with other devices in the network architecture 100 and / or with the system 108. The network 106 may include a wireless card or some other transceiver connection to facilitate this communication. In another embodiment, the network 106 may be implemented as, or include any of a variety of different communication technologies such as a widearea network (WAN), a local area network (LAN), a wireless network, a mobile network, a Virtual Private Network (VPN), the Internet, the Public Switched Telephone Network (PSTN), or the like.

[0076] In an embodiment, the network 106 may include, by way of example but not limitation, at least a portion of one or more networks having one or more nodes that transmit, receive, forward, generate, buffer, store, route, switch, process, or a combination thereof, etc. one or more messages, packets, signals, waves, voltage or current levels, some combination thereof, or so forth. The network 106 may also include, by way of example but not limitation, one or more of, a wireless network, a wired network, an internet, an intranet, a public network, a private network, a packet-switched network, a circuit-switched network, an ad hoc network, an infrastructure network, the PSTN, a cable network, a cellular network, a satellite network, a fiber optic network, or some combination thereof.

[0077] In an embodiment, the UE 104 is communicatively coupled with the network 106. The network 106 may receive a connection request from the UE 104. The network 106 may send an acknowledgment of the connection request to the UE 104. The UE 104 may transmit a plurality of signals in response to the connection request.

[0078] The system 108 is configured to monitor energy consumption of each UE 104 in real-time. For this purpose, the system 108 comprises one or more processors coupled to a memory and communication interfaces. The system 108 is operatively coupled with a monitoring unit that is configured to collect real-time network data corresponding to one or more network parameters affecting energy usage in each UE 104. Examples of such network parameters include signalling overhead, data transfer rates, access type, session duration, service type, and network slice. The real-time network data may be sourced from one or more data sources including the 5G / 6G core network elements, such as Access and Mobility Management Function (AMF), Session Management Function (SMF), and Policy Control Function (PCF), Radio Access Network (RAN) nodes such as gNodeBs, oruser plane elements such as User Plane Function (UPF).

[0079] The monitoring unit is also configured to collect energy utilization data from each UE 104 under a variety of network conditions. Such network conditions may include, for example, the frequency band used by the UE, the signal strength received at the UE, the Signal-to-Noise Ratio (SNR) at the UE, the uplink or downlink throughput, the number of handover events experienced, the current level of network congestion, the access type used (such as NSA or SA), the network slice type, and the transmission power level of the UE.

[0080] The collected data is processed by a processing unit of the system 108, which utilizes an Artificial Intelligence (Al) or Machine Learning (ML) model to generate an energy consumption pattern for each UE 104. This energy consumption pattern is used to compute an energy consumption information comprising one or more values associated with a plurality of consumption metrics. These consumption metrics include total energy used per session, energy per data volume, energy per frequency band, energy per access type, and energy per UE type. The processing unit further determines whether abnormal energy consumption is detected in a UE 104 by comparing the computed energy consumption information against a predefined energy consumption range stored in a database. Abnormal energy consumption refers to a deviation of the measured or predicted energy usage value for a given metric from the baseline or expected threshold range predefined for that metric, which may be based on UE type, service category, radio condition, or historical usage profile. For example, if the predefined expected energy per data volume for a smartphone under good signal conditions is in the range of 2.0-3.5 mWh / MB, and the detected value is 6.2 mWh / MB, the energy consumption is flagged as abnormal. Such a deviation may indicate conditions such as poor signal quality, network congestion, misconfigured applications, or hardware anomalies.

[0081] In the event of identifying abnormal energy consumption, the processing unit analyses the energy consumption information to identify one or more potential issues causing the abnormal behavior. The one or more potentialissues are displayed on a display unit operatively associated with the system 108. The display unit may be part of an electronic device accessible to the network operator, such as an operator-facing dashboard, or may be the UE 104 itself. The system 108 also generates and communicates recommendations to the affected UE 104 to perform one or more corrective measures that address the identified potential issues.

[0082] The system 108 further includes a model training unit configured to train and test the AUML model based on the collected real-time network data and the energy consumption data. During training, the system processes the energy utilization data from each UE 104 across the plurality of network conditions and correlates it with the real-time network data corresponding to each condition. A model training module is employed to train the AUML model on this data to predict energy consumption patterns. Following training, the trained model is tested by applying the same network data to the model and comparing the predicted energy consumption patterns with the actual energy utilization data collected from the UEs. For example, if the model predicts 25% higher consumption for a UE operating under low SNR and high throughput, and the measured utilization confirms the trend within a predefined error margin, the model is deemed validated. Upon successful validation, the model is stored as a context-aware energy prediction AUML model.

[0083] The system 108 further determines corrective measures by mapping the identified energy consumption issues to predefined corrective actions stored in a database. Such actions may include optimization of network configuration, adjustment of frequency bands, or device-side tuning such as radio module throttling. These corrective measures are communicated to the respective UE 104 for local implementation.

[0084] The display unit also supports visualization of the energy consumption chart for each UE 104, which may be used by network operators for trend analysis and strategic network planning. The energy chart may plot energyper session or consumption per throughput under different conditions and may be generated for individual UEs or groups of UEs in a specific geographical region or cell.

[0085] Although FIG. 1 shows exemplary components of the network architecture 100, in other embodiments, the network architecture 100 may include fewer components, different components, differently arranged components, or additional functional components than depicted in FIG. 1. Additionally, or alternatively, one or more components of the network architecture 100 may perform functions described as being performed by one or more other components of the network architecture 100.

[0086] FIG. 2 illustrates an exemplary block diagram 200 of the system 108, in accordance with an embodiment of the disclosure.

[0087] In an embodiment, the system 108 may include one or more processor(s) 202. The one or more processor(s) 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, or any other suitable computing elements capable of processing input data based on operational instructions. The one or more processor(s) 202 may be configured to execute instructions stored in memory 204 for performing real-time energy monitoring operations for at least one UE. In an implementation, the processor(s) 202 may further perform Al model inference, abnormality detection, and corrective action determination.

[0088] The memory 204 may be configured to store computer-readable instructions in a non-transitory storage medium. These instructions, when executed, enable data retrieval, energy consumption profiling, and interaction with user equipment over the network 106. The memory 204 may comprise volatile memory such as RAM, and non-volatile memory such as flash memory, EEPROM, or other magnetic or optical storage media. The memory 204 may also store intermediate data structures including energy consumption profiles, abnormality logs, and learned parameters of trained AI / ML models.

[0089] In an embodiment, the system 108 may include interface(s) 206. The interface(s) 206 may comprise hardware interfaces, network adapters, device drivers, and other physical or logical pathways for enabling bidirectional communication between the processor(s) 202 and external or internal subsystems. These interface(s) 206 may enable data exchange between the system 108 and one or more UEs 104 or data sources such as network functions, 5G / 6G core elements (e.g., AMF, SMF, PCF), and RAN nodes (e.g., gNodeBs). The interface(s) 206 may also facilitate communication with telemetry aggregators, logging systems, and visualization dashboards.

[0090] The system 108 may further include a processing engine 208, which may be implemented using a combination of hardware circuits and executable software logic stored in memory 204. The processing engine 208 is configured to collect, process, analyze, and act upon real-time network data and energy utilization data. The data may be collected from various sources such as 5G / 6G core networks, RAN nodes, network analytics functions, or UE-side telemetry signals. Real-time network data may include signaling overhead, data transfer rates, access type, session duration, service type, and network slice usage. Energy utilization data may be collected for each UE under multiple network conditions such as frequency band used, received signal strength, Signal-to-Noise Ratio (SNR), uplink / downlink throughput, number of handovers, congestion level, transmission power, access type, and slice type.

[0091] The processing engine 208 may include a model training unit for building and optimizing a context-aware AI / ML model used to predict energy consumption behavior. The training and deployment of the AI / ML model may be conducted through the following detailed workflow:

[0092] The processing engine 208 initiates model training by aggregating a comprehensive dataset. Historical data is retrieved from a combination of sources including RAN nodes (e.g., gNodeBs), 5G / 6G core elements (e.g., UPF, AMF, SMF), telemetry logs from UE 104, Network Management Systems (NMS),performance management systems, and event correlation engines. Collected data includes throughput, latency, signal strength, access type, device hardware profde, session logs, call records, and usage statistics. Additionally, contextual indicators such as time-of-day, geographical cell ID, and user mobility patterns may also be captured to enrich model input.

[0093] Following collection, the dataset undergoes rigorous pre-processing. Data cleaning is performed to remove incomplete records, correct inconsistencies, and eliminate duplicates. Missing data points may be imputed using statistical techniques such as mean substitution, k-nearest neighbors (KNN), or temporal interpolation, depending on the variable type. Outlier detection algorithms are applied to identify and exclude anomalous entries that may bias training. Data normalization ensures uniform scaling across all parameters (e.g., converting all throughput data to Mbps, energy to mWh). Heterogeneous logs from different network elements are merged into a unified schema suitable for machine learning. If labeled training is required, data entries may be tagged as “normal” or “abnormal” based on expert annotation or predefined energy thresholds. Sampling techniques such as stratified sampling or SMOTE may be applied to balance class distribution in the training dataset.

[0094] The pre-processed dataset is then subjected to feature engineering. The processing engine 208 applies statistical correlation analysis, recursive feature elimination, or principal component analysis (PCA) to identify the most predictive attributes for energy modeling. Selected features may include signal strength, session duration, uplink / downlink traffic volume, device type, frequency band, handover count, access technology, and QoS class identifier. These features are optimized to reduce model complexity while maintaining predictive performance. Feature transformation techniques such as log-scaling or one-hot encoding may be applied where appropriate.

[0095] The model training unit selects an appropriate machine learning framework such as gradient boosted trees, random forests, or deep learning modelsincluding convolutional or recurrent neural networks, depending on feature dimensionality and training objectives. The selected model is trained using the curated dataset. Model hyperparameters such as learning rate, tree depth, batch size, or number of epochs are iteratively tuned using validation sets or automated optimization methods (e.g., grid search, Bayesian optimization). Loss functions such as mean squared error or cross-entropy are used to guide convergence. To ensure robustness, cross-validation is applied, and performance is evaluated using metrics such as R2, Fl score, precision, and recall.

[0096] Upon achieving satisfactory accuracy, the trained AI / ML model is serialized and deployed within the processing engine 208 for real-time inference. The model receives incoming real-time network data and energy signals from live UEs and predicts energy consumption patterns under current conditions. The model’s predictions are periodically validated against actual measured values. The model may be retrained periodically with updated data to account for new UE types, spectrum configurations, or changing usage patterns.

[0097] The processing engine 208 then computes one or more energy consumption metrics for each UE, including total energy used per session, energy per data volume, energy per frequency band, energy per access type, and energy per UE type. These metrics are compared against predefined energy consumption ranges stored in database 210. If deviations are detected, abnormal consumption is flagged. The processing engine 208 performs root-cause analysis to identify one or more potential issues such as degraded SNR, excessive retransmissions, or inefficient frequency allocation.

[0098] The identified issues are rendered on a display unit associated with at least one electronic device. The electronic device may include a UE or a network operator dashboard. The visual output may include diagnostic summaries, trend graphs, consumption heatmaps, and actionable alerts. In addition, the processing engine 208 determines one or more corrective measures by referencing mappings in the database 210, which associate specific issue types with corrective actionssuch as suggesting alternative access types, recommending UE software updates, or initiating dynamic spectrum reassignment.

[0099] The processing engine 208 communicates these recommendations to the affected UE 104 over the network 106 using standard messaging protocols. For example, a high-energy usage pattern in a UE operating on a congested mmWave band may trigger a network-side handover to a mid-band carrier, or a device-level notification may recommend reducing background service activity.

[0100] FIG. 3 illustrates an exemplary system architecture 300 for monitoring the energy consumption of the at least one UE 104, in accordance with an embodiment of the present disclosure. FIG. 3 is explained in conjunction with FIGS. 1 and 2.

[0101] FIG. 3 depicts a communication flow between the UE 104, the network 106, the processing engine 208, and a 5G network architecture 302. The UE 104 may include a plurality of UE sensors, such as a Battery Management System (BMS), power meter, software tools, current and voltage sensors, power consumption sensors, thermal sensors, Radio Frequency (RF) sensors, Network Interface sensors, and Power Management Integrated Circuits (PMICs), to collect the energy utilization data under different network conditions from the at least one UE 104. The network conditions for which the energy utilization data is collected may include frequency band used, signal strength received at the UE, Signal-to- Noise Ratio (SNR), uplink and / or downlink throughput, handover frequency or events, network congestion level, access type, network slice type, and transmission power of the UE. The collected UE-side telemetry data is transmitted to the processing engine 208 via a gNodeB 310.

[0102] In an embodiment, the UE 104 may communicate with the 5G network architecture 302 for services such as video streaming, online gaming, data transfer, application downloads, and web browsing. The 5G network architecture 302 may include a plurality of network functions, such as an Access and Mobility Management Function (AMF), Session Management Function (SMF), PolicyControl Function (PCF), Charging Function (CHF), User Data Management (UDM), and Unified Data Repository (UDR). These functions act as data sources to the monitoring unit. For example, the AMF provides registration and mobility data; the SMF provides session configuration and QoS enforcement data; the PCF supplies policy and rule information; and the CHF supplies charging and usage records. These components together serve as one or more data sources from which real-time network data corresponding to one or more network parameters that affect energy usage in the at least one UE is collected by a monitoring unit within the processing engine 208.

[0103] The processing engine 208 may include a data collector 304, a management dashboard 306, and an AI / ME model 308. The data collector 304 collects real-time network data and UE telemetry data from the above-mentioned sources. The network parameters may include signalling overhead, data transfer rates, access type, session duration, service type, and network slice, which are directly associated with energy utilization behavior. The data collector 304 pre- processes and integrates the collected data and stores it in a format consumable by the AI / ML model 308. The AEML model 308 is configured to generate, by a processing unit, an energy consumption pattern for the at least one UE 104 based on the received real-time network data and the energy utilization data using an Artificial Intelligence (Al) or Machine Learning (ML) model. The energy consumption pattern may be visualized in the form of a graph, histogram, column chart, bar chart, area chart, or line chart.

[0104] The processing engine 208 further determines, by the processing unit, an energy consumption information for the at least one UE 104 based on the energy consumption pattern, wherein the energy consumption information comprises at least one value corresponding to each of one or more energy consumption metrics. These metrics include total energy used per session, energy per data volume, energy per frequency band, energy per access type, and energy per UE type. For example, energy per data volume can help identify devices consuming disproportionate energy per megabyte in congested scenarios.Illustratively, the total energy used per session may be 820 mWh for a 15 -minute video call; energy per data volume may be 3.2 mWh per megabyte transferred under normal traffic and 6.5 mWh per megabyte under high congestion; energy per frequency band may be 5. 1 mWh on sub-6 GHz and 9.3 mWh on mmWave; energy per access type may be 2.7 mWh using Wi-Fi and 4.8 mWh using 5G NR; and energy per UE type may range from 1.2 Wh / hour for a smartphone to 0.3 Wh / hour for a low -power loT sensor under similar load conditions.

[0105] The AI / ML model 308 is trained and tested by a model training unit using the real-time network data and the energy consumption data to generate a context-aware energy prediction AI / ML model. During training, the processing engine 208 processes the energy utilization data from each UE 104, wherein the energy utilization data is collected for each of a plurality of network conditions. Simultaneously, the real-time network data corresponding to the one or more network parameters is processed for each network condition. The model training module trains the AI / ML model for predicting energy consumption patterns for each UE using the processed energy utilization data and the processed real-time network data. For testing, the trained AI / ML model is applied to historical network data to determine an energy consumption profde corresponding to each UE. The model is validated by comparing the predicted energy consumption pattern obtained for each UE with the actual energy utilization data collected for the respective UE. For example, if the model predicts a 25 percent energy increase under low SNR and high uplink load, and real telemetry confirms the same within acceptable tolerance, the model is considered successfully validated. Upon successful validation, the trained AI / ML model is provided for deployment within the processing engine 208.

[0106] The processing engine 208 further determines, by the processing unit, whether an abnormal energy consumption is detected in the at least one UE 104 based on the energy consumption information and a predefined energy consumption range present for the at least one UE. In some examples, the predefined energy consumption range for each UE is defined by the operator. If abnormal energy usage is detected, the processing engine 208 identifies, by theprocessing unit, one or more potential issues leading to the abnormal energy consumption for the at least one UE based on analysis of the energy consumption information.

[0107] These potential issues are displayed, by a display unit, on at least one electronic device, wherein the at least one electronic device is associated with at least one network operator. In the present example, the electronic device includes the management dashboard 306 within the processing engine 208. Alternatively, the issues may also be displayed on the UE 104 itself via a device-facing interface. The dashboard 306 is configured to compile and present energy consumption trends such as abnormal peaks, consumption anomalies, and application-specific breakdowns. Visualizations may include session-wise comparisons, consumption heatmaps, or time-series line graphs.

[0108] The management dashboard 306 is further configured to display the energy consumption chart created for the at least one UE 104, showing consumption metrics overtime and enabling operators to make informed adjustments to network parameters or user policies.

[0109] The processing engine 208 also determines, by the processing unit, one or more corrective measures for each of the one or more potential issues identified for the at least one UE 104, wherein the one or more corrective measures are selected based on a mapping between identified energy consumption issues and corresponding corrective actions stored in a database. For example, if high energy per session is due to repeated handovers in a high-mobility zone, the suggested corrective measure may include network-level configuration of handover thresholds or recommendations for fixed-spectrum access.

[0110] Further, the processing engine 208 communicates, by the processing unit, the one or more corrective measures to the affected UE 104 via control signaling or in-band application messages. The UE 104 may then adjust internal configurations, such as turning off high-energy modules, modifying application behavior, or alerting the user to make usage adjustments.

[0111] FIG. 4 illustrates an exemplary process flow 400 for training the AI / ML model 308 to monitor the energy consumption ofthe UE 104, in accordance with an embodiment of the present disclosure.

[0112] At step 402, device and network train data are collected. The UE data corresponding to the one or more UE parameters from the UEs 104 is received. The UE data is collected using the plurality of UE sensors such as a battery management system, power meter, RF sensor, network interface sensor, or PMIC. The collected data includes energy utilization data under different network conditions. These network conditions include, but are not limited to, frequency band used by the at least one UE, signal strength received at the UE, Signal-to- Noise Ratio (SNR), uplink and / or downlink throughput, handover frequency or events, network congestion level, access type, network slice type, and transmission power of the UE. For instance, higher transmission power during poor signal reception may lead to increased power drain.

[0113] Simultaneously, at step 404, real-time network data corresponding to one or more network parameters associated with the at least one UE is collected from one or more data sources. The one or more data sources include network elements such as the 5G / 6G core (e.g., AMF, SMF, PCF), network functions, and RAN nodes (e.g., gNodeB). The network parameters include signalling overhead, data transfer rates, access type, session duration, service type, and network slice.

[0114] At step 406, the data collected from the UE and the network is used to prepare a training dataset. The training data includes pre-processed, cleaned, and normalized values for relevant energy-affecting parameters. For example, energy per data volume and energy per access type are computed and tagged in the training set. These training data help the AI / ML model learn to recognize patterns that affect energy consumption, including usage type (e.g., video vs. audio) and environmental impact (e.g., mobility through multiple cells).

[0115] At step 408, test data is extracted from the real-time network data to test model performance. The test data serves as a validation mechanism to assessthe predictive capability of the trained AI / ML model 308. The test data includes the same parameters as the training data and may originate from different time intervals or device populations.

[0116] At step 410, the training and testing of the AI / ML model 308 is performed using the real-time network data and the energy consumption data to generate a context-aware energy prediction AI / ML model. In this step, the processing unit processes the energy utilization data from each UE of the at least one UE, wherein the energy utilization data is collected for each of a plurality of network conditions. The real-time network data corresponding to the one or more network parameters is also processed for each network condition of the plurality of network scenarios. The model training module then trains the AI / ML model for predicting energy consumption pattern for each UE using the processed energy utilization data and the processed real-time network data. For instance, a recurrent neural network may learn energy drain trends for UEs during frequent handovers or for devices operating over a congested mmWave band.

[0117] At step 412, the training performance is evaluated. If the training goal is not met, meaning the model cannot reliably predict energy consumption with the required accuracy, the training loop is repeated with refined data or updated parameters. For example, if the prediction error for energy per session exceeds a threshold, the model re-trains on an augmented or corrected dataset. If the training goal is met, the AI / ML model 308 is deemed ready for testing at step 420.

[0118] At step 414, the validation process is carried out by applying the test data to the trained model and comparing the predicted energy consumption patterns with actual usage patterns from the UE. This step is critical for confirming that the model's predictions are reliable and context aware. For example, if the model accurately predicts high energy consumption during a video streaming session on a congested network slice, the validation is considered successful. If validation is unsuccessful, step 416 is executed, wherein the model is trained again with adjustments in the architecture, hyperparameters, or training set balance. This loopcontinues until validation is successful.

[0119] Upon successful validation, as determined at step 414, the AI / ML model 308 is ready for prediction at step 418. The model may now be deployed in the processing engine for live inference and monitoring of energy consumption for the UE 104.

[0120] After deployment, the AUML model 308 is used to generate an energy consumption pattern for the at least one UE based on the received real-time network data and the energy utilization data. The processing unit then determines an energy consumption information for the at least one UE based on the energy consumption pattern, wherein the energy consumption information comprises at least one value corresponding to each of one or more energy consumption metrics. These metrics include total energy used per session, energy per data volume, energy per frequency band, energy per access type, and energy per UE type. For example, the total energy used per session may be 1.2 Wh for a 30-minute video streaming session; the energy per data volume may be 4.5 mWh / MB for uplink traffic and 2.9 mWh / MB for downlink traffic; the energy per frequency band may be 6.1 mWh / MB when operating on n77 (3.5 GHz) and 8.7 mWh / MB on mmWave; the energy per access type may be 3.2 mWh / MB for Wi-Fi and 5.4 mWh / MB for 5G NR; and the energy per UE type may be 1.8 Wh / hour for a smartphone and 0.6 Wh / hour for a tablet performing the same activity under identical network conditions.

[0121] Using the generated energy consumption information, the processing unit determines whether an abnormal energy consumption is detected in the at least one UE based on the energy consumption information and a predefined energy consumption range present for the at least one UE. The predefined range is stored in a network-side database and may be configured per UE type or operational profile.

[0122] If an abnormality is detected, the processing unit identifies one or more potential issues leading to the abnormal energy consumption based on theanalysis of the energy consumption information. These issues are displayed by a display unit on at least one electronic device, wherein the electronic device is associated with at least one network operator. In certain configurations, the dashboard display may also be rendered on the UE. The visual dashboard may include charts showing session-wise energy spikes, application-level consumption, or energy trends over time.

[0123] The processing unit then determines one or more corrective measures for each of the one or more potential issues identified for the at least one UE, wherein the corrective measures are selected based on a mapping between identified energy consumption issues and corresponding corrective actions stored in a database. For instance, the system may recommend reduction of screen brightness, switch network modes, or disabling high-energy background apps. These recommendations are communicated by the processing unit to the UE, either through device management protocols or app-based notifications.

[0124] Finally, the method includes displaying the energy consumption chart created for the at least one UE, which may include historical and predicted usage trends, per-metric breakdown, and comparative benchmarking with similar device profiles.

[0125] FIG. 5 illustrates an exemplary flow chart 500 for a method of monitoring energy consumption of the UE 104 in real-time, in accordance with an embodiment of the present disclosure.

[0126] At step 502, the one or more UE data and the one or more network data are received. The one or more UE data is collected by the monitoring unit from sensors embedded within the UE 104, such as a Battery Management System (BMS), current sensors, voltage sensors, power consumption sensors, thermal sensors, Radio Frequency (RF) sensors, Network Interface sensors, and Power Management Integrated Circuits (PMICs). These sensors are configured to provide energy utilization data under different network conditions. The network conditions include frequency band used by the UE, signal strength received at the UE, Signal-to-Noise Ratio (SNR), uplink and / or downlink throughput, handover frequency or events, network congestion level, access type (e.g., standalone or non-standalone), network slice type (e.g., video slice, voice slice, mMTC slice), and transmission power of the UE. The one or more network data is received by the monitoring unit from one or more data sources, including but not limited to 5G / 6G core network entities (such as AMF, SMF, PCF), network functions (e.g., UDM, NWDAF), and Radio Access Network (RAN) nodes (e.g., gNodeBs). The one or more network parameters collected include signalling overhead, data transfer rates, access type, session duration, service type, and network slice.

[0127] At step 504, the training and testing of the AI / ML model 308 is performed by a model training unit using the real-time network data and the energy consumption data to generate a context-aware energy prediction AI / ML model. The training phase includes processing, by the processing unit, the energy utilization data from each UE of the at least one UE, wherein the energy utilization data is collected for each of the plurality of network conditions described above. Simultaneously, the processing unit processes the real-time network data corresponding to the one or more network parameters for each network condition. The model training module trains the AI / ML model for predicting energy consumption pattern for each UE using the processed energy utilization data and the processed real-time network data. For example, the model may learn that high uplink throughput during periods of poor signal strength results in above-normal energy consumption per session.

[0128] The training module applies the network data to the trained AI / ML model to determine an energy consumption profde corresponding to each UE. The trained AI / ML model is validated by comparing the predicted energy consumption pattern obtained for each UE with the actual energy utilization data collected for the respective UE. For instance, if the predicted energy per data volume deviates by less than 5 percent from the detected value under high congestion scenarios, the validation is considered successful. Upon successful validation, the model training module provides the trained AI / ML model for deployment.

[0129] At step 506, the current energy consumption pattern and the predicted energy consumption pattern for the UE 104 are generated by the processing unit using the trained AI / ML model and are displayed by a display unit via a graphical user interface (GUI). The GUI may be rendered on at least one electronic device, which may include the UE 104 itself or a network operator dashboard such as a centralized energy analytics portal. The graphical representation may include line charts, bar graphs, or comparative histograms depicting actual versus predicted usage metrics.

[0130] The energy consumption information displayed includes at least one value corresponding to each of one or more energy consumption metrics. These consumption metrics include total energy used per session, energy per data volume, energy per frequency band, energy per access type (e.g., Wi-Fi vs. LTE), and energy per UE type (e.g., smartphone vs. loT sensor). By rendering these metrics, the GUI provides granular insight into when and how energy is consumed by the UE.

[0131] Further, the display unit is configured to display one or more potential issues on the GUI based on an analysis of the energy consumption information. The potential issues are determined by identifying, by the processing unit, abnormal energy consumption based on a comparison of the energy consumption information with a predefined energy consumption range for the UE stored in a database. The processing unit identifies contributing factors, such as elevated transmission power during weak signal conditions or prolonged activity on high-energy applications.

[0132] The GUI also displays tailored recommendations generated by the processing unit to address the one or more potential issues. By doing so, the method communicates one or more corrective measures to the at least one UE. These corrective measures are selected based on a mapping between the identified energy consumption issues and corresponding corrective actions stored in a network-side database. For example, the GUI may suggest reducing screen brightness, disabling background services, switching access type to a lower energy mode, or applyingOS-level optimizations. These recommendations may be user-visible or automatically configured via mobile device management (MDM) policies.

[0133] FIG. 6 illustrates an exemplary flow diagram 600 representing a method for monitoring energy consumption of at least one user equipment (UE) in real-time, in accordance with an embodiment of the present disclosure.

[0134] At step 602, the method 600 comprises collecting, by a monitoring unit, real-time network data corresponding to one or more network parameters associated with the at least one UE from one or more data sources. The one or more data sources may include the 5G / 6G core, network functions, and Radio Access Network (RAN) nodes such as gNodeBs. Examples of network functions include the Access and Mobility Management Function (AMF), Session Management Function (SMF), Policy Control Function (PCF), User Data Management (UDM), and Network Data Analytics Function (NWDAF). The one or more network parameters collected may include signalling overhead, data transfer rates, access type, session duration, service type, and network slice. For instance, a UE transmitting data over a high-throughput network slice configured for ultra-reliable low-latency communication (URLLC) may generate different energy signatures compared to a slice optimized for enhanced mobile broadband.

[0135] At step 604, the method 600 comprises collecting, by the monitoring unit, energy utilization data under different network conditions from the at least one UE. The energy utilization data is collected from internal UE sensors, including battery monitoring circuits, RF power sensors, voltage and current meters, thermal sensors, and network interface modules. The network conditions under which the data is captured may include, for example, frequency band used by the at least one UE, signal strength received at the at least one UE, Signal-to-Noise Ratio (SNR), uplink and / or downlink throughput, handover frequency or events, network congestion level, access type, network slice type, and transmission power of the UE. For example, poor signal strength combined with high uplink throughput may result in abnormal transmission power levels and excessive battery drain.

[0136] At step 606, the method 600 comprises generating, by a processing unit, an energy consumption pattern for the at least one UE based on the received real-time network data and the energy utilization data using an Artificial Intelligence (AI)ZMachine Learning (ML) model. The AI / ML model may be implemented as a supervised learning model trained on labeled datasets comprising historical energy usage correlated with specific network and device states. During operation, the model may receive inputs such as average signal quality, packet retransmissions, and throughput per time interval and output an energy profile over time or per application session. The energy consumption pattern may take the form of statistical sequences, time-series graphs, or inferred curves that correlate UE activity with detected energy behavior.

[0137] At step 608, the method 600 comprises determining, by the processing unit, an energy consumption information for the at least one UE based on the energy consumption pattern, wherein the energy consumption information comprises at least one value corresponding to each of one or more energy consumption metrics. The energy consumption metrics may include total energy used per session, energy per data volume, energy per frequency band, energy per access type, and energy per UE type. For instance, energy per data volume may help quantify inefficiency in uplink transmission during periods of interference, and energy per frequency band may expose inefficiencies in mmWave deployments in dense urban environments. By deriving these metrics, the processing unit supports fine-grained energy profiling across multiple operating conditions and usage scenarios.

[0138] At step 610, the method 600 comprises determining, by the processing unit, whether an abnormal energy consumption is detected in the at least one UE based on the energy consumption information and a predefined energy consumption range present for the at least one UE. The predefined energy consumption range may be dynamically adjusted based on baseline data gathered from the same UE under normal operating conditions or benchmark data from other UEs of the same type. For example, a smartphone model operating with videostreaming may have an expected energy range of 5-8 mWh per megabyte. Any deviation outside this expected range — such as 12 mWh per megabyte — would be flagged as abnormal.

[0139] At step 612, the method 600 comprises identifying, by the processing unit, one or more potential issues leading to the abnormal energy consumption for the at least one UE based on analysis of the energy consumption information. The processing unit may utilize explainable Al (XAI) techniques or decision trees to trace contributing factors to the deviation. Examples of identified issues may include suboptimal handover configuration, excessive signaling activity, poorly coded applications generating frequent wakeups, or degraded RF modules forcing high transmission gain.

[0140] At step 614, the method 600 comprises displaying, by a display unit, the one or more potential issues on at least one electronic device, wherein the at least one electronic device is associated with at least one network operator. The display unit may be a network operator dashboard, a device management console, or the user equipment itself. The display content may include visualizations such as heatmaps of power consumption by module, trends over time, comparative benchmarks, and root-cause insights. For example, an operator dashboard may display that 20 percent of UEs within a particular cell exhibit above -threshold energy consumption, with a common factor being handover-related signaling spikes.

[0141] At step 616, the method 600 comprises communicating, by the processing unit, recommendations to the at least one UE to perform one or more corrective measures to address the one or more potential issues. The corrective measures are determined by referencing a rule-based or Al-inferred mapping stored in a database that links energy abnormalities to resolution actions. Examples of corrective measures include reconfiguring network parameters (e.g., handover thresholds, RRC timers), recommending the user to disable power-intensive background apps, dynamically switching the UE to a more efficient accesstechnology, or adjusting video resolution during streaming to balance throughput and power consumption.

[0142] By performing the above steps, the method enables continuous monitoring and intelligent management of UE energy performance in real-time networks, delivering actionable insights to both the network operator and the end user while reducing unnecessary energy expenditure at the device level. The integration of model-based analytics, real-time telemetry, and adaptive recommendations ensures sustainable network operations and improved device longevity.

[0143] FIG. 7 illustrates an exemplary computer system 700 in which or with which embodiments of the present disclosure may be implemented. As shown in FIG. 7, the computer system 700 may include an external storage device 710, a bus 720, a main memory 730, a read-only memory 740, a mass storage device 750, communication port(s) 760, and a processor 770. A person skilled in the art will appreciate that the computer system 700 may include more than one processor and communication ports. The processor 770 may include various modules associated with embodiments of the present disclosure. The communication port(s) 760 may be any of an RS-232 port for use with a modem-based dialup connection, a 10 / 100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. The communication port(s) 760 may be chosen depending on a network, such a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system 700 connects.

[0144] The main memory 730 may be a Random Access Memory (RAM), or any other dynamic storage device commonly known in the art. The read-only memory 740 may be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chips for storing static information e.g., start-up or Basic Input / Output System (BIOS) instructions for the processor 770. The mass storage device 750 may be any current or future mass storage solution, which can be used to store information and / or instructions. Exemplarymass storage device 750 includes, but is not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., having Universal Serial Bus (USB) and / or Firewire interfaces), one or more optical discs, Redundant Array of Independent Disks (RAID) storage, e.g. an array of disks.

[0145] The bus 720 communicatively couples the processor 770 with the other memory, storage, and communication blocks. The bus 720 may be, e.g. a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), Universal Serial Bus (USB), or the like, for connecting expansion cards, drives, and other subsystems as well as other buses, such a front side bus (FSB), which connects the processor 770 to the computer system 700.

[0146] Optionally, operator and administrative interfaces, e.g. a display, keyboard joystick, and a cursor control device, may also be coupled to the bus 720 to support direct operator interaction with the computer system. Other operator and administrative interfaces can be provided through network connections connected through the communication port(s) 760. Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system 700 limit the scope of the present disclosure.

[0147] In an embodiment, the processing engine collects UE data corresponding to one or more UE parameters from the at least one UE. Further, the processing engine collects network data corresponding to one or more network parameters from one or more data sources. The processing engine input the collected UE data and the network data to a trained AEML model to generate at least one current energy consumption pattern of the at least one UE. Further, the processing engine identifies an abnormal energy consumption of the at least one UE by comparing the at least one current energy consumption pattern with at least one predicted energy consumption pattern of the at least one UE. The processing engine further displays the identified abnormal energy consumption correspondingto one or more metrics to a network operator.

[0148] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.

[0149] The method and system of the present disclosure may be implemented in a number of ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0150] While considerable emphasis has been placed herein on the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be implemented merely as illustrative of the disclosure and not as a limitation.ADVANTAGES OF THE PRESENT DISCLOSURE

[0151] The present disclosure provides a method and a system for enabling real-time and granular monitoring of energy consumption of user equipment (UE) in modem wireless networks by integrating machine learning models with network telemetry and device-level sensing. By leveraging AI / ML-driven energy profding, the system dynamically processes data collected from the 5G / 6G core, radio access networks, and UE telemetry to deliver high-resolution energy analytics without requiring custom instrumentation or device-side firmware changes. This architecture permits continuous and context-aware monitoring of energy metrics across diverse deployment environments.

[0152] The present disclosure provides a method and a system for generating energy consumption patterns and performing predictive analysis using a trained AI / ML model, allowing identification of deviations from normal power usage in real-time. The system processes both device-side and network-side data, including parameters such as signal strength, throughput, session duration, and access type, to infer granular energy consumption metrics such as energy per data volume or energy per frequency band. By doing so, the system supports root-cause analysis of abnormal power usage and delivers actionable recommendations to reduce energy overhead in user devices.

[0153] The present disclosure provides a method and a system for improving energy efficiency by enabling network-aware optimizations in the UE and at the infrastructure level. The system identifies power inefficiencies caused by poor signal conditions, frequent handovers, or misconfigured radio parameters and translates these into operator-facing insights or device-side recommendations. This allows network operators to initiate macro cell re-planning, apply access-type prioritization, or dynamically adjust slicing configurations to enhance energy efficiency without compromising user experience.

[0154] The present disclosure provides a method and a system for enhancing device sustainability and user transparency by providing direct feedback to the UE on energy usage behavior and patterns through a visual dashboard orintegrated device notification interface. The feedback includes contextual suggestions such as disabling high-drain background applications, adjusting screen brightness, or scheduling updates in off-peak hours. By empowering users to take informed actions, the system fosters power-conscious behavior and reduces unnecessary energy waste at the device edge.

[0155] The present disclosure provides a method and a system for integrating seamlessly with existing 5G / 6G network architectures by deploying a non-intrusive monitoring and analysis framework that interacts with standard network functions such as AMF, SMF, PCF, and gNodeB. The system leverages probing interfaces to collect relevant network and device metrics, avoiding the need for extensive infrastructure modifications. This compatibility enables scalable deployment across multi-vendor environments, promoting wide adoption of energy-aware network intelligence with minimal operational overhead.

Claims

We claim:

1. A method for monitoring energy consumption of at least one user equipment (UE) in real-time, the method comprising: collecting (602), by a monitoring unit, real-time network data corresponding to one or more network parameters associated with the at least one UE from one or more data sources; collecting (604), by the monitoring unit, energy utilization data under different network conditions from the at least one UE; generating (606), by a processing unit, an energy consumption pattern for the at least one UE based on the received real-time network data and the energy utilization data using an Artificial Intelligence (AI)ZMachine Learning (ML) model; determining (608), by the processing unit, an energy consumption information for the at least one UE based on the energy consumption pattern , wherein the energy consumption information comprises at least one value corresponding to each of one or more energy consumption metrics; determining (610), by the processing unit, whether an abnormal energy consumption is detected in the at least one UE based on the energy consumption information and a predefined energy consumption range present for the at least one UE; identifying (612), by the processing unit, one or more potential issues leading to the abnormal energy consumption for the at least one UE based on analysis of the energy consumption information; displaying (614), by a display unit, the one or more potential issues on at least one electronic device, wherein the at least one electronic device is associated with at least one network operator; and communicate (616), by the processing unit, recommendations to the at least one UE to perform one or more corrective measures to address the one or more potential issues.

2. The method as claimed in claim 1, further comprises: training and testing, by a model training unit, the AI / ML model using the real-time network data and the energy consumption data to generate context-aware energy prediction AI / ML model.

3. The method as claimed in claim 2, wherein the step of training, by the model training unit, the AI / ML model to obtain the trained AI / ML model further comprises: processing, by the processing unit, the energy utilization data from each UE of the at least one UE, wherein the energy utilization data is collected for each of a plurality of network conditions; processing, by the processing unit, the real-time network data corresponding to the one or more network parameters for each network condition of the plurality of network conditions ; training, by a model training module, the AI / ML model for predicting energy consumption pattern for each UE using the processed energy utilization data and the processed real-time network data; applying, by the model training module, the network data to the trained AI / ML model to determine an energy consumption profile corresponding to each UE; validating, by the model training module, the trained AI / ML model based on the predicted energy consumption pattern obtained for each UE and the energy utilization data collected for the respective UE; and upon successful validation, providing, by the model training module, the trained AI / ML model.

4. The method as claimed in claim 1, further comprising: determining, by the processing unit, the one or more corrective measures for each of the one or more potential issues identified for the at least one UE, wherein the one or more corrective measures are selectedbased on a mapping between identified energy consumption issues and corresponding corrective actions stored in a database; and communicating, by the processing unit , the one or more corrective measures to one of the at least one UE.

5. The method as claimed in claim 1, further comprises: displaying, by the display unit, the energy consumption chart created for the at least one UE .

6. The method as claimed in claim 1, wherein the one or more energy consumption metrics comprises: a) total energy used per session, b) energy per data volume, c) energy per frequency band, d) energy per access type, and e) energy per UE type.

7. The method as claimed in claim 1, wherein the one or more network parameters comprises: a) signalling overhead, b) data transfer rates, c) access type, d) session duration, e) service type, and f) network slice.

8. The method as claimed in claim 1, wherein the plurality of network conditions comprises: a) frequency band used by the at least one UE, b) signal strength received at the at least one UE, c) Signal -to-Noise Ratio (SNR) received at the at least one UE, d) uplink and / or downlink throughput;e) handover frequency or events; f) network congestion level; g) access type; h) network slice type; and i) transmission power of the UE.

9. A system for monitoring energy consumption of at least one user equipment (UE) in real-time, the system comprising: a memory (204) storing instructions; one or more communication interfaces (206); and one or more hardware processors (202) coupled to the memory (204) via the one or more communication interfaces (206), wherein the one or more hardware processors (202) comprises: collect, by a monitoring unit, real-time network data corresponding to one or more network parameters that affect energy usage in the at least one UE from one or more data sources; collect, by the monitoring unit, energy utilization data under different network conditions from the at least one UE; generate, by a processing unit, an energy consumption pattern for the at least one UE based on the received real-time network data and the energy utilization data using an Artificial Intelligence (AI)ZMachine Learning (ML) model; determine, by the processing unit, an energy consumption information for the at least one UE based on the energy consumption pattern , wherein the energy consumption information comprises at least one value corresponding to each of one or more energy consumption metrics; determine, by the processing unit, whether an abnormal energy consumption is detected in the at least one UE based on the energy consumption information and a predefined energy consumption range present for the at least one UE;identify, by the processing unit, one or more potential issues leading to the abnormal energy consumption for the at least one UE based on analysis of the energy consumption information; display, by a display unit, the one or more potential issues on at least one electronic device, wherein the at least one electronic device is associated with at least one network operator; and communicate, by the processing unit, recommendations to the at least one UE to perform one or more corrective measures to address the one or more potential issues.

10. The system as claimed in claim 9, wherein the one or more hardware processors further comprises a model training unit configured to train and test the AUML model using the real-time network data and energy consumption data to generate context-aware energy prediction AI / ML model.

11. The system as claimed in claim 10, wherein the model training unit further comprises: the processing unit configured to: process the energy utilization data from each UE of the at least one UE, wherein the energy utilization data is collected for each of a plurality of network conditions; and process the real-time network data corresponding to the one or more network parameters for each network condition of the plurality of network scenarios; and a model training module configured to: train the AI / ML model for predicting energy consumption pattern for each UE using the processed energy utilization data and the processed real-time network data; apply the network data to the trained AI / ML model to determine an energy consumption profile corresponding to each UE;validate the trained AI / ML model based on the predicted energy consumption pattern obtained for each UE and the energy utilization data collected for the respective UE; and provide, upon successful validation, the trained AI / ML model.

12. The system as claimed in claim 9, wherein the one or more hardware processors further comprises: the processing unit configured to: determine the one or more corrective measures for each of the one or more potential issues identified for the at least one UE, , wherein the one or more preventive actions are selected based on a mapping between identified energy consumption issues and corresponding corrective actions stored in a database; and communicate the one or more corrective measures to one of the at least one UE.

13. The system as claimed in claim 9, wherein the one or more hardware processors further comprises: the display unit configured to display the energy consumption chart created for the at least one UE.

14. The system as claimed in claim 9, wherein the one or more consumption metrics comprises: a) total energy used per session, b) energy per data volume, c) energy per frequency band, d) energy per access type, and e) energy per UE type.

15. The system as claimed in claim 9, wherein the one or more network parameters comprises:a) signalling overhead, b) data transfer rates, c) access type, d) session duration, e) service type, and f) network slice.

16. The system as claimed in claim 9, wherein the plurality of network conditions comprises: a) frequency band used by the at least one UE, b) signal strength received at the at least one UE, c) Signal -to-Noise Ratio (SNR) received at the at least one UE, d) uplink and / or downlink throughput; e) handover frequency or events; f) network congestion level; g) access type; h) network slice type; and i) transmission power of the UE.

17. A user equipment (102) communicatively coupled to a system (108), said coupling comprises steps of: receiving a connection request; sending an acknowledgment of the connection request to the system (108); and transmitting data from the user equipment (102) to the system (108), wherein the system (108) is configured to monitoring energy consumption of the user equipment (UE) in real-time as claimed in claim 9.

18. A computer program product comprising a non-transitory computer- readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to execute a method formonitoring energy consumption of at least one user equipment (UE), the method comprising steps of: collecting, by a monitoring unit, real-time network data corresponding to one or more network parameters that affect energy usage in the at least one UE from one or more data sources; collecting, by the monitoring unit, energy utilization data under different network conditions from the at least one UE; generating, by a processing unit, an energy consumption pattern for the at least one UE based on the received real-time network data and the energy utilization data using an Artificial Intelligence (AI)ZMachine Learning (ML) model; determining, by the processing unit, an energy consumption information for the at least one UE based on the energy consumption pattern , wherein the energy consumption information comprises at least one value corresponding to each of one or more energy consumption metrics; determining, by the processing unit, whether an abnormal energy consumption is detected in the at least one UE based on the energy consumption information and a predefined energy consumption range present for the at least one UE; identifying, by the processing unit, one or more potential issues leading to the abnormal energy consumption for the at least one UE based on analysis of the energy consumption information; displaying, by a display unit, the one or more potential issues on at least one electronic device, wherein the at least one electronic device is associated with at least one network operator; and communicate, by the processing unit, recommendations to the at least one UE to perform one or more corrective measures to address the one or more potential issues.

Images