Method and system for regulating an energy consumption in a heterogeneous network (hetnet) environment

Abstract

The present disclosure relates to a method [400] and a system [300] for regulating an energy consumption in a Heterogeneous Network (HetNet) environment The present disclosure encompasses: monitoring [404], by a processing unit [302], traffic levels at one or more cell sites in a network region, said monitoring corresponds to evaluating a set of KPIs; predicting [406], by the processing unit [302], the one or more traffic levels; identifying [408], by the processing unit [302] via an identification unit [304], a candidate cell site and a set of neighbouring cell sites based on the one or more traffic levels; determining [410], by the processing unit [302], a coverage hole flag; and automatically switching [412], by the processing unit [302], between a power ON state and a power OFF of the identified candidate cell site based on the coverage hole flag to regulate the energy consumption and maintain a pre-defined operational criterion.

Description

METHOD AND SYSTEM FOR REGULATING AN ENERGY CONSUMPTION IN A HETEROGENEOUS NETWORK (HETNET) ENVIRONMENTTECHNICAL FIELD

[0001] Embodiments of the present disclosure generally relate to network performance management systems. More particularly, embodiments of the present disclosure relate to methods and systems for regulating an energy consumption in a Heterogeneous Network (HetNet) environment.BACKGROUND

[0002] The following description of the 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 is used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of the prior art.

[0003] Wireless communication technology has rapidly evolved over the past few decades, with each generation bringing significant improvements and advancements. The first generation of wireless communication technology was based on analog technology and offered only voice services. However, with the advent of the second generation (2G) technology, digital communication and data services became possible, and text messaging was introduced. The third generation (3G) technology marked the introduction of high-speed internet access, mobile video calling, and location-based services. The fourth generation (4G) technology revolutionized wireless communication with faster data speeds, better network coverage, and improved security. Currently, the fifth generation (5G) technology is being deployed, promising even faster data speeds, low latency, and the ability to connect multiple devices simultaneously. With each generation, wireless communication technology has become more advanced, sophisticated, and capable of delivering more services to its users.

[0004] Energy efficiency is a critical consideration for cell site operations, particularly when it comes to the switch on / off process of a cell site. Cell sites consume a significant amount of energy, and inefficient switch on / off procedures can result in unnecessary power consumption and increased operational costs. In a typical cellular network, one can easily see that the traffic demandin the peak hours is much higher than that at night, which inspires the different rates offered by cellular operators. To address this mismatch in demand, optimizing energy efficiency during the cell site switch on / off process is essential.

[0005] Further, over the period of time various solutions have been developed to improve the performance of communication devices and to ensure energy efficiency. However, there are certain challenges with existing solutions. Firstly, proper equipment management and maintenance play a crucial role in energy efficiency. Regular inspections and maintenance activities help identify and address any issues that may contribute to excessive power consumption during the switch on / off process. However, ensuring that equipment is operating at its optimum efficiency, such as utilizing energy-saving features and implementing power management protocols, is a humongous task. Furthermore, adopting energy-efficient hardware and components can contribute to overall energy savings during the switch on / off process but is an expensive process.

[0006] In the current existing solutions, continuous monitoring and data analysis are key for identifying areas for energy optimization. By collecting and analyzing real-time data on energy usage, site performance, and environmental factors, operators can gain insights into energy patterns and make informed decisions to improve efficiency. However, this requires a lot of manual intervention.

[0007] Thus, there exists an imperative need in the art to implement smart automation and intelligent solutions that can improve energy efficiency.SUMMARY

[0008] This section is provided to introduce certain aspects of the present disclosure in a simplified form that are further described below in the detailed description. This summary is not intended to identify the key features or the scope of the claimed subject matter.

[0009] An aspect of the present disclosure may relate to a method for regulating an energy consumption in a Heterogeneous Network (HetNet) environment. The method comprises monitoring, by a processing unit, one or more traffic levels at one or more cell sites in a network region, wherein said monitoring corresponds to evaluating a set of Key Performance Indicators (KPIs) associated with the one or more cell sites. The method further comprises predicting, by the processing unit, the one or more traffic levels associated with each of the one or more cell sites.The method further comprises identifying, by the processing unit, via an identification unit, a candidate cell site and a set of neighbouring cell sites based on the predicted one or more traffic levels. The method further comprises determining, by the processing unit, a coverage hole flag associated with the identified candidate cell site and the set of neighbouring cell sites. The method further comprises automatically switching, by the processing unit, between a power ON state and a power OFF state of the identified candidate cell site based on the determined coverage hole flag and maintain a pre-defined operational criterion associated with the HetNet environment.

[0010] In an exemplary aspect of the present disclosure, the automatically switching, by the processing unit, between the power ON state and the power OFF state of the identified candidate cell site, maintains a pre-defined operational criterion associated with the HetNet environment.

[0011] In another exemplary aspect of the present disclosure, the method further comprises analysing, by the processing unit, the one or more traffic levels of the one or more cell sites to identify one of a period of minimal traffic level and a period of no traffic level. The method further comprises evaluating, by the processing unit, the energy consumption during one of the identified period of minimal traffic level and the period of no traffic level, wherein the energy consumption is evaluated against a predefined efficiency threshold. The method further comprises predicting, by the processing unit, one of a target period of minimal traffic level and a target period of no traffic level, based on one or more historical traffic level patterns and an associated energy usage. The method further comprises adjusting, by the processing unit, the automatically switching between the power ON state or the power OFF state of the identified candidate cell site during one of the predicted target period of minimal traffic level and the predicted target period of no traffic level.

[0012] In an exemplary aspect of the present disclosure, the set of KPIs comprises at least one of a Physical Resource Block (PRB) Utilization, a Number of Radio Resource Control (RRC) Users, a number of active users, a Cell effective throughput, and a Total traffic (Uplink and Downlink).

[0013] In an exemplary aspect of the present disclosure, the predicting further comprises implementing, by the processing unit, one or more supervised machine learning techniques, comprising at least a support vector technique implemented via a Support Vector Machine (SVM), wherein the support vector technique is implemented to anticipate a user data based on a historical traffic level data, a day of week, and a time, utilizing a kernel function to consider both a spatial distance and a temporal distance between one or more data points.

[0014] In an exemplary aspect of the present disclosure, the automatically switching between the power ON state and the power OFF state is further based on evaluating, by the processing unit, a coverage and an overlap impact that occurs when the candidate site is switched OFF or ON to ensure no coverage hole is created that affect user experience.

[0015] In an exemplary aspect of the present disclosure, the identifying the candidate cell site and the set of neighbouring cell sites comprises evaluating at least one of a measurement range of a signal strength and a site location, based on one or more variations in one or more traffic level patterns over a time, a day of week, and one or more seasonal changes.

[0016] In an exemplary aspect of the present disclosure, the determining the coverage hole flag comprises evaluation of a planning data and a crowdsourcing data comprising one or more parameters, wherein the one or more parameters comprises at least one of a best server plot (latitude and longitude of a site location) and a signal strength, to tag one or more areas with a received signal strength less than -110 as one or more potential coverage holes.

[0017] In an exemplary aspect of the present disclosure, for the automatically switching between the power ON state and the power OFF state, the method further comprises deactivating the identified candidate cell site. The method further comprises triggering a handover mechanism to ensure a seamless transition of one or more users to the set of neighbouring cell sites. The method further comprises updating a network configuration to reflect deactivation of a macro 5G new radio (NR) node B (gNB).

[0018] In an exemplary aspect of the present disclosure, subsequent to the automatically switching, the method further comprises continuously monitoring, by the processing unit, of at least one of: the one or more traffic levels; a network performance; and a user experience of the set of neighbouring cell sites, wherein the continuously monitoring of the at least one of the one or more traffic levels, the network performance, and the user experience enables assessing of a traffic level distribution and a capacity utilization in the set of neighbouring cell sites, followed by a reactivation of the macro 5G new radio (NR) node B (gNB) of the candidate cell site when the predicted or actual one or more traffic levels of a set of neighbour gNBs corresponding to the set of neighbouring cell sites increases above a predefined threshold.

[0019] Another aspect of the present disclosure may relate to a system for regulating an energy consumption in a Heterogeneous Network (HetNet) environment. The system comprises a processing unit and an identification unit connected to each other. The processing unit is configured to monitor one or more traffic levels at one or more cell sites in a network region, wherein said monitoring corresponds to evaluating a set of Key Performance Indicators (KPIs) associated with the one or more cell sites. The processing unit is further configured to predict the one or more traffic levels associated with each of the one or more cell sites. The processing unit is further configured to identify, via the identification unit, a candidate cell site and a set of neighbouring cell sites based on the predicted one or more traffic levels. The processing unit is further configured to determine a coverage hole flag associated with the identified candidate cell site and the set of neighbouring cell sites. The processing unit is further configured to automatically switch between the power ON state or the power OFF state of the identified candidate cell site based on the determined coverage hole flag to regulate the energy consumption and, maintain a pre-defined operational criterion associated with the HetNet environment.

[0020] Yet another aspect of the present disclosure may relate to a non-transitory computer readable storage medium storing instructions for regulating an energy consumption in a Heterogeneous Network (HetNet) environment, the instructions include executable code which, when executed by one or more units of a system, causes a processing unit of the system to monitor one or more traffic levels at one or more cell sites in a network region, wherein said monitoring corresponds to evaluating a set of Key Performance Indicators (KPIs) associated with the one or more cell sites. The instructions further include executable code which, when executed causes the processing unit of the system to predict the one or more traffic levels associated with each of the one or more cell sites; and to identify, via the identification unit of the system, a candidate cell site and a set of neighbouring cell sites based on the predicted one or more traffic levels. The instructions further include executable code which, when executed cause; the processing unit of the system to determine a coverage hole flag associated with the identified candidate cell site and the set of neighbouring cell sites. The instructions further include executable code which, when executed causes the processing unit of the system to automatically switch the power ON or OFF of the identified candidate cell site based on the determined coverage hole flag to regulate the energy consumption and, maintain a pre-defined operational criterion associated with the HetNet environment.OBJECTS OF THE DISCLOSURE

[0021] Some of the objects of the present disclosure, which at least one embodiment disclosed herein satisfies are listed herein below.

[0022] It is an object of the present disclosure to provide a system and a method for regulating an energy consumption in a Heterogeneous Network (HetNet) environment.

[0023] It is an object of the present disclosure to provide a system and a method for smart automation and intelligent machine learning techniques to improve energy efficiency.

[0024] It is another object of the present disclosure to provide a solution that implements energy monitoring systems and leverages advanced analytics, which can help in detecting traffic conditions and in highlighting opportunities for further energy-saving initiatives.

[0025] It is yet another object of the present disclosure to provide a solution for energy to be allocated efficiently, reducing unnecessary power consumption, and minimizing carbon footprint.BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated herein, and constitute 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. Also, the embodiments shown in the figures are not to be construed as limiting the disclosure, but the possible variants of the method and system according to the disclosure are illustrated herein to highlight the advantages of the disclosure. It will be appreciated by those skilled in the art that disclosure of such drawings includes disclosure of electrical components or circuitry commonly used to implement such components.

[0027] FIG. 1 A illustrates an exemplary system architecture for regulating energy consumption in a Heterogeneous Network (HetNet) environment, in accordance with exemplary implementations of the present disclosure.

[0028] FIG. IB illustrates an exemplary schematic diagram for regulating energy consumption in a Heterogeneous Network (HetNet) environment in accordance with exemplary implementations of the present disclosure.

[0029] FIG. 2 illustrates an exemplary block diagram of a computing device upon which the features of the present disclosure may be implemented in accordance with exemplary implementation of the present disclosure.

[0030] FIG. 3 illustrates an exemplary block diagram of a system for regulating energy consumption in a Heterogeneous Network (HetNet) environment, in accordance with exemplary implementations of the present disclosure.

[0031] FIG. 4 illustrates a method flow diagram for regulating energy consumption in a Heterogeneous Network (HetNet) environment in accordance with exemplary implementations of the present disclosure.

[0032] FIG. 5 illustrates an exemplary diagram for regulating the energy consumption in the HetNet environment, in accordance with exemplary implementations of the present disclosure.

[0033] The foregoing shall be more apparent from the following more detailed description of the disclosure.DETAILED DESCRIPTION

[0034] 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 may 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.

[0035] 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.

[0036] 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, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail.

[0037] Also, it is noted that individual embodiments may be described as a process which 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 may 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.

[0038] 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 — in a manner similar to the term “comprising” as an open transition word — without precluding any additional or other elements.

[0039] As used herein, a “processing unit” or “processor” or “operating processor” includes one or more processors, wherein processor refers to any logic circuitry for processing instructions. A 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 Signal 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 present disclosure. More specifically, the processor or processing unit is a hardware processor.

[0040] As used herein, “a user equipment”, “a user device”, “a smart-user-device”, “a smartdevice”, “an electronic device”, “a mobile device”, “a handheld device”, “a wirelesscommunication device”, “a mobile communication device”, “a communication device” may be any electrical, electronic, and / or computing device or equipment, capable of implementing the features of the present disclosure. The user equipment / device may include, but is not limited to, a mobile phone, smart phone, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, wearable device or any other computing device which is capable of implementing the features of the present disclosure. Also, the user device may contain at least one input means configured to receive an input from unit(s) which are required to implement the features of the present disclosure.

[0041] As used herein, “storage unit” or “memory unit” refers to a machine or computer-readable medium including any mechanism for storing information in a form readable by a computer or similar machine. For example, a computer-readable medium includes read-only memory (“ROM”), random access memory (“RAM”), magnetic disk storage media, optical storage media, flash memory devices or other types of machine-accessible storage media. The storage unit stores at least the data that may be required by one or more units of the system to perform their respective functions.

[0042] As used herein “interface” or “user interface refers to a shared boundary across which two or more separate components of a system exchange information or data. The interface may also be referred to a set of rules or protocols that define communication or interaction of one or more modules or one or more units with each other, which also includes the methods, functions, or procedures that may be called.

[0043] All modules, units, components used herein, unless explicitly excluded herein, may be software modules or hardware processors, the processors being a general-purpose processor, a special purpose processor, a conventional processor, a digital signal processor (DSP), a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits (ASIC), Field Programmable Gate Array circuits (FPGA), any other type of integrated circuits, etc.

[0044] As used herein the transceiver unit include at least one receiver and at least one transmitter configured respectively for receiving and transmitting data, signals, information, or a combination thereof between units / components within the system and / or connected with the system.

[0045] As discussed in the background section, the current known solutions have several shortcomings. The present disclosure aims to overcome the above-mentioned and other existing problems in this field of technology by providing method and system for regulating an energy consumption in a Heterogeneous Network (HetNet) environment. The present solution utilises automatically switching for activating or deactivation of the one or more cell sites for regulating the energy consumption by deactivating the one or more cell sites and transferring the one or more users to the neighbouring cell sites and saving the power of that one or more cell sites based on parameters such as traffic levels, network performance, energy consumption, etc.

[0046] Referring to FIG. 1A which illustrates an exemplary system architecture

[0100] for regulating energy consumption in a Heterogeneous Network (HetNet) environment, in accordance with exemplary implementations of the present disclosure. The HetNet environment comprises one or more layers which interact with each other in order to regulate energy consumption in the HetNet environment. The one or more layers include a radio access network (RAN) layer

[0114] , a network management layer

[0106] , an intelligent platform layer / a near-real-time radio intelligent control (NRT-RIC) layer

[0102] , and a service management and orchestration (SMO) layer / a selforganizing network (SON) layer

[0104] , The RAN layer

[0114] communicates with the SMO layer / the SON layer

[0104] via a centralised self-organizing network (CSON) interface

[0156] , The network management layer

[0106] , the intelligent platform layer / the NRT-RIC layer

[0102] , and the SMO layer / the SON layer

[0104] functions in conjunction with each other. Further, NRT-RIC layer

[0102] may exchange control signals and receive instructions from the network management layer

[0106] to orchestrate and optimize the RAN operations. The network management layer

[0106] interfaces with the radio access network layer

[0114] ,

[0047] The RAN Layer

[0114] comprises a combined centralized and distributed unit (CCDU)

[0116] and an open radio access network radio unit (O-RU)

[0136] , The CCDU

[0116] and the O-RU

[0136] are connected with each other via an open front haul (OFH) / a management plane (M-Plane)

[0134] , The CCDU

[0116] is a unit which performs the operation for both a centralized unit and a decentralized unit and handles both the higher layers and the lower layers of a protocol stack, which includes the higher / upper physical layer

[0128] , a media access control (MAC) layer

[0126] , and a radio link control (RLC) layer

[0124] and also a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, and a radio resource control (RRC) layer. The O-RU

[0136] is a component of O-RAN networks that perform the function of radio access nodes and connects the user equipment with the wireless communication network. The M-Plane

[0134] is an interface which is responsible for managing the O-RU

[0136] ,

[0048] The CCDU

[0116] comprises at least one of a radio resource control packet data convergence protocol - control (RRC PDCP-C)

[0118] , a service data adaptation protocol packet data convergence protocol - user (SDAP PDCP-U)

[0120] , a distributed self-organizing network (DSON)

[0122] , a radio link control RLC layer

[0124] , a medium access control (MAC) layer

[0126] , an upper physical layer

[0128] , an open radio access network - centralized unit - user - plane (ORAN-C-U-S Plane)

[0130] , and an open radio access network management plane (0-RAN M- Plane)

[0132] , The RRC PDCP-C

[0118] comprises of the Radio Resource Control protocol (RRC) and the Packet Data Convergence Protocol - Control (PDCP-C). The RRC manages radio resources like assigning channels and power. Further, the Packet Data Convergence Protocol - Control (PDCP-C) prepares data for transmission (PDCP-C for control data, PDCP-U for user data). The Distributed Self-Organizing Network (DSON)

[0122] allows the network to automatically optimize itself without manual intervention. Further the PDCP-C

[0118] is located in the air interface on the top of the RLC layer

[0124] , The Radio Link Control (RLC) layer

[0124] ensures reliable data delivery over the radio link.

[0049] Further, the Medium Access Control (MAC) layer

[0126] , manages how different devices share the radio channel. Further, the higher / upper physical layer

[0128] transmits and receives raw radio signals. Furthermore, the ORAN-C-U-S Plane

[0130] splits the processing between a central unit and distributed units for user data handling. Moreover, the 0-RAN M-Plane (Management Plane)

[0132] manages the overall network configuration.

[0050] The O-RU

[0136] comprises at least one of the ORAN-C-U-S Plane

[0130] , the O-RAN M- Plane

[0132] , an inverse fast fourier transform / preamble format (IFFT / PRACH) Precoding

[0138] , a cyclic prefix (CP) Addition

[0140] , a digital beamforming (digital BF)

[0142] , a digital predistortion (DPD)

[0144] , a channel frequency response (CFR)

[0146] , a digital up converter (DUC) / a digital down converter (DDC)

[0148] , a Power Amplifier (PA) / a low-noise amplifier (LNA)

[0150] , an analog-digital converter (ADC) / a digital-analog converter (DAC)

[0152] , a duplexer / a circulator

[0154] ,

[0051] The IFFT / PRACH Precoding

[0138] comprises of the Inverse Fast Fourier Transform (IFFT) and the Preamble Format (PRACH) Precoding. The Inverse Fast Fourier Transform (IFFT) converts frequency-domain data into time-domain signals, essential for OFDM (Orthogonal Frequency Division Multiplexing) transmission. Further, the Preamble Format (PRACH) Precoding, prepares the random-access preamble for transmission, enabling initial access andsynchronization between the UE and the network. Further, the Channel Frequency Response (CFR)

[0146] measures and characterizes how the transmitted signal is altered by the propagation channel. This information is used to compensate for channel impairments and to improve signal quality. The Cyclic Prefix (CP) Addition

[0140] , adds a cyclic prefix to each OFDM symbol to mitigate inter-symbol interference (ISI) caused by multipath propagation. This enhances the robustness of the transmitted signal. Moreover, the digital BF (Beamforming)

[0142] utilizes digital signal processing to direct the transmission and reception of signals in specific directions, improving signal strength and reducing interference. This enhances overall network performance and coverage.

[0052] The DPD

[0144] is a baseband signal processing technique that corrects the impairments in RF power amplifiers (PAs). The digital up converter (DUC)

[0148] is a device which translates a signal from baseband to intermediate frequency (IF) band, and the digital down converter (DDC)

[0148] is a device which converts a signal from intermediate frequency band to baseband. The PA

[0150] is a type of electronic amplifier that converts a low-power radio-frequency (RF) signal into a higher-power signal. The LNA

[0150] is a component at the front-end of a radio receiver circuit which reduces the unwanted noises in the radio signal. The ADC

[0152] is a device that converts an analogue signal into a limited number of digital output codes and the DAC

[0152] is a device that converts a limited number of digital output codes into an analogue signal. The duplexer

[0154] is an electronic device that allows bi-directional (duplex) communication over a single path and isolates the receiver from the transmitter while permitting them to share a common antenna. The circulator

[0154] is a passive, non-reciprocal three-port or four-port device that only allows a microwave or radio-frequency (RF) signal to exit through the port directly after the one it entered.

[0053] The network management layer

[0106] interacts with one or more cell sites such as of an outdoor small cell (ODSC)

[0160] , an indoor small cell (IDSC)

[0162] , or a macro next generation node base station (gNB)

[0164] , The network management layer

[0106] , as shown in FIG. 1A, comprises at least a fault management and alarm handing (FM) module

[0108] , a performance management (PM) module

[0110] , and a configuration management (CM) module

[0112] , and is also responsible for performing the functions illustrated in the FIG. 1A, such as infrastructure key performance measurements (Infrastructure KPMs), centralized unit key performance measurements (CU KPMs), media access control key performance measurements (MAC KPMs), and software upgrades. The Key Performance Indicators (KPIs) enables assessment of the overall energy consumption across the network and derive corresponding energy efficiency metrics. Thesoftware upgrades may refer to an upgrade / update of the firmware or software provided in the one or more network nodes for their smooth functioning.

[0054] The Infrastructure KPMs are the key performance measurements used for analysing / assessing the performance of the network infrastructure. The Infrastructure KPMs analyses the parameters such as an availability, a utilization, a latency, a throughput, one or more error rates, a power consumption, and a security associated with the network. The availability may be assessed based on a network availability, a system uptime, and a node uptime. The utilization may be assessed based on a utilization of a central processing unit, a memory utilization, a disk utilization, and a network interface utilization. The latency may be assessed based on an infrastructure latency, and an end-to-end latency. The throughput may be assessed based on a network throughput, and a storage throughput. The one or more error rates may be assessed based on a packet error rate (PER), a bit error rate (BER), and a hardware failure rate. The power consumption may be assessed based on an overall power usage, and a power efficiency. The security may be assessed based on a number of security incidents, and an intrusion detection metric.

[0055] The CU KPMs are the key performance measurements used for analysing / assessing the performance of the centralized unit (CU). The CU KPMs analyses the parameters such as a control plane latency, a user plane latency, a throughput, a mobility management, a session management, one or more error rates, and a load balancing. The control plane latency may be assessed based on both the control plane latency as well as a session setup latency. The user plane latency may be assessed based on both the user plane latency as well as a packet forwarding delay. The throughput may be assessed based on a downlink throughput, and an uplink throughput. The mobility management may be assessed based on a handover success rate, and a handover latency. The session management may be assessed based on a session setup success rate, and a session drop rate. The one or more error rates may be assessed based on a control plane error rate and a user plane error rate. The load balancing may be assessed based on a traffic distribution and a resource utilization.

[0056] The MAC KPMs are the key performance measurements used for analysing / assessing the performance of a medium access control elements. The MAC KPMs analyses the parameters such as a resource block utilization, a latency, a throughput, one or more error rates, a retransmission metric, a buffer status, a Quality of Service (QoS), and an interference management. The resource block utilization may be assessed based on a physical resource block (PRB) utilization and ascheduling efficiency. The latency may be assessed based on medium access control protocol data unit (MAC PDU) latency and a hybrid automatic repeat request (HARQ) latency. The throughput may be assessed based on a MAC layer throughput and a data rate per user equipment (UE). The one or more error rates may be assessed based on a MAC PDU error rate, and a HARQ retransmission rate. The retransmission metric may be assessed based on a MAC PDU error rate and a HARQ retransmission rate. The buffer state may be assessed based on a buffer occupancy, and a buffer throughput. The QoS may be assessed based on a quality-of-service class identifier (QCI) performance and a QoS scheduling latency. The interference management may be assessed based on an interference level and an interference mitigation efficiency.

[0057] Referring to FIG. IB, an exemplary schematic diagram for regulating energy consumption in the HetNet environment is disclosed in accordance with exemplary implementations of the present disclosure. For Performance Monitoring, a RAN management layer

[0158] (i.e., Intelligent Platform / NRT-RIC Layer

[0102] and the Network Management Layer

[0106] ) collects data for monitoring the performance of the one or more cell sites. The performance monitoring includes monitoring at least the one or more traffic levels, and the predicted one or more traffic levels, a coverage map, etc. For model training, the RAN management layer

[0158] utilizes the AI / ML techniques for effective and efficient functioning of the RAN management layer

[0158] , For predictive analysis, the RAN management layer

[0158] utilizes the historic data associated with one or more traffic levels at the one or more cell sites in the past. The RAN management layer

[0158] is responsible for triggering the one or more cell sites ON or OFF (i.e. power ON or OFF), if the predefined thresholds for the one or more traffic levels is satisfied by the selected cell site, indicating low traffic at a selected cell site (shown as T1<LTS in the FIG. IB) and low traffic at neighbouring cell sites (shown as T2<LTN in the FIG. IB), and also if the coverage hole flag is determined to be zero or absent. T1 is the time taken for monitoring the one or more traffic levels of each cell site and to switch the power on / off if criteria meets for T1 monitoring period. T2 is the time required for monitoring the traffic levels of each cell and for sending reactivation signal if criteria meets for T2 monitoring period. The LTS may refer to low threshold for source. The LTN may refer to the low threshold for neighbours.

[0058] The intelligent platform layer / the NRT-RIC layer

[0102] provides efficient control and optimization / regulation of network functions and services in real-time or near-real-time through fine-grained data collection and actions. The intelligent platform layer / the NRT-RIC layer

[0102] performs scenario identification, predictive analysis of one or more traffic levels, parameter optimization for example, regulating energy consumption by optimizing power usage of the oneor more cell sites, training of an AI / ML model based on AI / ML techniques and data aggregations. The scenario identification may be done by identifying the radio frequency of the candidate cell sites, and the one or more neighbouring cell sites. The data aggregation may be done based on the PRB utilisation. The predictive analysis of the one or more traffic levels is predicting the one or more traffic levels in the upcoming time period for identifying which of the one or more cell sites is going to have a lower traffic level or no traffic level in the upcoming time period. For model training, data aggregation and predictive analysis is used and machine learning techniques are applied on the data aggregation and the predictive analysis. The parameter optimization may be regulating energy consumption by optimizing power usage of the one or more cell sites.

[0059] The intelligent platform layer / the NRT-RIC layer

[0102] collects site data base, configuration parameters from a configuration management (CM) module

[0112] , performance counters from a performance management (PM) module

[0110] and alarms from the fault management (FM) module

[0108] from all elements from the RAN layer via the network management layer

[0106] , The CM module

[0112] may be responsible for management of configuration data such as cell administrative state. The PM module

[0110] may be responsible for management of performance management data such as PR Utilisation, RRC users, active users, total traffic (both uplink and downlink). The FM module

[0108] may be responsible for management of fault management data such as service affecting alarms. The FM module

[0108] , the PM module

[0110] , and the CM module

[0112] , are used in conjunction with Open radio Access Network Radio Intelligent Controller (ORAN RIC) for determination of decisions associated with regulation of energy consumption.

[0060] The service management and orchestration (SMO) layer

[0104] manages the components and network functions of an open RAN. The self-organizing network (SON) layer

[0104] comprises an automation technology designed to make the planning, configuration, management, optimization, and healing of mobile radio access networks in a simpler and faster way. The SMO layer / SON layer

[0104] is responsible for making / implementing policies, models and slicing the network, and also performing the functions for user session management, medium access / radio management, device downlink / uplink management, data acquisition. The SON layer

[0104] acts as a central intelligence controller, communicating with the network management layer

[0106] , CCDU

[0116] , and O-RU

[0136] through standardized interfaces and incorporates above mentioned AI / ML policies to make intelligent decisions for optimizing network performance, resource allocation, and energy efficiency. The macro gNBs

[0164] / ODSC

[0160] / IDSC

[0162] integrate with the SON / SMO layer

[0104] directly. The SON layer

[0104] houses SON techniques for networkoptimization, acting as the brain. It leverages a network operator platform for other vendor gNBs and interfaces directly with such gNBs from other vendors network operator through its network management layer

[0106] for its nodes.

[0061] For implementing policies and models, the SMO layer / SON layer

[0104] implements network policies and models that define how the network resources should be allocated and managed. This includes setting quality of service (QoS) parameters, traffic prioritization, and other operational guidelines. For network slicing, the SMO layer / SON layer

[0104] is used for creating virtual networks (slices) that cater to specific services or user groups with customized requirements. This capability allows efficient resource utilization and service differentiation. For user session management, the SMO layer / SON layer

[0104] manages user sessions within the network, for ensuring seamless connectivity and handover between different network segments or technologies (e.g., 4G to 5G).

[0062] For Medium Access or Radio Management, the SMO layer / SON layer

[0104] optimises the medium access and radio resources to enhance network efficiency and performance. This includes scheduling transmissions, managing interference, and optimizing power levels. For Device Uplink and Downlink Management, the SMO layer / SON layer

[0104] handles the management of data transmissions between user devices and the network, and ensures efficient use of uplink and downlink resources based on traffic demands and user requirements. For Data Acquisition and Analysis, the SMO layer / SON layer

[0104] collects network performance data and performs analysis to monitor the health of the network, detect anomalies, and optimize resource usage dynamically.

[0063] The present disclosure provides a solution that is implemented in the intelligent platform layer / the NRT-RIC layer

[0102] , It communicates with the network management layer

[0106] to gather network information, performance metrics, and configuration data. It exchanges control signals and receives instructions from the network management layer

[0106] to orchestrate and optimize the RAN operations.

[0064] Also, the RAN management layer

[0158] is also responsible for performing the functions, as illustrated in the FIG. IB, such as data collection, performance monitoring (predicted traffic level, actual traffic level and coverage map), predictive analysis, parameter optimization, scenario identification, managing AI / ML techniques, model training, data aggregation, and configuration management etc. At step SI, illustrated as PM Data Collection in the FIG. IB, the RANmanagement layer

[0158] collects data associated with one or more traffic levels at the one or more cell sites for the data collection. Thereafter, at step S2, the RAN management layer

[0158] triggers the one or more cell sites in the RAN layer

[0114] OFF based on the predictive analysis by the RAN management layer

[0158] , Then, at step S3, the RAN layer

[0114] sends an acknowledgement to the RAN management layer

[0158] with regard to the power status of the one or more cell sites in the RAN layer

[0114] , Then, at step S4, the RAN management layer

[0158] again collects the data associated with the one or more traffic levels to check for any changes in the one or more traffic levels. Then at step S5, if the one or more traffic levels are increased at the one or more cell sites, then the RAN management layer

[0158] reactivates the one or more cell sites by sending a wakeup signal to the RAN layer

[0114] , wherein the step S5 is performed if the one or more traffic levels at the neighbouring cell sites is more than the predefined threshold for the neighbouring cell sites (shown as T2>LTN in the FIG. IB). Thereafter, at step S6, the RAN management layer

[0158] keeps collecting the data associated with the one or more traffic levels for triggering the one or more cell sites OFF for regulating energy consumption based on the one or more traffic levels.

[0065] FIG. 2 illustrates an exemplary block diagram of a computing device

[0200] upon which the features of the present disclosure may be implemented in accordance with exemplary implementation of the present disclosure. In an implementation, the computing device

[0200] may also implement a method for regulating energy consumption in a Heterogeneous Network (HetNet) environment utilising the system. In another implementation, the computing device

[0200] itself implements the method for regulating energy consumption in a Heterogeneous Network (HetNet) environment using one or more units configured within the computing device

[0200] , wherein said one or more units are capable of implementing the features as disclosed in the present disclosure.

[0066] The computing device

[0200] may include a bus

[0202] or other communication mechanism for communicating information, and a hardware processor

[0204] coupled with bus

[0202] for processing information. The hardware processor

[0204] may be, for example, a general-purpose microprocessor. The computing device

[0200] may also include a main memory

[0206] , such as a random-access memory (RAM), or other dynamic storage device, coupled to the bus

[0202] for storing information and instructions to be executed by the processor

[0204] , The main memory

[0206] also may be used for storing temporary variables or other intermediate information during execution of the instructions to be executed by the processor

[0204] , Such instructions, when stored in non-transitory storage media accessible to the processor

[0204] , render the computing device

[0200] into a special-purpose machine that is customized to perform the operations specified in the instructions. The computing device

[0200] further includes a read only memory (ROM)

[0208] orother static storage device coupled to the bus

[0202] for storing static information and instructions for the processor

[0204] ,

[0067] A storage device

[0210] , such as a magnetic disk, optical disk, or solid-state drive is provided and coupled to the bus

[0202] for storing information and instructions. The computing device

[0200] may be coupled via the bus

[0202] to a display

[0212] , such as a cathode ray tube (CRT), Liquid crystal Display (LCD), Light Emitting Diode (LED) display, Organic LED (OLED) display, etc. for displaying information to a computer user. An input device

[0214] , including alphanumeric and other keys, touch screen input means, etc. may be coupled to the bus

[0202] for communicating information and command selections to the processor

[0204] , Another type of user input device may be a cursor controller

[0216] , such as a mouse, a trackball, or cursor direction keys, for communicating direction information and command selections to the processor

[0204] , and for controlling cursor movement on the display

[0212] , The input device typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allow the device to specify positions in a plane.

[0068] The computing device

[0200] may implement the techniques described herein using customized hard-wired logic, one or more ASICs or FPGAs, firmware, and / or program logic which in combination with the computing device

[0200] causes or programs the computing device

[0200] to be a special-purpose machine. According to one implementation, the techniques herein are performed by the computing device

[0200] in response to the processor

[0204] executing one or more sequences of one or more instructions contained in the main memory

[0206] , Such instructions may be read into the main memory

[0206] from another storage medium, such as the storage device

[0210] , Execution of the sequences of instructions contained in the main memory

[0206] causes the processor

[0204] to perform the process steps described herein. In alternative implementations of the present disclosure, hard-wired circuitry may be used in place of or in combination with software instructions.

[0069] The computing device

[0200] also may include a communication interface

[0218] coupled to the bus

[0202] , The communication interface

[0218] provides a two-way data communication coupling to a network link

[0220] that is connected to a local network

[0222] , For example, the communication interface

[0218] may be an integrated services digital network (ISDN) card, cable modem, satellite modem, or a modem to provide a data communication connection to a corresponding type of telephone line. As another example, the communication interface

[0218] may be a local area network (LAN) card to provide a data communication connection to a compatibleLAN. Wireless links may also be implemented. In any such implementation, the communication interface

[0218] sends and receives electrical, electromagnetic, or optical signals that carry digital data streams representing various types of information.

[0070] The computing device

[0200] can send messages and receive data, including program code, through the network(s), the network link

[0220] and the communication interface

[0218] , In the Internet example, a server

[0230] might transmit a requested code for an application program through the Internet

[0228] , the ISP

[0226] , the local network

[0222] , the host

[0224] and the communication interface

[0218] , The received code may be executed by the processor

[0204] as it is received, and / or stored in the storage device

[0210] , or other non-volatile storage for later execution.

[0071] Referring to FIG. 3, an exemplary block diagram of a system

[0300] for regulating energy consumption in a Heterogeneous Network (HetNet) environment, is shown, in accordance with the exemplary implementations of the present disclosure. The system

[0300] comprises at least one processing unit

[0302] and at least one identification unit

[0304] , Further, in some implementations, the system

[0300] may also be provided with a storage unit, that may also be used for implementation of the present disclosure. Also, all of the components / units of the system

[0300] are assumed to be connected to each other unless otherwise indicated below. As shown in the figures all units shown within the system

[0300] should also be assumed to be connected to each other. Also, in FIG. 3 only a few units are shown, however, the system

[0300] may comprise multiple such units or the system

[0300] may comprise any such numbers of said units, as required to implement the features of the present disclosure. In an implementation, the system

[0300] may reside in a server or a network entity.

[0072] The system

[0300] is configured for regulating an energy consumption in a Heterogeneous Network (HetNet) environment, with the help of the interconnection between the components / units of the system

[0300] , The regulation of energy consumption is optimisation of the consumption of energy by the network components within the HetNet environment. The optimisation may be done by altering the operation of the network components. The HetNet environment is an environment in which multiple types of wireless networks are present which may use different kinds of radio access technologies (RATs). For example, a network environment where a wireless network that provides a service through a wireless local area network (WLAN) and where said wireless network is able to maintain the service when switching to a cellular network is called a wireless heterogeneous network.

[0073] For regulating the energy consumption, initially the processing unit

[0302] is configured to monitor one or more traffic levels at one or more cell sites in a network region, wherein said monitoring corresponds to evaluating a set of Key Performance Indicators (KPIs) associated with the one or more cell sites. The one or more traffic levels may refer to the levels of traffic at the one or more cell sites i.e., the number of user equipment connected to one or more base stations located in said one or more cell sites and / or the amount of data / transactions between the user equipment and the one or more base stations located in said one or more cell sites. For instance, the one or more traffic levels may be high, average, or low and may also be minimal traffic level or no traffic level, which can be based on an amount of traffic at the one or more cell sites at any period of time. The one or more cell sites may refer to the entire set of equipment(s) needed to receive and transmit radio signals for cellular voice and data transmission. The network region may refer to a geographical area for which the energy consumption is required to be regulated. The monitoring of the one or more traffic levels at the one or more cell sites in the network region is done by evaluation of the set of KPIs and wherein said monitoring helps in identification of usage of the one or more cell sites, and in monitoring which of the one or more cell sites can be regulated for energy consumption. The set of KPIs may include but not limited to at least one of a Physical Resource Block (PRB) Utilization, a number of Radio Resource Control (RRC) Users and a number of active users, a Cell effective throughput, and a Total traffic (Uplink and Downlink). The PRB utilization provides an average number of subcarriers allocated to users across all cell sites over a period of time and provides an indicator associated with network utilization. The number of RRC users and the number of active users respectively provide the number of UEs

[0102] : which are actively or inactively in connection with the one or more cell sites at a particular period of time, and which are actively in connection with the one or more cell sites at the particular period of time. A higher number of the RRC users and active users may indicate towards high usage or high traffic at the one or more cell sites and which may indicate that the one or more cell sites should not be regulated for maintaining the Quality of Service (QoS) as such regulation may lead to automatic switching between the power ON or OFF of the one or more cell sites which will impact the services provided to the users. The cell effective throughput may refer to the amount of data moved in the one or more cell sites. A higher cell effective throughput may indicate that the one or more cell sites is currently in use and should not be regulated for maintaining the Quality of Service (QoS) provided by the one or more cell sites. The total traffic indicates the amount of uplink traffic and the amount of downlink traffic in the one or more cell sites. A higher total traffic may further indicate that the one or more cell sites is currently under use and should not be regulated for maintaining the QoS.

[0074] Once, the one or more traffic levels are monitored, then next the processing unit

[0302] is configured to predict the one or more traffic levels associated with each of the one or more cell sites. The prediction of the one or more traffic levels is done for predicting the one or more traffic levels in the upcoming time period to identify which of the one or more cell sites is going to have a lower traffic level or no traffic level in the upcoming time period.

[0075] After the prediction of the one or more traffic levels for each of the one or more cell sites, next the processing unit

[0302] is configured to identify, via the identification unit

[0304] , a candidate cell site and a set of neighbouring cell sites based on the predicted one or more traffic levels. The candidate cell site may be a cell site for which the power consumption is required to be regulated. The set of neighbouring cell sites are the one or more cell sites which are around the candidate cell site. Further, to identify the candidate cell site and the set of neighbouring cell sites, the processing unit

[0302] is configured to evaluate a measurement range of a signal strength and a site location, based on one or more variations in one or more traffic level patterns over a time, a day of week, and one or more seasonal changes. The identification of the candidate cell site and the set of neighbouring cell sites is therefore based on many factors such as including but not limited to the measurement range of the signal strength, the site location, and the one or more traffic level patterns. The site location refers to a geolocation of the geographical region for the one or more cell sites for which the energy consumption is required to be regulated, this geolocation would help in determination of the surrounding or nearby one or more cell sites which are around the candidate cell. The candidate cell site can be identified based on the one or more traffic level patterns over different period of time, and the period of time can be over a day of the week, over a season and over some pre-defined time. The one or more variations in the one or more traffic level patterns indicate a change in the pattern of the one or more traffic levels over a particular period of time, which may be an increase in the one or more traffic levels, a decrease in the one or more traffic levels, and no change in the one or more traffic level patterns. The one or more traffic level patterns are based on the above-disclosed prediction for the one or more traffic levels which indicates that at the particular time, or the particular day of week or in the particular one or more season there exists the one or more variations in the one or more traffic levels. In case the one or more variations in the one or more traffic level patterns indicate a significant reduction in the one or more traffic levels, then it may help in identification of the candidate cell site from the one or more cell sites. More specifically, in an event when there is a significant reduction in the one or more traffic levels of a cell site, then such cell site is identified as the candidate cell site and said candidate cell site is used for the regulation of the energy consumption.

[0076] Next, after the identification of the candidate cell sites and the neighbouring cell sites, the processing unit

[0302] is further configured to determine a coverage hole flag associated with the identified candidate cell site and the set of neighbouring cell sites. The coverage hole flag is an indicator or alert for indicating that there exists a region in the network coverage region at which there is no coverage, i.e., there is no usable signal strength for availing the services provided by the communication network. The coverage hole flag may be a numeric constant, alphanumeric constant and / or like format that is obvious to a person skilled in the art. The identification of the coverage hole and determining a coverage hole flag enables the check for identifying if there is no coverage in certain geographical regions due to which it can be confirmed that the regulation of energy consumption for the candidate cell site does not result in absence of coverage for that particular region. The present disclosure aims to regulate the energy consumption but if regulation of the energy consumption would lead to coverage issues, then it would be undesirable to the service providers as well as the consumers of the service.

[0077] In order to determine the coverage hole flag, the processing unit

[0302] is further configured to evaluate a planning data and a crowdsourcing data comprising one or more parameters, wherein the one or more parameters comprises at least of a best server plot (latitude and longitude of a site location) and a signal strength, to tag one or more areas with a received signal strength less than - 110 as one or more potential coverage holes. The coverage hole flag is raised based on the evaluation of the planning data and the crowdsourcing data. The planning data is observed from the one or more parameters which may be the best server plot and the signal strength of each of the one or more cell sites. The best server plot may be identified based on the latitude and longitude of a site location (i.e., the geographical region of the one or more cell sites). The signal strength may be the reference signal received power (RSRP). The crowdsourcing data may be the data sourced from the public or from one or more users that are connected with the candidate cell site. The crowdsourcing data comprises a user location, an identifier associated with the candidate cell site, and signal strength in terms of RSRP of the candidate cell site. The best server plot may refer to a graphical representation that is used in telecommunications for analysing the coverage and the signal strength across the telecommunications network. The best server plot may be used for distribution of signal strengths from different base stations or access points, helping network planners optimize coverage, manage handovers, plan capacity, and improve overall network performance. The best server plot also helps in identifying areas with weak signals, optimizing resource allocation, and enhancing user experience by ensuring seamless connectivity and service quality.

[0078] Moreover, for evaluation of the coverage hole flag, after obtaining the planning data and the crowdsourcing data, a smart network layer is created to improve the best server plot or the site location. Then, the candidate cell site is identified for which an impact of the coverage hole is calculated. Thereafter, a cell site coverage layer is disabled and a new coverage layer is created within the area of the deactivated cell site. After this, one or more bins are identified and consolidated that have a signal strength less than -110 and then these one or more bins are tagged as coverage holes. Based on this identification one or more potential coverage holes are further identified and validated with the field measurements using the crowdsource data. The evaluation of the coverage hole flags may be done periodically, such as over a period of a week, over a period of month, etc.

[0079] Consider an example, if the coverage hole flag is 0 then it is indicative that the candidate cell site at a site location even when turned / switched off may still be covered by the other neighbouring cell sites. Thereby, at non-peak hours such as at night time the candidate cell site may be turned off without hampering the coverage provided by other neighbouring cell sites.

[0080] After, the determination of a coverage hole flag, the processing unit

[0302] is further configured to automatically switch the power ON or power OFF, of the identified candidate cell site based on the determined coverage hole flag to regulate the energy consumption. The automatically switching, by the processing unit

[0302] , between the power ON state and the power OFF state of the identified candidate cell site maintains a pre-defined operational criterion associated with the HetNet environment. The identified candidate cell site is switched ON or OFF (i.e. power ON or power OFF) based on whether the switching the power OFF of the candidate cell site would lead to raising of the coverage hole flag, if there is no problem of coverage holes, then the candidate cell site is switched OFF. The power ON or power OFF refers to the activation and deactivation, respectively, of the candidate cell site which would lead to altering the operational status of the candidate cell site. The power ON state may refer to the operational status of the cell site, and the power OFF state may refer to the non-operational status of the cell site. The pre-defined operational criterion refers to the operational status of the communication network, and the pre-defined operational criterion of the communication network can be assessed based on the availability of coverage and a Quality of Service provided by the communication network in the HetNet environment or in the network region. The pre-defined operational criterion is also further based on the energy consumption by the one or more candidate cell site, and the set of neighbouring cell sites.

[0081] The present disclosure further discloses that to automatically switch between the power ON state or the power OFF state the identified cell site, the processing unit

[0302] is configured to evaluate a coverage and an overlap impact that occurs when the candidate site is switched OFF or ON to ensure no coverage hole is created that affect user experience. The coverage refers to the geographical area for which the communication network is able to provide service using the one or more cell sites. The overlap impact is the impact caused due to overlap of coverage area by multiple cell sites.

[0082] The present disclosure further discloses that to automatically switch between the power ON state and the power OFF state, the processing unit

[0302] is configured to deactivate the identified candidate cell site. Then the processing unit

[0302] is configured to trigger a handover mechanism to ensure a seamless transition of one or more users to the set of neighbouring cell sites. Thereafter, the processing unit

[0302] is further configured to update a network configuration to reflect deactivation of a macro 5G new radio (NR) node B (gNB). More specifically, the handover mechanism is the mechanism used for transfer of cellular transmission from one or more cell sites to one or more different cell sites, without losing any connectivity between the one or more users and the network. Therefore, this mechanism enables switching of the candidate cell site without having the one or more users to face connection issues with the one or more cell sites, which may degrade Quality of Service and may also affect customer experience. Also, to automatically switch, the network configuration for the one or more cell sites or specifically the candidate cell site is altered to reflect that the candidate cell site is deactivated. The network configuration would then reflect that the candidate cell site which may be the macro 5G new radio (NR) node base station (gNb) has been deactivated.

[0083] The present disclosure further discloses that for regulating the energy consumption in the HetNet environment based on future traffic levels, the processing unit

[0302] is configured to analyse the one or more traffic levels of the one or more cell sites to identify one of a period of minimal traffic level and a period of no traffic level. The period of minimal traffic level is a period where the one or more traffic levels are minimal traffic level or low traffic level. The period of no traffic level is the period where the one or more traffic levels are non-existent i.e. no traffic level.

[0084] After analysing the one or more traffic levels, the processing unit

[0302] is further configured to evaluate the energy consumption during one of the identified period of minimal traffic level and the period of no traffic level, wherein the energy consumption is evaluated against a predefined efficiency threshold. The evaluation is done based on the energy consumption at theperiod of minimal traffic level and the period of no traffic level in order to ascertain whether the deactivation of the candidate cell site would be able provide significant effect for regulation of energy consumption, i.e., determining if the switching would be efficient or not. For example, if in case of period of minimal traffic level, the energy consumption by the candidate cell site is not very high, and deactivation would not result in significant reduction in energy consumption, then it may be determined that deactivation is not required since it would not be efficient. Further, the predefined efficiency threshold is a threshold limit for determining whether the energy consumption of the candidate cell site is high. If the energy consumption reaches the predefined efficiency threshold, then it may be determined that the energy consumption by the candidate cell site is high, which can be regulated for achieving efficient regulation of the energy consumption. For example, the predefined efficiency threshold for PRB Utilization of top 3 neighbouring cell sites should be less than 70%. In another example, the predefined efficiency threshold for PRB Utilization of the candidate cell site should be less than 10 percent.

[0085] For determining whether the switching would be efficient or not, the energy efficiency may be determined based on the following formula:

[0086] The EE scenario i may refer to the energy efficiency in a scenario. The Vz may refer to the aggregated throughput in a served measured area / Cell for a traffic level, say 1. The Vz may also be associated with a served traffic volume divided by the measurement period. The Vz may be calculated in megabytes per second (Mbps). The ECz may refer to the sum of the average power consumption of all nodes in the simulated or the measurement area under the load level 1 / varied traffic pattern. The ECz may be calculated in watts.

[0087] Further, for the identification of power consumption in an area, a power per area unit metric may be calculated, which may be a network average power usage (P) divided by the coverage area of the network (A) and may be expressed in the unit [W / m2], Power per area unit is further a very relevant quantity at low traffic loads, as in this case the network is coverage limited rather than capacity limited.

[0088] Based on the evaluation of the energy consumption, the processing unit

[0302] is further configured to predict one of a target period of minimal traffic level and a target period of no traffic level, based on one or more historical traffic patterns and an associated energy usage. The target period of minimal traffic level may refer to a period of time in future where the one or more trafficlevels are minimal traffic level or low traffic level. The target period of no traffic level may refer to a period of time in future where the one or more traffic levels are non-existent i.e. no traffic level. The associated energy usage refers to the energy consumption by the one or more cell sites in a future period of time.

[0089] After the prediction of the target traffic levels, the processing unit

[0302] is further configured to adjust the automatically switching between the power ON state or the power OFF state of the identified candidate cell site during one of, the predicted target period of minimal traffic level and the predicted target period of no traffic level. Once, the target period of minimal traffic level or the target period of no traffic level is predicted, then based on the prediction, the candidate cell site may be deactivated for regulating the energy consumption.

[0090] The present disclosure further discloses that to predict the one or more traffic levels associated with each of the one or more cell sites, the processing unit

[0302] is further configured to implement one or more supervised machine learning techniques comprising at least a support vector technique implemented via a Support Vector Machine (SVM). The support vector technique is implemented to anticipate a user data based on a historical traffic data, a day of week, and a time, utilizing a kernel function to consider both a spatial distance and a temporal distance between one or more data points. The one or more supervised machine learning techniques may refer to the techniques that uses labelled datasets to train algorithms to predict outcomes and recognize patterns. In one implementation, the processing unit

[0302] may also be used for predicting based on one or more unsupervised machine learning. The one or more supervised machine learning techniques may refer to the techniques in which models are not supervised using a specific training dataset, and the model itself finds the hidden patterns and insights from the given data. The one or more Support Vector Machine (SVM) is a supervised machine learning algorithm used for both classification and regression. The historical traffic data is the data related to the one or more traffic levels at the one or more cell sites in the past. The spatial distance is the length of the path chosen to move from one point in space to another point. The temporal distance is the amount of time that separates a present time and the predicted target period. The kernel function is function which maps points or vectors from one feature space to another space. The one or more data points may be a present period of time and the future period of time. The user data may refer to a data associated with crowd source data, a data associated with the minimization of drive tests, and a data associated with a network resource and a service level.

[0091] The data associated with crowd source data may refer to the information collected from a large number of users or devices within a network to understand real-time network performance and user experiences. The data associated with crowd source data helps to identify network issues, optimize the coverage and the capacity, and also improves the quality of service based on actual user data.

[0092] The data associated with the minimization of drive tests may refer to the data used for application of a technique for collection of network performance data without traditional manual drive tests, and reducing operational costs and time. The data associated with the minimization of drive tests enables continuous monitoring of network parameters such as the coverage and the quality, thereby supporting proactive optimization and compliance with service level agreements.

[0093] The data associated with the network resource and the service level may refer to the standards and metrics which defines the quality and availability of the network resources and services in 5G networks. The data associated with the network resource and the service level guides network design, deployment, and management to ensure consistent service delivery, optimize resource allocation, and meet customer expectations.

[0094] The Support Vector Machine (SVM) based model can be trained using a given training dataset of a historical data (x<) with additional features for the one or more variations such as a data of the week (d,) and a time (t) and corresponding traffic levels yt).

[0095] In one example, the kernel function such as the RBF kernel, may be selected, based on:)As provided above, k denotes the RBF Kernel. The RBF kernel may be a radial basis function kernel or a Gaussian kernel that operates by measuring the similarity between data points based on their Euclidean distance in the input space. Further, x(, di, ti, and y< may refer to a first set of samples used for RBF Kernel. The Xi may refer to the historical data, the di may refer to the data of the week, the t may refer to the time, and y< may refer to the corresponding traffic levels. Further, xj, dj,tj, and y / may refer to a second set of samples used for RBF kernel. The xj may refer to the historical data, the d, may refer to the data of the week, the tj may refer to the time, and yzmay refer to the corresponding traffic levels. The c may refer to the standard deviation and may alsobe a free parameter. The y is calculated using the formula y = The —I2I | dj | , |tj — tj |2may refer to the squared Euclidean distance between the two feature vectors. The exp may refer to the exponential function associated with the kernel function.

[0096] Thereafter, solving the SVM optimization problem to find a weight vector (w) and a bias term (b) by using the formula: min 0.5The <t> may refer to the implicit mapping embedded in the RBF Kernel. The solution to the SVM optimization problem for training the model is subject to fulfilment of the condition that for all training samples. The w is the weight factor and b is the bias term which are determined by using the above formula. The bias term may refer to an incorrect assumption in which some aspects of a dataset are given more weight and / or representation than other. In other words, the bias term may be the error between an average model prediction and the ground truth. The condition is provided by the following formula: ytX ((w, <f> (Xj, dt, ti)) + b) > 1.

[0097] Then, calculating the predicted traffic load (f(x)) using the weight vector, bias term, and kernel function by using the following formula: (x, d, t) = (w, <f> (x, d, t)) + b.The (x, d, t) represents the feature mapping to the higher-dimensional space including x, d, and t. The w is the weight factor, and b is the bias term. The bias term may refer to an incorrect assumption in which some aspects of a dataset are given more weight and / or representation than other. In other words, the bias term may be the error between an average model prediction and the ground truth. The x may refer to the historical data, the d may refer to the data of the week, the t may refer to the time, and y may refer to the corresponding traffic levels.

[0098] Thus, the SVM machine learning model can be trained based the abovementioned technique and then can be used for prediction based on the above.

[0099] In an implementation, the SVM machine learning model can be used for prediction, based on a given new input of historical traffic data (xnew) with the corresponding day of the week (dnew) and time (tnew), the predicted traffic load (ypred) can be calculated using the learned SVM model.

[0100] Firstly, calculating the kernel function values between (xnew, dnew, tnew) and the support vectors in the training set using the formula:As provided above, k denotes the RBF Kernel. The RBF kernel may be a radial basis function kernel or a Gaussian kernel that operates by measuring the similarity between data points based on their Euclidean distance in the input space. Further, xt, di, ti, and y< may refer to a first set of samples used for RBF Kernel. The Xi may refer to the historical data, the di may refer to the data of the week, the t may refer to the time, and y< may refer to the corresponding traffic levels. Further, Xnew, dnew, tnew, and ynew may refer to a second set of samples used for RBF kernel. The xnew may refer to the historical data, the dnew may refer to the data of the week, the tnew may refer to the time, and ynew may refer to the corresponding traffic levels. The c may refer to the standard deviation and may also be a free parameter. The y is calculated using the formula y = — Themay refer to the squared Euclidean distance between the two feature vectors. The exp may refer to the exponential function associated with the kernel function.

[0101] Then, computing the predicted traffic load by using the formula:The o are the Lagrange multipliers which are obtained during the training of the SVM model. The b is the bias term. The bias term may refer to an incorrect assumption in which some aspects of a dataset are given more weight and / or representation than other. In other words, the bias term may be the error between an average model prediction and the ground truth. The ypredis the predicted traffic load. As provided above, k denotes the RBF Kernel. The RBF kernel may be a radial basis function kernel or a Gaussian kernel that operates by measuring the similarity between data points based on their Euclidean distance in the input space. Further, x(, di, t, and y< may refer to a first set of samples used for RBF Kernel. The Xi may refer to the historical data, the di may refer to the data of the week, the t may refer to the time, and y< may refer to the corresponding traffic levels. Further, Xnew, dnew, tnew, and ynew may refer to a second set of samples used for RBF kernel. The xnew may refer to the historical data, the dnew may refer to the data of the week, the tnew may refer to the time, and ynew may refer to the corresponding traffic levels.

[0102] It may be noted that the above-mentioned formulas, equations, and the values of the variables used in the respective formulas / equations for calculation, training of the model, and prediction of one or more traffic levels are only exemplary, and in no manner to be construed to limit the scope of the present subject matter. Any other techniques known to a person skilled in the art may also be used for calculation and training of the model. All such other examples and techniques would also lie within the scope of the present subject matter.

[0103] Continuing further with the present example, in this modified procedure, the kernel function considers both the spatial distance between historical traffic data points and the temporal distance between the day of the week and time values. This allows the SVM model to capture the dependencies between the traffic level, the day of the week, and the time for more accurate predictions in the telecommunication network.

[0104] The present disclosure further discloses that subsequent to the step of automatically switching, the processing unit

[0302] is further configured to continuously monitor at least one of the one or more traffic levels, a network performance, and a user experience of the set of neighbouring cell sites. The continuously monitoring of the at least one of the one or more traffic levels, the network performance, and the user experience enables assessing of a traffic level distribution and a capacity utilization in the set of neighbouring cell sites, followed by a reactivation of the macro 5G new radio (NR) node B (gNB) of the candidate cell site when the predicted or actual one or more traffic levels of a set of neighbour gNBs corresponding to the set of neighbouring cell sites increases above a predefined threshold. The network performance may refer to the performance or measures of the quality of service in the communication network. The user experience may refer to the experience of the one or more users which are connected with the one or more cell sites, or more particularly connected with the set of neighbouring cell sites. The continuous monitoring is also an important part which helps in keeping a check on the one or more traffic levels of the candidate cell site, and helps in identification of the change in the one or more traffic levels. If there is an increase in the one or more traffic levels, then it is important to activate the candidate cell site for accommodating the increased traffic level. If the candidate cell site is not reactivated then it may lead to overload at the set of neighbouring cell sites which is undesirable, hence it is important to continuously monitor the one or more traffic levels, the network performance, and the user experience at the set of neighbouring cell sites.

[0105] Referring to FIG. 4, an exemplary method flow diagram

[0400] for regulating an energy consumption in a Heterogeneous Network (HetNet) environment, in accordance with exemplary implementations of the present disclosure is shown. In an implementation the method

[0400] is performed by the system

[0300] , Further, in an implementation, the system

[0300] may be present in a server device to implement the features of the present disclosure. Also, as shown in FIG. 4, the method

[0400] starts at step

[0402] ,

[0106] The method for regulating an energy consumption in a Heterogeneous Network (HetNet) environment is described as below. The regulation of energy consumption is optimisation of the consumption of energy by the network components within the HetNet environment. The optimisation may be done by altering the operation of the network components. The HetNet environment is an environment in which multiple types of wireless networks are present which may use different kinds of radio access technologies (RATs). For example, a network environment where a wireless network that provides a service through a wireless local area network (WLAN) and where said wireless network is able to maintain the service when switching to a cellular network is called a wireless heterogeneous network.

[0107] Initially, at step

[0404] , the method comprises monitoring, by a processing unit

[0302] , one or more traffic levels at one or more cell sites in a network region, wherein said monitoring corresponds to evaluating a set of Key Performance Indicators (KPIs) associated with the one or more cell sites. The one or more traffic levels may refer to the levels of traffic at the one or more cell sites i.e., the number of user equipment connected to one or more base stations located in said one or more cell sites and / or the amount of data / transactions between the user equipment and the one or more base stations located in said one or more cell sites. For instance, the one or more traffic levels may be high, average, or low and may also be minimal traffic level or no traffic level, which can be based on an amount of traffic at the one or more cell sites at any period of time. The one or more cell sites may refer to the entire set of equipment(s) needed to receive and transmit radio signals for cellular voice and data transmission. The network region may refer to a geographical area for which the energy consumption is required to be regulated. The monitoring of the one or more traffic levels at the one or more cell sites in the network region is done by evaluation of the set of KPIs and wherein said monitoring helps in identification of usage of the one or more cell sites, and in monitoring which of the one or more cell sites can be regulated for energy consumption. The set of KPIs comprises at least one of a Physical Resource Block (PRB) Utilization, a Number of Radio Resource Control (RRC) Users, a number of active users, a Cell effective throughput, and a Total traffic (Uplink and Downlink). The PRB utilization provides anaverage number of subcarriers allocated to users across all cell sites over a period of time and provides an indicator associated with network utilization. The number of RRC users and the number of active users respectively provide the number of UEs

[0102] : which are actively or inactively in connection with the one or more cell sites at a particular period of time, and which are actively in connection with the one or more cell sites at the particular period of time. A higher number of the RRC users and active users may indicate towards high usage or high traffic at the one or more cell sites and which may indicate that the one or more cell sites should not be regulated for maintaining the Quality of Service (QoS) as such regulation may lead to automatic switching between the power ON state or power OFF state of the one or more cell sites which will impact the services provided to the users. The cell effective throughput may refer to the amount of data moved in the one or more cell sites. A higher cell effective throughput may indicate that the one or more cell sites is currently in use and should not be regulated for maintaining the Quality of Service (QoS) provided by the one or more cell sites. The total traffic indicates the amount of uplink traffic and the amount of downlink traffic in the one or more cell sites. A higher total traffic may further indicate that the one or more cell sites is currently under use and should not be regulated for maintaining the QoS.

[0108] Once, the one or more traffic levels are monitored, then next at step

[0406] , the method

[0400] further comprises predicting, by the processing unit

[0302] , the one or more traffic levels associated with each of the one or more cell sites. The prediction of the one or more traffic levels is done for predicting the one or more traffic levels in the upcoming time period to identify which of the one or more cell sites is going to have a lower traffic level or no traffic level in the upcoming time period.

[0109] After the prediction of the one or more traffic levels for each of the one or more cell sites, next at step

[0408] , the method

[0400] further comprises identifying, by the processing unit

[0302] via an identification unit

[0304] , a candidate cell site and a set of neighbouring cell sites based on the predicted one or more traffic levels. The candidate cell site may be a cell site for which the power consumption is required to be regulated. The set of neighbouring cell sites are the one or more cell sites which are around the candidate cell site. Further, the step of identifying the candidate cell site and the set of neighbouring cell sites comprises evaluating a measurement range of a signal strength and a site location, based on one or more variations in one or more traffic level patterns over a time, a day of week, and one or more seasonal changes. The identification of the candidate cell site and the set of neighbouring cell sites is therefore based on many factors such as including but not limited to the measurement range of the signal strength, the site location, and the one ormore traffic level patterns. The site location refers to a geolocation of the geographical region for the one or more cell sites for which the energy consumption is required to be regulated, this geolocation would help in determination of the surrounding or nearby one or more cell sites which are around the candidate cell. The candidate cell site can be identified based on the one or more traffic level patterns over different period of time, and the period of time can be over a day of the week, over a season and over some pre-defined time. The one or more variations in the one or more traffic level patterns indicate a change in the pattern of the one or more traffic levels over a particular period of time, which may be an increase in the one or more traffic levels, a decrease in the one or more traffic levels, and no change in the one or more traffic level patterns. The one or more traffic level patterns are based on the above-disclosed prediction for the one or more traffic levels which indicates that at the particular time, or the particular day of week or in the particular one or more season there exists the one or more variations in the one or more traffic levels. In case the one or more variations in the one or more traffic level patterns indicate a significant reduction in the one or more traffic levels, then it may help in identification of the candidate cell site from the one or more cell sites. More specifically, in an event when there is a significant reduction in the one or more traffic levels of a cell site, then such cell site is identified as the candidate cell site and said candidate cell site is used for the regulation of the energy consumption.

[0110] Next, after the identification of the candidate cell sites and the neighbouring cell sites, at step

[0410] , the method

[0400] further comprises determining, by the processing unit

[0302] , a coverage hole flag associated with the identified candidate cell site and the set of neighbouring cell sites. The coverage hole flag is an indicator or alert for indicating that there exists a region in the network coverage region at which there is no coverage, i.e., there is no usable signal strength for availing the services provided by the communication network. The coverage hole flag may be a numeric constant, alphanumeric constant and / or like format that is obvious to a person skilled in the art. The identification of the coverage hole and determining a coverage hole flag enables the check for identifying if there is no coverage in certain geographical regions due to which it can be confirmed that the regulation of energy consumption for the candidate cell site does not result in absence of coverage for that particular region. The present disclosure aims to regulate the energy consumption but if regulation of the energy consumption would lead to coverage issues, then it would be undesirable to the service providers as well as the consumers of the service.[OHl] For determining the coverage hole flag the method

[0400] comprises evaluation of a planning data and a crowdsourcing data comprising of one or more parameters, wherein the one or more parameters comprises at least one of a best server plot (latitude and longitude of a sitelocation) and a signal strength, to tag one or more areas with a received signal strength less than - 110 as one or more potential coverage holes. The coverage hole flag is raised based on the evaluation of the planning data and the crowdsourcing data. The planning data is observed from the one or more parameters which may be the best server plot and the signal strength of each of the one or more cell sites. The best server plot may be identified based on the latitude and longitude of a site location (i.e., the geographical region of the one or more cell sites). The signal strength may be the reference signal received power (RSRP). The crowdsourcing data may be the data sourced from the public or from one or more users that are connected with the candidate cell site. The crowdsourcing data comprises a user location, an identifier associated with the candidate cell site, and signal strength in terms of RSRP of the candidate cell site. The best server plot may refer to a graphical representation that is used in telecommunications for analysing the coverage and the signal strength across the telecommunications network. The best server plot may be used for distribution of signal strengths from different base stations or access points, helping network planners optimize coverage, manage handovers, plan capacity, and improve overall network performance. The best server plot also helps in identifying areas with weak signals, optimizing resource allocation, and enhancing user experience by ensuring seamless connectivity and service quality.

[0112] Moreover, for evaluation of the coverage hole flag, after obtaining the planning data and the crowdsourcing data, a smart network layer is created to improve the best server plot or the site location. Then, the candidate cell site is identified for which an impact of the coverage hole is calculated. Thereafter, a cell site coverage layer is disabled and a new coverage layer is created within the area of the deactivated cell site. After this, one or more bins are identified and consolidated that have a signal strength less than -110 and then these one or more bins are tagged as coverage holes. Based on this identification one or more potential coverage holes are further identified and validated with the field measurements using the crowdsource data. The evaluation of the coverage hole flags may be done periodically, such as over a period of a week, over a period of month, etc.

[0113] Consider an example, if the coverage hole flag is 0 then it is indicative that the candidate cell site at a site location even when turned / switched off may still be covered by the other neighbouring cell sites. Thereby, at non-peak hours such as at night time the candidate cell site may be turned off without hampering the coverage provided by other neighbouring cell sites.

[0114] After, the determination of a coverage hole flag, thereafter at step

[0412] , the method

[0400] further comprises automatically switching, by the processing unit

[0302] , between a power ON state and a power OFF state, of the identified candidate cell site based on the determined coverage hole flag to regulate the energy consumption. The automatically switching, by the processing unit, between the power ON state and the power OFF state of the identified candidate cell site maintains a pre-defined operational criterion associated with the HetNet environment. The identified candidate cell site is switched ON or OFF (i.e. power ON or power OFF) based on whether the switching OFF of the candidate cell site would lead to raising of the coverage hole flag, if there is no problem of coverage holes, then the candidate cell site is switched OFF. The power ON or the power OFF refers to the activation and deactivation of the candidate cell site which would lead to altering the operational status of the candidate cell site. The power ON state may refer to the operational status of the cell site, and the power OFF state may refer to the non-operational status of the cell site. The pre-defined operational criterion refers to the operational status of the communication network, and the pre-defined operational criterion of the communication network can be assessed based on the availability of coverage and a Quality of Service provided by the communication network in the HetNet environment or in the network region. The pre-defined operational criterion are also further based on the energy consumption by the one or more candidate cell site, and the set of neighbouring cell sites.

[0115] The present disclosure further discloses that the automatically switching between the power ON state and the power OFF state is further based on evaluating, by the processing unit

[0302] , a coverage and an overlap impact that occurs when the candidate site is switched OFF or ON to ensure no coverage hole is created that affect user experience. The coverage refers to the geographical area for which the communication network is able to provide service using the one or more cell sites. The overlap impact is the impact caused due to overlap of coverage area by multiple cell sites.

[0116] The present disclosure further discloses that for the automatically switching between the power ON state and the power OFF state, the method

[0400] further comprises deactivate the identified candidate cell site. Thereafter, the method

[0400] further comprises trigger a handover mechanism to ensure a seamless transition of one or more users to the set of neighbouring cell sites. Then the method

[0400] further comprises update a network configuration to reflect deactivation of a macro 5G new radio (NR) node B (gNB). More specifically, the handover mechanism is the mechanism used for transfer of cellular transmission from one or more cell sites to one or more different cell sites, without losing any connectivity between the one or more usersand the network. Therefore, this mechanism enables switching of the candidate cell site without having the one or more users to face connection issues with the one or more cell sites, which may degrade Quality of Service and may also affect customer experience. Also, to automatically switch, the network configuration for the one or more cell sites or specifically the candidate cell site is altered to reflect that the candidate cell site is deactivated. The network configuration would then reflect that the candidate cell site which may be the macro 5G new radio (NR) node base station (gNb) has been deactivated.

[0117] The present disclosure further discloses that the method

[0400] further comprises analysing, by the processing unit

[0302] , the one or more traffic levels of the one or more cell sites to identify one of a period of minimal traffic level and a period of no traffic level. The period of minimal traffic level is a period where the one or more traffic levels are minimal traffic level or low traffic level. The period of no traffic level is the period where the one or more traffic levels are nonexistent i.e. no traffic level.

[0118] After analysing the one or more traffic levels, the method

[0400] further comprises evaluating, by the processing unit

[0302] , the energy consumption during one of the identified period of minimal traffic level and the period of no traffic level, wherein the energy consumption is evaluated against a predefined efficiency threshold. The evaluation is done based on the energy consumption at the period of minimal traffic level and the period of no traffic level in order to ascertain whether the deactivation of the candidate cell site would be able provide significant effect for regulation of energy consumption, i.e., determining if the switching would be efficient or not. For example, if in case of period of minimal traffic level, the energy consumption by the candidate cell site is not much high, and deactivation would not result in significant reduction in energy consumption, then it may be determined that deactivation is not required since it would not be efficient. Further, the predefined efficiency threshold is a threshold limit for determining whether the energy consumption of the candidate cell site is high. If the energy consumption reaches the predefined efficiency threshold, then it may be that the energy consumption by the candidate cell is high which can be regulated for achieving efficient regulation of the energy consumption. For example, the predefined efficiency threshold for PRB Utilization of top 3 neighbouring cell sites should be less than 70%. In another example, the predefined efficiency threshold for PRB Utilization of the candidate cell site should be less than 10 percent.

[0119] For determining whether the switching would be efficient or not, the energy efficiency may be determined based on the following formula:

[0120] The EE scenario i may refer to the energy efficiency in a scenario. The Vz may refer to the aggregated throughput in a served measured area / Cell for a traffic level, say 1. The Vz may also be associated with a served traffic volume divided by the measurement period. The Vz may be calculated in megabytes per second (Mbps). The ECz may refer to the sum of the average power consumption of all nodes in the simulated or the measurement area under the load level 1 / varied traffic pattern. The ECz may be calculated in watts.

[0121] Further, for the identification of power consumption in an area, a power per area unit metric may be calculated, which may be a network average power usage (P) divided by the coverage area of the network (A) and may be expressed in the unit [W / m2], Power per area unit is further a very relevant quantity at low traffic loads, as in this case the network is coverage limited rather than capacity limited.

[0122] Based on the evaluation of the energy consumption, the method

[0400] further comprises predicting, by the processing unit

[0302] , one of a target period of minimal traffic level and a target period of no traffic level, based on one or more historical traffic level patterns and an associated energy usage. The target period of minimal traffic level may refer to a period of time in future where the one or more traffic levels are minimal traffic level or low traffic level. The target period of no traffic level may refer to a period of time in future where the one or more traffic levels are non-existent i.e. no traffic level. The associated energy usage refers to the energy consumption by the one or more cell sites in a future period of time.

[0123] After the prediction of the target traffic levels, the method encompasses adjusting, by the processing unit

[0302] , the automatically switching between the power ON state or power OFF state of the identified candidate cell site during one of the predicted target period of minimal traffic level and the predicted target period of no traffic level. Once, the target period of minimal traffic level or the target period of no traffic level is predicted, then based on the prediction, the candidate cell site may be deactivated for regulating the energy consumption.

[0124] The present disclosure further discloses that predicting further comprises implementing, by the processing unit

[0302] , one or more supervised machine learning techniques comprising at least a support vector technique implemented via a Support Vector Machine (SVM), wherein thesupport vector technique is implemented to anticipate a user data based on a historical traffic level data, a day of week, and a time, utilizing a kernel function to consider both a spatial distance and a temporal distance between one or more data points. The one or more supervised machine learning techniques may refer to the techniques that uses labelled datasets to train algorithms to predict outcomes and recognize patterns. In one implementation, the processing unit

[0302] may also be used for predicting based on one or more unsupervised machine learning. The one or more supervised machine learning techniques may refer to the techniques in which models are not supervised using a specific training dataset, and the model itself find the hidden patterns and insights from the given data. The one or more Support Vector Machine (SVM) is a supervised machine learning algorithm used for both classification and regression. The historical traffic data is the data related to the one or more traffic levels at the one or more cell sites in the past. The spatial distance is the length of the path chosen to move from one point in space to another point. The temporal distance is the amount of time that separates a present time and the predicted target period. The kernel function is function which maps points or vectors from one feature space to another space. The one or more data points may be a present period of time and the future period of time. The user data may refer to a data associated with crowd source data, a data associated with the minimization of drive tests, and a data associated with a network resource and a service level.

[0125] The data associated with crowd source data may refer to the information collected from a large number of users or devices within a network to understand real-time network performance and user experiences. The data associated with crowd source data helps to identify network issues, optimize the coverage and the capacity, and also improves the quality of service based on actual user data.

[0126] The data associated with the minimization of drive tests may refer to the data used for application of a technique for collection of network performance data without traditional manual drive tests, and reducing operational costs and time. The data associated with the minimization of drive tests enables continuous monitoring of network parameters such as the coverage and the quality, thereby supporting proactive optimization and compliance with service level agreements.

[0127] The data associated with the network resource and the service level may refer to the standards and metrics which defines the quality and availability of the network resources and services in 5G networks. The data associated with the network resource and the service level guides network design, deployment, and management to ensure consistent service delivery, optimize resource allocation, and meet customer expectations.

[0128] The Support Vector Machine (SVM) based model can be trained using a given training dataset of a historical data (x<) with additional features for the one or more variations such as a data of the week (d,) and a time (t) and corresponding traffic levels yt).

[0129] In one example, the kernel function such as the RBF kernel, may be selected, based on:)As provided above, k denotes the RBF Kernel. The RBF kernel may be a radial basis function kernel or a Gaussian kernel that operates by measuring the similarity between data points based on their Euclidean distance in the input space. Further, x(, di, ti, and y< may refer to a first set of samples used for RBF Kernel. The Xi may refer to the historical data, the di may refer to the data of the week, the t may refer to the time, and y< may refer to the corresponding traffic levels. Further, xj, dj,tj, and y / may refer to a second set of samples used for RBF kernel. The xj may refer to the historical data, the d, may refer to the data of the week, the tj may refer to the time, and yzmay refer to the corresponding traffic levels. The c may refer to the standard deviation and may alsobe a free parameter. The y is calculated using the formula y The —I dj |2I | , |tj — tj |2may refer to the squared Euclidean distance between the two feature vectors.The exp may refer to the exponential function associated with the kernel function.

[0130] Thereafter, solving the SVM optimization problem to find a weight vector (w) and a bias term (b) by using the formula: min 0.5The may refer to the implicit mapping embedded in the RBF Kernel. The solution to the SVM optimization problem for training the model is subject to fulfilment of the condition that for all training samples. The w is the weight factor and b is the bias term which are determined by using the above formula. The bias term may refer to an incorrect assumption in which some aspects of a dataset are given more weight and / or representation than other. In other words, the bias term may be the error between an average model prediction and the ground truth. The condition is provided by the following formula: j / j Xdt, ti)) + b) > 1.

[0131] Then, calculating the predicted traffic load (f(x)) using the weight vector, bias term, and kernel function by using the following formula: (x, d, t) = (w, <f> (x, d, t)) + b .The <t> (x, d, t) represents the feature mapping to the higher-dimensional space including x, d, and t. The w is the weight factor, and b is the bias term. The bias term may refer to an incorrect assumption in which some aspects of a dataset are given more weight and / or representation than other. In other words, the bias term may be the error between an average model prediction and the ground truth.

[0132] Thus, the SVM machine learning model can be trained based the abovementioned technique and then can be used for prediction based on the above.

[0133] The SVM machine learning model can be used for prediction, based on a given new input of historical traffic data (xnew) with the corresponding day of the week (dnew) and time (tnew), the predicted traffic load (ypred) can be calculated using the learned SVM model.

[0134] Firstly, calculating the kernel function values between (xnew, dnew, tnew) and the support vectors in the training set using the formula:As provided above, k denotes the RBF Kernel. The RBF kernel may be a radial basis function kernel or a Gaussian kernel that operates by measuring the similarity between data points based on their Euclidean distance in the input space. Further, x(, di, ti, and y< may refer to a first set of samples used for RBF Kernel. The xt may refer to the historical data, the di may refer to the data of the week, the t may refer to the time, and y< may refer to the corresponding traffic levels. Further, Xnew, dnew, tnew, and ynewmay refer to a second set of samples used for RBF kernel. The xnewmay refer to the historical data, the dnew may refer to the data of the week, the tnew may refer to the time, and ynewmay refer to the corresponding traffic levels. The c may refer to the standard deviationand may also be a free parameter. The y is calculated using the formula y = — Themay refer to the squared Euclidean distance between the two feature vectors. The exp may refer to the exponential function associated with the kernel function.

[0135] Then, computing the predicted traffic load by using the formula:The az are the Lagrange multipliers which are obtained during the training of the SVM model. The b is the bias term. The bias term may refer to an incorrect assumption in which some aspects of a dataset are given more weight and / or representation than other. In other words, the bias term may be the error between an average model prediction and the ground truth. The ypredis the predicted traffic load. As provided above, k denotes the RBF Kernel. The RBF kernel may be a radial basis function kernel or a Gaussian kernel that operates by measuring the similarity between data points based on their Euclidean distance in the input space. Further, x(, di, t, and y< may refer to a first set of samples used for RBF Kernel. The x(may refer to the historical data, the di may refer to the data of the week, the t may refer to the time, and y< may refer to the corresponding traffic levels. Further, Xnew, dnew,tnew, and ynewmay refer to a second set of samples used for RBF kernel. The xnewmay refer to the historical data, the d e may refer to the data of the week, the tnewmay refer to the time, and ynewmay refer to the corresponding traffic levels.

[0136] It may be noted that the above-mentioned formulas, equations, and the values of the variables used in the respective formulas / equations for calculation, training of the model, and prediction of one or more traffic levels are only exemplary, and in no manner to be construed to limit the scope of the present subject matter. Any other techniques known to a person skilled in the art may also be used for calculation and training of the model. All such other examples and techniques would also lie within the scope of the present subject matter.

[0137] In this modified procedure, the kernel function considers both the spatial distance between historical traffic data points and the temporal distance between the day of the week and time values. This allows the SVM model to capture the dependencies between the traffic level, the day of the week, and the time for more accurate predictions in the telecommunication network.

[0138] The present disclosure further discloses that subsequent to the automatically switching, the method encompasses continuously monitoring of: the one or more traffic levels; a network performance; and a user experience of the set of neighbouring cell sites, wherein the continuously monitoring occurs to assess a traffic level distribution and a capacity utilization in the set of neighbouring cell sites, followed by a reactivation of the macro 5G new radio (NR) node B (gNB) of the candidate cell site when the predicted or actual one or more traffic levels of a set of neighbourgNBs corresponding to the set of neighbouring cell sites increases above a predefined threshold. The network performance may refer to the performance or measures of the quality of service in the communication network. The user experience may refer to the experience of the one or more users which are connected with the one or more cell sites, or more particularly connected with the set of neighbouring cell sites. The continuous monitoring is also an important part which helps in keeping a check on the one or more traffic levels of the candidate cell site, and helps in identification of the change in the one or more traffic levels. If there is an increase in the one or more traffic levels, then it is important to activate the candidate cell site for accommodating the increased traffic level. If the candidate cell site is not reactivated then it may lead to overload at the set of neighbouring cell sites which is undesirable, hence it is important to continuously monitor the one or more traffic levels, the network performance, and the user experience at the set of neighbouring cell sites.

[0139] Referring to FIG. 5, an exemplary diagram for regulating the energy consumption in the HetNet environment, in accordance with exemplary implementation of the present disclosure is shown. For regulation of the energy consumption, data is taken from a data source

[0502] , the data taken from the data source may be of two types, one is a historical data

[0504] , and a streaming data

[0506] , The historical data

[0504] is taken for implementing machine learning model for prediction of the one or more traffic levels. The streaming data

[0506] is taken for regulating the energy consumption and taking decisions for switching the candidate cell site to power OFF state. In the exemplary implementation, the machine learning model is trained for both 5G New Radio (NR) and the Long-Term Evolution (LTE) telecommunication networks.

[0140] For training the model, input data is taken at step

[0508] , and step

[0514] for NR and LTE, respectively. The PRB utilisation in 5G New Radio (NR), and the Long-Term Evolution (LTE) is collected. Further, the list of neighbouring cell sites for both LTE and the NR are also collected.

[0141] Further, the input data is used for pre-processing at step

[0510] , and step

[0516] for NR and LTE, respectively. Then the cell sites, such as 700 MHz cell sites of same sector in case of NR, and 850 MHz cell sites of same sector in case of LTE are identified. Further, top 3 neighbouring cell sites are also identified for both NR (in the 3.5 GHz band), and the LTE (in the 2.3 GHz band), based on handover counts.

[0142] Furthermore, at step

[0512] , and step

[0518] for NR and LTE respectively, three conditions (or threshold criteria) are required to be checked for both LTE and the NR. In case of NR, the firstcondition is that the PRB Utilization of 3500 MHz cell is less than 10 percent. The second condition is that the PRB utilisation of the 700 MHz cell of the same sector is less than 20 percent. The third condition is that the PRB Utilization of the top 3 neighbours is less than 70 percent in case of no congestion. In case of LTE, the first condition is that the PRB Utilization of 2300 MHz cell is less than 10 percent. The second condition is that the PRB Utilization of 850 MHz cell of the same sector is less than 50 percent. The third condition is that when the PRB utilization of the top 3 neighbours is less than 70 percent.

[0143] Then, at step

[0520] , prediction of the load (PRB Utilization) based on identification of the historical traffic level data (such as for the past month) and the one or more variations (such as on weekdays, weekends, festivals, and events) is performed. The prediction and identification may be done by the machine learning model trained by machine learning techniques. The one or more variations on weekdays may be the change in traffic level pattern in different days of week from Monday to Friday. The one or more variations on weekends may be the change in traffic level pattern on Saturdays and Sundays. The one or more variations of the traffic level pattern are identified during the festivals, events, occasions, and planned events such as Dussehra, Diwali, concerts, etc.

[0144] Then, at step

[0522] , a start time and an end time for the automatically switching the power ON state and the power OFF state for 2.3 GHz and 3.5 GHz cell for the next 24 hours are predicted. Then based on such prediction a switching duration, a start time for switching the power OFF, and the end time for switching the power ON may be provided.

[0145] Thereafter, at step

[0524] , the PRB Utilization for the candidate cell site for (both 3.5 GHz and 2.3 GHz) are fetched before the start time (i.e. switching the power ON / OFF). If the PRB utilization of the candidate cell site is less than 10 percent, then the process moves onto step

[0528] , If the PRB utilization of the candidate cell site is greater than 10 percent, then the process moves to step

[0532] , wherein the automatic switching of the candidate cell site to the power OFF state is aborted.

[0146] Thereafter, at step

[0528] , if the PRB Utilization of the same sector Frequency Division Duplex (FDD) cells for both 700 MHz cell sites and the 850 MHz cell sites is less than 20 percent and 50 percent respectively, then the process moves onto step

[0530] , However, if the PRB Utilization of the same sector FDD cells for both 700 MHz cell sites and the 850 MHz cell sites isgreater than 20 percent and 50 percent respectively, then at step

[0532] , the automatically switching the candidate cell site to the power OFF state is aborted.

[0147] Furthermore, at step

[0530] , if the PRB Utilization of the top 3 neighbouring cell sites is less than 70 percent, then the process moves to step

[0534] , However, if the PRB Utilization of the top 3 neighbouring cell sites is greater than 70 percent, then at step

[0532] , the automatically switching the candidate cell site to the power OFF state is aborted.

[0148] Further, at step

[0534] , the automatically switching between the power ON state and the power OFF state is initiated. For regulating the energy consumption, the candidate cell site (3.5 GHz or 2.3 GHz) is switched to power OFF state.

[0149] Thereafter, at step

[0536] , continuously monitoring of the PRB Utilization for the FDD cells from the same sector is done. Further, top 3 neighbouring cell sites are also monitored till the END time. The continuously monitoring may be done periodically every 15 minutes.

[0150] Thereafter, at step

[0538] , if the predicted PRB utilization in the future for the candidate cell sited is greater than 50 percent, or in case the predicted PRB utilization at the top 3 neighbouring cell sites is greater than 70 percent, then at step

[0540] , automatically switching the candidate cell site to power ON state is initiated i.e. reactivating the candidate cell site.

[0151] However, if the predicted PRB utilization in the future for the candidate cell sited is lower than 50 percent, or in case the predicted PRB utilization at the top 3 neighbouring cell sites is also lower than 70 percent, then the process moves back to step

[0524] and an iteration / cycle is created for the step

[0524] to step

[0538] , until the condition at step

[0538] is satisfied.

[0152] The present disclosure further discloses a non-transitory computer readable storage medium storing instructions for regulating an energy consumption in a Heterogeneous Network (HetNet) environment, the instructions include executable code which, when executed by one or more units of a system

[0300] , causes a processing unit

[0302] of the system

[0300] to monitor one or more traffic levels at one or more cell sites in a network region, wherein said monitoring corresponds to evaluating a set of Key Performance Indicators (KPIs) associated with the one or more cell sites. The instructions further include executable code which, when executed causes the processing unit

[0302] of the system

[0300] to predict the one or more traffic levels associated with each of the one or more cell sites; and to identify, via the identification unit

[0304] of the system

[0300] , a candidate cell site and a set of neighbouring cell sites based on the predicted one or more traffic levels. The instructions further include executable code which, when executed causes the processing unit

[0302] of the system

[0300] to determine a coverage hole flag associated with the identified candidate cell site and the set of neighbouring cell sites. The instructions further include executable code which, when executed causes the processing unit

[0302] of the system

[0300] to automatically switch between the power ON state or power OFF state of the identified candidate cell site based on the determined coverage hole flag to regulate the energy consumption and, maintain a pre-defined operational criterion associated with the HetNet environment.

[0153] As is evident from the above, the present disclosure provides a technically advanced solution for regulating an energy consumption in a Heterogeneous Network (HetNet) environment. The present solution utilizes machine learning techniques to proactively identify the sites and take action without the need to rely on low usage monitoring periods. Further, the method enables to save power consumption by identifying sites in advance and deactivating cells without compromising the quality of service. Furthermore, the solution as disclosed in the present disclosure proactively evaluates the coverage hole and overlap impact before cell site switch off. Additionally, any variations in traffic patterns over time, day of the week, and seasonal changes taken into account. Thereby, it may be used for dynamic multi-objective optimization and efficient estimation of the coverage hole even before triggering cell switch on / oflf

[0154] Furthermore, the present disclosure provides an improved energy efficiency by effectively optimizing power consumption in networks, particularly in HetNet environments. By identifying and selectively switching off / on certain components based on load conditions, it helps reduce overall energy consumption, leading to improved energy efficiency. Further, the present solution results in increased cost savings, by optimizing power consumption. The solution helps reduce operational costs associated with energy usage in 5G networks. This can result in significant cost savings for network operators. Additionally, the present disclosure provides an improved network performance by taking into account load conditions and QoS requirements, thereby ensuring that the network performance remains at an optimal level. By intelligently managing the switching off / on of components, it helps maintain a balance between energy efficiency and network performance. The present disclosure is applicable to networks of different sizes and configurations, making it scalable and adaptable to different deployment scenarios. The present disclosure provides improved sustainability, by reducing energy consumption and optimizing resource utilization, therefore the disclosure contributes to the sustainability of 5G networks and also aligns with the industry's goals of reducing carbon footprint and promoting environmentally friendlypractices. The present disclosure further provides a seamless user experience, despite the power optimizations, the present disclosure ensures that the QoS requirements of users are maintained. This helps deliver a seamless and uninterrupted user experience, even with the switching off / on of network components.

[0155] While considerable emphasis has been placed herein on the disclosed implementations, it will be appreciated that many implementations can be made and that many changes can be made to the implementations without departing from the principles of the present disclosure. These and other changes in the implementations of the present disclosure will be apparent to those skilled in the art, whereby it is to be understood that the foregoing descriptive matter to be implemented is illustrative and non-limiting.

[0156] Further, in accordance with the present disclosure, it is to be acknowledged that the functionality described for the various components / units can be implemented interchangeably. While specific embodiments may disclose a particular functionality of these units for clarity, it is recognized that various configurations and combinations thereof are within the scope of the disclosure. The functionality of specific units as disclosed in the disclosure should not be construed as limiting the scope of the present disclosure. Consequently, alternative arrangements and substitutions of units, provided they achieve the intended functionality described herein, are considered to be encompassed within the scope of the present disclosure.

Claims

We Claim:

1. A method [400] for regulating an energy consumption in a Heterogeneous Network (HetNet) environment, the method [400] comprising: monitoring [404], by a processing unit [302], one or more traffic levels at one or more cell sites in a network region, wherein said monitoring corresponds to evaluating a set of Key Performance Indicators (KPIs) associated with the one or more cell sites; predicting [406], by the processing unit [302], one or more traffic levels associated with each of the one or more cell sites; identifying [408], by the processing unit [302] via an identification unit [304], a candidate cell site and a set of neighbouring cell sites based on the predicted one or more traffic levels; determining [410], by the processing unit [302], a coverage hole flag associated with the identified candidate cell site and the set of neighbouring cell sites; and automatically switching [412], by the processing unit [302], between a power ON state and a power OFF state of the identified candidate cell site based on the determined coverage hole flag.

2. The method [400] as claimed in claim 1, wherein the automatically switching [410], by the processing unit [302], between the power ON state and the power OFF state of the identified candidate cell site, maintains a pre-defined operational criterion associated with the HetNet environment.

3. The method [400] as claimed in claim 1, further comprising: analysing, by the processing unit [302], the one or more traffic levels of the one or more cell sites to identify one of a period of minimal traffic level and a period of no traffic level; evaluating, by the processing unit [302], the energy consumption during one of the identified period of minimal traffic level and the period of no traffic level, wherein the energy consumption is evaluated against a predefined efficiency threshold; predicting, by the processing unit [302], one of a target period of minimal traffic level and a target period of no traffic level, based on one or more historical traffic level patterns and an associated energy usage; and adjusting, by the processing unit [302], the automatically switching between the power ON state and the power OFF state of the identified candidate cell site during one of the predicted target period of minimal traffic level and the predicted target period of no traffic level.

4. The method [400] as claimed in claim 1, wherein the set of KPIs comprises at least one of a Physical Resource Block (PRB) Utilization, a Number of Radio Resource Control (RRC) Users, a number of active users, a Cell effective throughput, and a Total traffic (Uplink and Downlink).

5. The method [400] as claimed in claim 1, wherein the predicting further comprises implementing, by the processing unit [302], one or more supervised machine learning techniques, comprising at least a support vector technique implemented via a Support Vector Machine (SVM), wherein the support vector technique is implemented to anticipate a user data based on a historical traffic level data, a day of week, and a time, utilizing a kernel function to consider both a spatial distance and a temporal distance between one or more data points.

6. The method [400] as claimed in claim 1, wherein the automatically switching between the power ON state and the power OFF state is further based on evaluating, by the processing unit, a coverage, and an overlap impact that occurs when the candidate site is switched OFF or ON to ensure no coverage hole is created that affect user experience.

7. The method [400] as claimed in claim 1, wherein the identifying the candidate cell site and the set of neighbouring cell sites comprises evaluating at least one of: a measurement range of a signal strength and a site location, based on one or more variations in one or more traffic level patterns over a time, a day of week, and one or more seasonal changes.

8. The method [400] as claimed in claim 1, wherein the determining the coverage hole flag comprises evaluation of a planning data and a crowdsourcing data comprising one or more parameters, wherein the one or more parameters comprises at least one of a best server plot (latitude and longitude of a site location) and a signal strength, to tag one or more areas with a received signal strength less than -110 as one or more potential coverage holes.

9. The method [400] as claimed in claim 1, wherein for the automatically switching between the power ON state and the power OFF state, the method [400] further comprises: deactivating the identified candidate cell site; triggering a handover mechanism to ensure a seamless transition of one or more users to the set of neighbouring cell sites; and updating a network configuration to reflect deactivation of a macro 5G new radio (NR) node B (gNB).

10. The method [400] as claimed in claim 9, wherein subsequent to the automatically switching, the method further comprises:continuously monitoring, by the processing unit [302], of at least one of: the one or more traffic levels; a network performance; and a user experience of the set of neighbouring cell sites, wherein the continuously monitoring of the one or more traffic levels, the network performance, and the user experience enables assessing of a traffic level distribution and a capacity utilization in the set of neighbouring cell sites; and reactivating, by the processing unit [302], the macro 5G new radio (NR) node B (gNB) of the candidate cell site when the predicted or actual one or more traffic levels of a set of neighbour gNBs corresponding to the set of neighbouring cell sites increases above a predefined threshold.

11. A system [300] for regulating an energy consumption in a Heterogeneous Network (HetNet) environment, the system [300] comprising: a processing unit [302], configured to: monitor one or more traffic levels at one or more cell sites in a network region, wherein said monitoring corresponds to evaluating a set of Key Performance Indicators (KPIs) associated with the one or more cell sites; predict one or more traffic levels associated with each of the one or more cell sites; identify, via an identification unit [304], a candidate cell site and a set of neighbouring cell sites based on the predicted one or more traffic levels; determine a coverage hole flag associated with the identified candidate cell site and the set of neighbouring cell sites; and automatically switch between a power ON state and a power OFF state of the identified candidate cell site based on the determined coverage hole flag.

12. The system [300] as claimed in claim 11, wherein the automatically switch between the power ON state and the power OFF state of the identified candidate cell site maintains a predefined operational criterion associated with the HetNet environment.

13. The system [300] as claimed in claim 11, wherein the processing unit [302] is further configured to: analyse the one or more traffic levels of the one or more cell sites to identify one of a period of minimal traffic level and a period of no traffic level; evaluate the energy consumption during one of the identified period of minimal traffic level and the period of no traffic level, wherein the energy consumption is evaluated against a predefined efficiency threshold; predict one of a target period of minimal traffic level and a target period of no traffic level, based on one or more historical traffic patterns and an associated energy usage; andadjust the automatically switching the power ON state and power OFF state of the identified candidate cell site during one of the predicted target period of minimal traffic level and the predicted target period of no traffic level.

14. The system [300] as claimed in claim 11, wherein the set of KPIs comprises at least one of a Physical Resource Block (PRB) Utilization, a number of Radio Resource Control (RRC) Users and a number of active users, a Cell effective throughput, and a Total traffic (Uplink and Downlink).

15. The system [300] as claimed in claim 11, wherein to predict, the processing unit [302] is further configured to implement one or more supervised machine learning techniques comprising at least a support vector technique implemented via a Support Vector Machine (SVM), wherein the support vector technique is implemented to anticipate a user data based on a historical traffic data, a day of week, and a time, utilizing a kernel function to consider both a spatial distance and a temporal distance between one or more data points.

16. The system [300] as claimed in claim 11, wherein to automatically switch, the processing unit [302] is further configured to evaluate a coverage and an overlap impact that occurs when the candidate site is switched OFF or ON to ensure no coverage hole is created that affect user experience.

17. The system [300] as claimed in claim 11, wherein to identify the candidate cell site and the set of neighbouring cell sites, the processing unit [302] is configured to evaluate a measurement range of a signal strength and a site location, based on one or more variations in one or more traffic level patterns over a time, a day of week, and one or more seasonal changes.

18. The system [300] as claimed in claim 11, wherein to determine the coverage hole flag, the processing unit [302] is further configured to evaluate a planning data and a crowdsourcing data comprising one or more parameters, wherein the one or more parameters comprises a best server plot (latitude and longitude of a site location) and a signal strength, to tag one or more areas with a received signal strength less than -110 as one or more potential coverage holes.

19. The system [300] as claimed in claim 11, wherein to automatically switch, the processing unit [302] is configured to deactivate the identified candidate cell site, triggering a handover mechanism to ensure a seamless transition of one or more users to the set of neighbouring cellsites, and updating a network configuration to reflect deactivation of a macro 5G new radio (NR) node B (gNB).

20. The system [300] as claimed in claim 19, wherein subsequent to the automatically switching, the processing unit [302] is further configured to continuously monitor the one or more traffic levels, a network performance, and a user experience of the set of neighbouring cell sites, wherein the continuously monitoring of the one or more traffic levels, the network performance, and the user experience enables assessing of a traffic level distribution and a capacity utilization in the set of neighbouring cell sites; and reactivate the macro 5G new radio (NR) node B (gNB) of the candidate cell site when the predicted or actual one or more traffic levels of a set of neighbour gNBs corresponding to the set of neighbouring cell sites increases above a predefined threshold.

21. A non-transitory computer-readable storage medium storing instructions for regulating an energy consumption in a Heterogeneous Network (HetNet) environment, the instructions comprising executable code which, when executed by one or more units of a system [300], causes: a processing unit [302] of the system [300] to monitor one or more traffic levels at one or more cell sites in a network region, wherein said monitoring corresponds to evaluating a set of Key Performance Indicators (KPIs) associated with the one or more cell sites; the processing unit [302] of the system [300] to predict one or more traffic levels associated with each of the one or more cell sites; the processing unit [302] of the system [300] to identify, via an identification unit [304], a candidate cell site and a set of neighbouring cell sites based on the predicted one or more traffic levels; the processing unit [302] of the system [300] to determine a coverage hole flag associated with the identified candidate cell site and the set of neighbouring cell sites; and the processing unit [302] of the system [300] to automatically switch between a power ON state and a power OFF state of the identified candidate cell site based on the determined coverage hole flag.

Images