Method and system for estimating energy consumption in wireless access network

Abstract

In order to estimate the energy consumption in a radio access network (RAN), each carrier in each of a remote radio unit (RRU) and / or an active antenna unit (AAU) in the RAN reports an energy consumption related parameter of the carrier to a main carrier of the RRU or the AAU, and in order to estimate the energy consumption in the RAN, each carrier in each of the RRU and / or the active antenna unit (AAU) in the RAN reports an energy consumption related parameter of the carrier to the main carrier of the RRU or the AAU. Each primary carrier uses a local artificial intelligence (AI) or machine learning (ML) based energy consumption estimator to create a local mapping between the energy consumption related parameters and the energy consumption of the RRU or the AAU using the reported energy consumption related parameters of the carrier. Then, each primary carrier reports the local mapping to an optimization node that creates a generic mapping between the energy consumption related parameters and the energy consumption of all the RRUs in the RAN and / or the AAU using a generic AI and / or ML based energy consumption estimator.

Description

Technical Field

[0001] The present disclosure generally relates to a radio access network, and more particularly, to methods and systems for estimating energy consumption in a radio access network. Background Art

[0002] The 3rd generation partnership project (3GPP) new radio (NR) version 16 defines an energy consumption model for 5G user equipment (UE). 3GPP NR version 18 further attempts to develop a set of flexible and dynamic network energy saving solutions. The network energy saving solutions should consider the impact of key energy consumption factors of 5G base stations (BS) (such as power amplifiers (PA), the number of TxRUs, static circuit components), and should also consider the 5G BS sleep mode and its associated transition time, etc. There is currently no accurate 5G BS energy consumption estimation framework that can meet the requirements of 3GPP. Therefore, 3GPP takes building such a BS energy consumption estimation framework as the first important goal for building and evaluating network energy saving solutions.

[0003] In the existing solutions, a model that explicitly represents the linear relationship between network power consumption and transmission power is provided. Considering different sleep depths and the transition time between different energy states, this model can also support massive multiple-input multiple-output (mMIMO) and energy saving capabilities. However, this solution does not consider multi-carrier and / or carrier aggregation (CA) capabilities, and the mMIMO power consumption estimation seems inaccurate, with an optimistic estimate of 40.5 W per BS.

[0004] Another existing solution includes mMIMO and multi-carrier capability characteristics, namely in-band continuous, in-band discontinuous, and inter-band. However, none of these works consider all the requirements of 3GPP. Importantly, most of these estimation frameworks are theoretical and not accurate enough to capture the energy consumption of real 5G radio units and even the network.

[0005] It should be noted that the radio frequency unit is the main energy-consuming entity of the entire network. According to GSMA statistics, the energy consumption in the radio access network (RAN) reaches 73%, and the energy consumption of the radio frequency unit accounts for 66% to 82% of the energy consumption in the BS. In fact, the radio frequency unit responsible for TX / RX signal processing can take the following forms: 1. Remote Radio Unit (RRU), which (a) exchanges digital signals with the Baseband Unit (BBU) through an optical fiber cable, and (b) exchanges analog signals with a passive antenna element through a coaxial cable; or 2. Active Antenna Unit (AAU), roughly speaking, which integrates the RRU function and the passive antenna element into one unit and provides the hardware and logic to (i) control the precoding coefficient of each passive antenna element, and (ii) combine the digital signals from each passive antenna element / divide the digital signals to each passive antenna element.

[0006] In 3GPP terminology, the radio frequency unit is also referred to as the "Transmission Reception Point (TRP)", which is an antenna array with one or more antenna elements that can be used for a network located at a specific geographical location in a specific area. Traditionally, RRU, AAU, and TRP are multi-carrier and use broadband PAs to operate these multi-carriers.

[0007] From the above discussion, it can be known that the energy consumption of a carrier or cell cannot be determined independently of the behavior of other carriers or cells co-located in the same RRU / AUU because they share circuits. Therefore, creating an energy consumption estimation framework for each carrier or cell will result in inaccurate BS / network energy consumption estimation because the multi-carrier characteristics of the above RRU or AAU will not be considered.

[0008] Another major problem is that using only local cell data cannot create a general energy consumption estimation framework for each RRU or AAU because the data used to implement the estimation will be limited to the configurations and scenarios locally observed by this RRU or AAU. For example, in a given area, due to high load, not all energy-saving modes may be activated in a given RRU or AAU. The goal is to predict the energy consumption of the RRU or AAU at any operating point / configuration of the RRU or AAU, even if that operating point / configuration has not been locally observed.

[0009] Therefore, it is necessary to solve the above technical problems / shortcomings in estimating the energy consumption in the RAN. Summary of the Invention

[0010] The objective of the present disclosure is to provide a method for estimating energy consumption in a radio access network (RAN) and a system for estimating energy consumption in a RAN, while avoiding one or more drawbacks of the prior art methods.

[0011] This objective is achieved by the features of the independent claims. Additionally, embodiments will be apparent from the dependent claims, the description, and the drawings.

[0012] The present disclosure provides a method for estimating energy consumption in a RAN.

[0013] According to a first aspect, a method for estimating energy consumption in a RAN is provided. The method includes: each carrier in each of one or more remote radio units (RRUs) and / or one or more active antenna units (AAUs) in the RAN reporting energy consumption related parameters of the carrier to the primary carrier of the RRU or AAU. The method includes: the primary carrier in each of one or more RRUs and / or AAUs using a local artificial intelligence (AI)- or machine learning (ML)-based energy consumption estimator to create a local mapping between the reported energy consumption related parameters of the carriers in the RRU or AAU and the energy consumption of the RRU or AAU, by using the reported energy consumption related parameters of the carriers in the RRU or AAU. The method includes: the primary carrier in each of one or more RRUs and / or AAUs reporting the local mapping to an optimization node of the RAN. The method includes: the optimization node using a general AI- and / or ML-based energy consumption estimator to create a general mapping between the energy consumption related parameters and the energy consumption of all RRUs and / or AAUs in the RAN, by using all the reported local mappings. The method includes: the optimization node using the local AI- and / or ML-based energy consumption estimator of the RRU or AAU to refine the local mapping between the energy consumption related parameters and the energy consumption of each of the RRUs and / or AAUs, by using all the reported local mappings.

[0014] This method improves the accuracy of network energy consumption estimation, thereby improving network energy saving optimization. This method uses network and energy related information collected at each of the RRUs or AAUs, which allows for capturing locally (i) specific network operating conditions, such as traffic, massive MIMO, and (ii) characteristics, such as manufacturing differences and temperature effects, at each of the RRUs or AAUs.

[0015] This method provides more accurate network energy consumption estimation for heterogeneous multi-vendor networks including different radio frequency units (including RRUs and AAUs) from any vendor and any possible network configuration.

[0016] This method can obtain the generalization characteristics crucial for network energy efficiency optimization. This method generalizes across multiple products and parameter configurations. Thus, for example, in a scenario where the configuration of the first RRU or AAU has not been measured and is not available in the data used to build the estimator, but this configuration can be used for other RRUs or AAUs (e.g., the second RRU / AAU, or the third RRU / AAU), an accurate energy consumption estimate can be generated for the first RRU or AAU.

[0017] Optionally, the method includes: an optimization node reporting refined local mapping to the primary carrier in each of one or more RRUs and / or AAUs in the RAN.

[0018] Optionally, the method includes: the primary carrier in each of one or more RRUs or AAUs updating the local AI- or ML-based energy consumption estimator using the refined local mapping; repeating the method using the updated local AI- or ML-based energy consumption estimator.

[0019] Optionally, the method includes: an optimization node applying a predefined network energy efficiency optimization strategy to the RRUs or AAUs in the RAN using the current state of a general AI- and / or ML-based energy consumption estimator.

[0020] Optionally, the optimization node includes the controller of the RAN or the primary carrier of the primary RRU or AAU in the RAN.

[0021] Optionally, the primary RRU or AAU in the RAN is preselected by the controller of the RAN among all the RRUs and / or AAUs in the RAN.

[0022] Optionally, the primary carrier in each of one or more RRUs and / or AAUs is preselected by the controller of the RAN among all the carriers in each of one or more RRUs and / or AAUs.

[0023] Optionally, the method includes: the controller of the RAN defining the architecture of the local AI- or ML-based energy consumption estimator in each primary carrier in each of one or more RRUs and / or AAUs, the architecture including the input and output of the local AI- or ML-based energy consumption estimator, and the time period for reporting energy consumption-related parameters by other carriers in each of one or more RRUs and / or AAUs; the controller of the RAN defining the architecture of the general AI- or ML-based energy consumption estimator for the optimization node, the architecture including the input and output of the general AI- or ML-based energy consumption estimator.

[0024] Optionally, the method includes: for each of one or more remote radio units (RRUs) and / or active antenna units (AAUs), a primary carrier defines energy consumption related parameters to be reported by other carriers of the RRU or AAU based on defined inputs of a local AI or ML based energy consumption estimator.

[0025] Optionally, the energy consumption related parameters reported by a carrier in each of one or more RRUs and / or AAUs include configuration parameters of the RRU or AAU related to the energy consumption of the RRU or AAU and carrier-level key performance indicators (KPIs).

[0026] According to a second aspect, a system for estimating energy consumption in a radio access network (RAN) is provided, including one or more remote radio units (RRUs) and / or one or more active antenna units (AAUs). The system includes carriers in each of one or more RRUs and / or AAUs for reporting energy consumption related parameters of each carrier to a primary carrier of the RRU or AAU. The primary carrier in each of one or more RRUs and / or AAUs is configured to: create a local mapping between the reported energy consumption related parameters and the energy consumption of the RRU or AAU by using a local artificial intelligence (AI) or machine learning (ML) based energy consumption estimator for the carriers in the RRU or AAU; report the local mapping to an optimization node of the RAN. The optimization node is configured to: create a general mapping between the energy consumption related parameters and the energy consumption of all RRUs and / or AAUs in the RAN by using a general AI and / or ML based energy consumption estimator for all reported local mappings. The optimization node is configured to: refine the local mapping between the energy consumption related parameters and the energy consumption of each of the RRUs and / or AAUs by using the local AI and / or ML based energy consumption estimator for the RRU or AAU for all reported local mappings.

[0027] The system improves the accuracy of network energy consumption estimation, thereby improving network energy saving optimization. The system uses network and energy related information collected at each RRU or AAU, which allows for capturing locally (i) specific network operating conditions such as traffic, massive MIMO, and (ii) characteristics such as manufacturing differences and temperature effects at each RRU or AAU.

[0028] The system provides more accurate network energy consumption estimation in heterogeneous multi-vendor networks including different radio frequency units (including RRUs and / or AAUs) from any vendor and any possible network configuration.

[0029] The system is capable of obtaining generalization characteristics that are crucial for network energy efficiency optimization. The system generalizes across multiple product and parameter configurations. Thus, for example, in a scenario where the configuration of the first RRU or AAU has not been measured and is not available in the data used to build the estimator, but this configuration is available for other RRUs or AAUs (e.g., the second RRU / AAU or the third RRU / AAU), an accurate energy consumption estimate can be generated for the first RRU or AAU.

[0030] Optionally, the optimization node is also used to report a refined local mapping to the primary carrier in each of one or more RRUs and / or AAUs in the RAN.

[0031] Optionally, the primary carrier in each of one or more RRUs or AAUs is also used to update the local AI or ML-based energy consumption estimator using the refined local mapping.

[0032] Optionally, the optimization node is also used to apply a predefined network energy efficiency optimization strategy to the RRUs or AAUs in the RAN using the current state of the general AI and / or ML-based energy consumption estimator.

[0033] Optionally, the optimization node includes the controller of the RAN or the primary carrier of the primary RRU or AAU in the RAN.

[0034] Optionally, the primary RRU or AAU in the RAN is preselected by the controller of the RAN among all the RRUs and / or AAUs in the RAN.

[0035] Optionally, the primary carrier in each of one or more RRUs and / or AAUs is preselected by the controller of the RAN among all the carriers in each of one or more RRUs and / or AAUs.

[0036] Optionally, the controller of the RAN is used to: define the architecture of the local AI or ML-based energy consumption estimator in each primary carrier in each of one or more RRUs and / or AAUs, which includes the inputs and outputs of the local AI or ML-based energy consumption estimator, and the time period for other carriers in each of one or more RRUs and / or AAUs to report energy consumption-related parameters; define the architecture of the general AI or ML-based energy consumption estimator for the optimization node, which includes the inputs and outputs of the general AI or ML-based energy consumption estimator.

[0037] Optionally, the primary carrier in each of one or more RRUs and / or AAUs is used to define the energy consumption-related parameters to be reported by other carriers of the RRU or AAU based on the defined inputs of the local AI or ML-based energy consumption estimator.

[0038] Optionally, the energy consumption related parameters reported for each carrier in one or more RRUs and / or AAUs include the configuration parameters of the RRU or AAU related to the energy consumption of the RRU or AAU and the carrier-level key performance indicators (KPIs).

[0039] These and other aspects of the present disclosure will be apparent from one or more of the embodiments described below. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Embodiments of the present disclosure will now be described, by way of example only, with reference to the accompanying drawings, in which:

[0041] Figure 1 is a block diagram of a system for estimating energy consumption in a radio access network (RAN) according to an embodiment of the present disclosure;

[0042] Figure 2 is a flowchart of a method for estimating energy consumption based on artificial intelligence / machine learning according to an embodiment of the present disclosure;

[0043] Figures 3A to 3C is an exemplary illustration of an active antenna unit (AAU) for estimating energy consumption during operation within an AAU according to an embodiment of the present disclosure;

[0044] Figure 4 is an interaction diagram showing information exchange between a central controller, a master AAU, and one or more slave AAUs according to an embodiment of the present disclosure;

[0045] Figures 5A to 5B is an exemplary illustration of a primary carrier within an active antenna unit (AAU) for estimating energy consumption during operation within the AAU according to an embodiment of the present disclosure;

[0046] Figure 5C is according to an embodiment of the present disclosure by Figure 1 an exemplary illustration of a model trained with operation information within an active antenna unit (AAU) by a primary carrier;

[0047] Figures 6A to 6B is an exemplary illustration of model exchange between one or more slave AAUs and a master AAU and a central controller according to an embodiment of the present disclosure;

[0048] Figure 7An exemplary illustration of a federated learning method for constructing and improving local and general AI / ML-based network energy consumption estimators according to an embodiment of the present disclosure;

[0049] Figure 8 An exemplary illustration of a federated learning method for constructing and improving local and general AI / ML-based network plus user equipment (UE) energy consumption estimators according to an embodiment of the present disclosure;

[0050] Figure 9 An interaction diagram showing information exchange between a central controller, a main AAU, one or more slave AAUs, and a UE according to an embodiment of the present disclosure;

[0051] Figure 10A and Figure 10B A flowchart showing a method for estimating energy consumption in a RAN according to an embodiment of the present disclosure;

[0052] Figure 11 A diagram of a computer system (e.g., an optimization node) in which various architectures and functions in the previous various embodiments can be implemented. Detailed Embodiments

[0053] Embodiments of the present disclosure provide methods and systems for estimating energy consumption in a radio access network (RAN).

[0054] To make it easier for those skilled in the art to understand the solutions of the present disclosure, the following embodiments of the present disclosure are described in conjunction with the accompanying drawings.

[0055] Terms such as "first", "second", "third", and "fourth" (if any) in the specification, claims, and above-mentioned drawings of the present disclosure are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or order. It should be understood that such terms are interchangeable under appropriate circumstances, for example, so that the embodiments of the present disclosure described herein can be implemented in a sequence other than the sequences shown or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device including a series of steps or units is not necessarily limited to the clearly listed steps or units, but may include other steps or units not clearly listed or inherent to such process, method, product, or device.

[0056] Figure 1Block diagram of a system 100 for estimating energy consumption in a RAN 102 according to an embodiment of the present disclosure. The system 100 includes carriers 105A-105Z in each of one or more remote radio units (RRUs) 104A-104N and / or active antenna units (AAUs) 106A-106N. The carriers 105A-105Z are used to report energy consumption related parameters of each of the carriers 105A-105Z to the primary carriers 108A-108Z of the RRU 104A or the AAU 106A. The primary carriers 108A-108Z in each of one or more RRUs 104A-104N and / or one or more AAUs 106A-106N are used to: create a local mapping between the reported energy consumption related parameters and the energy consumption of the RRU 104A or the AAU 106A by using a local artificial intelligence (AI)- or machine learning (ML)-based energy consumption estimator. The primary carriers 108A-108Z in each of one or more RRUs 104A-104N and / or one or more AAUs 106A-106N are used to report the local mapping to an optimization node 110 of the RAN 102. The optimization node 110 is used to: create a general mapping between the energy consumption related parameters and the energy consumption of all the RRUs 104A-104N and / or AAUs 106A-106N in the RAN 102 by using a general AI- and / or ML-based energy consumption estimator with all the reported local mappings. The optimization node 110 is used to: refine the local mapping between the energy consumption related parameters and the energy consumption of each of the RRUs 104A-104N and / or AAUs 106A-106N by using the local AI- and / or ML-based energy consumption estimator of the RRU104A or the AAU 106A with all the reported local mappings.

[0057] The system 100 improves the accuracy of network energy consumption estimation, thus improving network energy saving optimization. The system 100 uses network and energy related information collected at each of one or more RRUs 104A-104N or one or more AAUs 106A-106N, which allows for capturing locally at each RRU or AAU (i) specific network operating conditions, such as traffic, massive MIMO, and (ii) characteristics, such as manufacturing differences and temperature effects.

[0058] System 100 provides a more accurate network energy consumption estimation for the following method, which is used for better network energy saving optimization of heterogeneous multi-vendor networks including different radio frequency units (including RRUs and / or AAUs) from any vendor and any possible network configurations.

[0059] The system 100 is capable of obtaining generalization characteristics crucial for network energy efficiency optimization. The system 100 generalizes across multiple product and parameter configurations. Thus, for example, in a scenario where the configuration of RRU 104A or AAU 106A has not been measured and is not available in the data used to build the estimator, but this configuration can be used for other RRUs or AAUs (such as RRU 104B / AAU 106B or RRU104N or AAU 106N), an accurate energy consumption estimation can be generated for RRU 104A or AAU 106A.

[0060] Optionally, the optimization node 110 is also used to report refined local mapping to the primary carriers 108A to 108Z in each of one or more RRUs 104A to 104N and / or AAUs 106A to 106N in the RAN 102.

[0061] Optionally, the primary carriers 108A to 108Z in each of one or more RRUs 104A to 104N or AAUs 106A to 106N are also used to update the local AI- or ML-based energy consumption estimator using the refined local mapping.

[0062] Optionally, the optimization node 110 is also used to apply a predefined network energy efficiency optimization strategy to the RRUs 104A to 104N or AAUs 106A to 106N in the RAN 102 using the current state of the general AI- and / or ML-based energy consumption estimator.

[0063] Optionally, the optimization node 110 includes a controller of the RAN 102 or the primary carrier 108A of the primary RRU or AAU in the RAN 102.

[0064] Optionally, the primary RRU or AAU in the RAN 102 is preselected by the controller of the RAN 102 among all the RRUs104A to 104N and / or AAUs 106A to 106N in the RAN 102.

[0065] Optionally, the primary carriers 108A to 108Z in each of one or more RRUs 104A to 104N and / or AAUs 106A to 106N are preselected by the controller of the RAN 102 among all the carriers 105A to 105Z in each of one or more RRUs 104A to 104N and / or AAUs 106A to 106N.

[0066] Optionally, the controller of the RAN 102 is configured to: define the architecture of a local AI- or ML-based energy consumption estimator in each of one or more of the RRU 104A to 104N and / or AAU 106A to 106N for each of the primary carriers 108A to 108Z, the architecture including the inputs and outputs of the local AI- or ML-based energy consumption estimator, and the time periods for other carriers in each of one or more of the RRU 104A to 104N and / or AAU 106A to 106N to report energy consumption related parameters; split the table into shards consisting of rows based on the date values included in the data fields in each row; define the architecture of a general AI- or ML-based energy consumption estimator for the optimization node 110, the architecture including the inputs and outputs of the general AI- or ML-based energy consumption estimator.

[0067] Optionally, for each of the primary carriers 108A to 108Z in each of one or more of the RRU 104A to 104N and / or AAU 106A to 106N, based on the defined inputs of the local AI- or ML-based energy consumption estimator, define the energy consumption related parameters to be reported by other carriers of the RRU 104A or AAU 106A.

[0068] Optionally, the energy consumption related parameters reported by each of the carriers 105A to 105Z in each of one or more of the RRU 104A to 104N and / or AAU 106A to 106N include the configuration parameters of the RRU 104A or AAU 106A related to the energy consumption of the RRU 104A or AAU 106A and the carrier-level key performance indicators (KPIs).

[0069] The optimization node 110 can be a central controller (deployed, for example, at the operation, management, and maintenance network management function), or a prior-selected primary carrier of a prior-selected primary RRU or AAU of a group of RRUs or AAUs. The optimization node 110 is capable of optimizing the network energy efficiency of the RAN 102.

[0070] Figure 2It is a flowchart of a method for estimating energy consumption based on artificial intelligence / machine learning according to an embodiment of the present disclosure. In step 202, the method starts. The controller of the RAN identifies the primary carrier of each of one or more RRUs and / or AAUs, and defines an AI / ML-based energy consumption estimator architecture or mapping architecture, including inputs and outputs, as well as measurement and reporting periods. In step 204, mapping establishment is performed. The controller of the RAN indicates these decisions to the primary carrier of each of one or more RRUs and / or AAUs, and the primary carrier of each of one or more RRUs and / or AAUs indicates to its secondary carriers (i.e., other carriers deployed in the same RRU or AAU) the cell-level key performance indicators (KPIs) that will be reported together with the measurement and reporting timings. The RAN controller can directly configure the secondary carriers.

[0071] In step 206, if there are measurement and reporting timings, the secondary carriers evaluate the relevant cell-level KPIs according to the configuration in the second step and exchange them with their primary carriers; otherwise, step 204 is repeated. In step 208, the primary carrier of each RRU or AAU updates its local AI / ML-based energy consumption mapping, i.e., the AI / ML-based energy consumption estimator, using an AI / ML method.

[0072] In step 210, after the local AI / ML-based energy consumption estimator is updated, it enters the inter-AAU communication phase, where the primary carrier of each RRU or AAU reports the updated local AI / ML-based energy consumption mapping to the optimization node. The optimization node realizes network energy efficiency optimization through the Xn interface. In step 212, the optimization node updates the general AI / ML-based energy consumption mapping using AI / ML techniques. In step 214, the optimization node updates each of the local AI / ML-based energy consumption mappings using AI / ML techniques.

[0073] In step 216, the optimization node can use this mapping to run a predefined network energy efficiency optimization strategy. The general AI / ML-based energy consumption mapping can be provided as an input to a larger existing network energy efficiency optimization method. In step 218, it enters the inter-AAU communication phase, where the optimization node reports the updated local AI / ML-based energy consumption mapping to the primary carrier of each RRU or AAU. When the subsequent measurement and reporting timings are triggered, the method is repeated from step 206 onwards.

[0074] Figures 3A to 3CExemplary illustration of an active antenna unit (AAU) for estimating energy consumption according to an embodiment of the present disclosure. Taking a RAN including X sites as an example, where each site has Y AAUs and each AAU supports Z carriers. In this example, the Z carriers driven by the same AAU share the same transceiver, and the transceiver includes M transceiver ports. Figure 3A Shows an AAU 302 that supports Z carriers. Assuming according to the actual situation that the energy consumption can only be measured at the AAU level. The Z carriers deployed on the RRU or AAU 302 cannot sense the energy consumption of their RRU or AAU 302, so the energy consumption per carrier or per cell cannot be measured. Optionally, a network composed of AAUs is selected. Optionally, the network energy consumption estimation is also performed on a network composed of RRUs, or a combination of AAUs and RRUs.

[0075] Figure 3B Shows the local AI / ML energy consumption mapping per AAU. The local AI / ML-based energy consumption estimator / mapping is created for each AAU based on local observations of the carriers of this AAU. In this example, Y local estimators are created.

[0076] Figure 3C Shows the exchange of local AI / ML energy consumption mapping from multiple local AAUs to an optimization node. The primary carrier of each of the multiple local AAUs 304A to 304N shares the local AI / ML-based energy consumption estimator / mapping with an optimization node 306 responsible for optimizing the network energy efficiency. For example, Y local estimators are exchanged.

[0077] The local AI / ML power consumption mapping is exchanged between the multiple local AAUs 304A to 304N and the optimization node 306. The optimization node 306 creates a general AI / ML-based energy consumption mapping and a general estimator for the network at the coordination node. The optimization node 306: (a) refines the local AI / ML-based energy consumption mapping using the global view; (b) performs network energy efficiency optimization using the network AI / ML energy consumption mapping; and (c) shares the updated local AI / ML-based energy consumption mapping with the primary carrier of each of the multiple local AAUs 304A to 304N. In this example, Y updated local estimators are exchanged. The updated local AI / ML energy consumption mapping is also exchanged from the optimization node 306 to each of the multiple local AAUs 304A to 304N.

[0078] Figure 4It is an interaction diagram showing information exchange between a central controller 402, a master AAU 404, and one or more slave AAUs 406 according to an embodiment of the present disclosure. In step 408, the central controller 402 requests a mapping update. In step 410, the master AAU 404 requests mapping inputs from one or more slave AAUs 406. In step 412, the mapping inputs are transmitted from one or more slave AAUs 406 to the master AAU 404. In step 414, the local mapping inputs are measured in the master AAU 404. In step 416, the local mapping inputs are updated. In step 418, the model is shared with the central controller 402. In step 420, the network mapping is updated in the master AAU 404. In step 422, network optimization is performed based on the network mapping. In step 424, the local mapping is updated. In step 426, the central controller 402 shares the mapping with one or more slave AAUs 406.

[0079] Figures 5A to 5B It is an exemplary illustration of a primary carrier in an active antenna unit (AAU) for estimating power consumption in operations within the AAU according to an embodiment of the present disclosure. Each AAU includes a primary carrier 502 and a plurality of secondary carriers 504A to 504N. Optionally, a reporting timing relationship is determined for each of the plurality of secondary carriers 504A to 504N. The primary carrier 502 may be the carrier with the lowest frequency, i.e., the carrier with the largest coverage. After each measurement at the plurality of secondary carriers 504A to 504N, a measurement is reported to the primary carrier 502 immediately. Optionally, the reporting may occur at a certain time after the measurement. The reporting timing may be periodic, for example, 1 minute, or aperiodic.

[0080] The primary carrier 502 of the AAU can obtain the power consumption of this AAU. Then, in each reporting period, the primary carrier 502 in each AAU collects: (i) input data necessary for the AAU to construct a local AI / ML power consumption mapping; (ii) output data necessary for the AAU to construct a local AI / ML power consumption mapping; (iii) input information data necessary for the AAU to construct a local AI / ML power consumption mapping. Similarly, in each reporting period, each of the plurality of secondary carriers 504A to 504N in the AAU also collects corresponding data and sends the data to the primary carrier 502 within the AAU.

[0081] Each of the multiple secondary carriers 504A to 504N in the AAU sends data to the primary carrier 502 within the AAU. The necessary input information for each carrier required for the AAU to create the AI / ML energy consumption estimator / map includes: the number of available TRXs, the carrier transmission mode (i.e., TDD / FDD), the SUL usage status, the carrier frequency, the carrier bandwidth, the maximum transmit power of the carrier during the reporting period, the DL and UL PRB loads of the carrier during the reporting period, the symbol off duration during the reporting period, the channel off duration during the reporting period, the carrier off duration during the reporting period, and the deep sleep duration during the reporting period.

[0082] Figure 5C is an exemplary illustration of a model 506 trained based on the operation information within an active antenna unit (AAU) by Figure 1 the primary carrier. The energy consumption related parameters required for the AAU to create the AI / ML energy consumption estimator / map include the AAU power consumption during the reporting period. After obtaining all the above information, the primary carrier 502 in the AAU trains the AI / ML energy consumption estimator / map of the AAU. Optionally, the training objective is to penalize the prediction error and uncertainty. Optionally, the AI / ML power map / estimator is an artificial neural network (ANN).

[0083] Figures 6A to 6B is an exemplary illustration of the inter-AAU model exchange between one or more secondary AAUs 604A to 604N, the primary AAU 602, and the central controller 606 according to an embodiment of the present disclosure. The optimization node is the primary AAU 602 with the primary carrier responsible for optimizing the network energy efficiency. The inter-AAU model exchange may require a primary AAU selection process. Optionally, the optimization node is the central controller 606 responsible for optimizing the network energy efficiency. The central controller 606 can be located in the control layer or the core (i.e., the management and orchestration entity). Optionally, the central controller 606 is an ORAN controller (e.g., a near-RT RIC or a non-RT RIC).

[0084] In the inter-AAU model exchange, the reporting period can be selected. The reporting period can be set to 1 minute. Optionally, the primary carrier of each of the one or more secondary AAUs 604A to 604N sends the trained local AI / ML-based energy consumption estimator / map to the primary carrier of the primary AAU 602 or to the central controller 606 at each reporting period.

[0085] In the case of model exchange within the AAU, the exchange is achieved through the Xn interface from the primary carrier of the AAU and the primary carrier of the primary AAU. In the case of model exchange within the AAU, the exchange is achieved through an appropriate interface according to the position of the central controller 606.

[0086] Figure 7 It is an exemplary illustration of a federated learning method for constructing and improving local and general AI / ML-based network energy consumption estimators according to an embodiment of the present disclosure. The exemplary illustration includes a plurality of networks 702A to 702N (including a plurality of primary carriers 704A to 704N) and a central controller 706. Using each of the received AI / ML estimators / mappings and AI / ML techniques, the primary carriers of the primary AAUs of the plurality of networks 702A to 702N or the central controller 706 of the plurality of networks 702A to 702N train and continuously improve a general AI / ML-based energy consumption estimator / mapping for the plurality of networks 702A to 702N, each of the local AI / ML-based energy consumption estimators / mappings using a global "view", and other local mappings. Optionally, a federated learning method is used to construct and improve local and general AI / ML-based energy consumption estimators / mappings.

[0087] Optionally, the general AI / ML-based energy consumption estimator / mapping can be used for network energy efficiency optimization. The primary carriers of the primary AAUs of the plurality of networks 702A to 702N or the central controller 706 use the general AI / ML-based energy consumption estimator / mapping as input to run their network energy efficiency optimization logic. The general AI / ML-based energy consumption estimator / mapping can be constructed using the local information of each AAU of the plurality of networks 702A to 702N, which allows the optimized node to predict the energy consumption of any energy-saving strategy configuration tested during the optimization process and identify better network energy-saving configurations for the plurality of networks 702A to 702N.

[0088] Figure 8is an exemplary illustration of a federated learning method for constructing and improving local and general AI / ML-based network plus user equipment (UE) energy consumption estimators according to an embodiment of the present disclosure. The exemplary illustration includes a plurality of network plus UE arrangements 802A to 802N (including a plurality of primary carriers 804A to 804N and a plurality of UEs 806A to 806N) and a central controller 808. For overall network energy consumption optimization, the consumption of the plurality of network plus UE arrangements 802A to 802N can be modeled. Each UE in the plurality of network plus UE arrangements 802A to 802N uses the same AI / ML framework as the primary carrier of the RRU or AAU to create its own AI / ML UE energy consumption estimator / map for creating the estimator / map of the primary carrier. At each reporting period, each AI / ML UE energy consumption estimator / map of the plurality of network plus UE arrangements 802A to 802N is reported to the serving cell via the air interface, and then each serving carrier uses the central controller 808 to combine the AI / ML UE energy consumption estimator / map with its own local AI / ML AAU energy consumption estimator / map.

[0089] Figure 9 is an interaction diagram showing information exchange among a central controller 902, a primary active antenna unit (AAU) 904, a secondary active antenna unit (AAU) 906, and a user equipment (UE) 908 according to an embodiment of the present disclosure. At step 910, the secondary AAU 906 requests an input of cell key performance indicator (KPI) from the UE 908. At step 912, the secondary AAU 906 updates the cell-level KPI. At step 914, the central controller 902 requests a model update from the central controller 902. At step 916, the primary AAU 904 requests a mapping input from the secondary AAU 906. At step 918, the secondary AAU 906 transmits the mapping input to the primary AAU 904. At step 920, the primary AAU 904 measures the local mapping input. At step 922, the primary AAU 904 updates the local mapping input. At step 924, the primary AAU 904 shares the mapping with the central controller 902. At step 926, the central controller 902 updates the network mapping. At step 928, the central controller 902 performs network optimization. At step 930, the central controller 902 applies the local mapping update. At step 932, the central controller 902 shares the mapping with the primary AAU 904, the secondary AAU 906, and the UE 908.

[0090] Figure 10A and Figure 10BFIG. 0 is a flowchart showing a method for estimating energy consumption in a RAN according to an embodiment of the present disclosure. At step 1002, each carrier in one or more remote radio units (RRUs) and / or one or more active antenna units (AAUs) in the RAN reports energy consumption related parameters of the carrier to the primary carrier of the RRU or AAU. At step 1004, the primary carrier in each of one or more RRUs and / or AAUs uses a local artificial intelligence (AI)- or machine learning (ML)-based energy consumption estimator to create a local mapping between the reported energy consumption related parameters of the carriers in the RRU or AAU and the energy consumption of the RRU or AAU using the reported energy consumption related parameters of the carriers in the RRU or AAU. At step 1006, the primary carrier in each of one or more RRUs and / or AAUs reports the local mapping to an optimization node of the RAN. At step 1008, the optimization node uses a general AI- and / or ML-based energy consumption estimator to create a general mapping between the energy consumption related parameters and the energy consumption of all RRUs and / or AAUs in the RAN using all the reported local mappings. At step 1010, for each of the RRUs and / or AAUs, the optimization node uses the local AI- and / or ML-based energy consumption estimator of the RRU or AAU to refine the local mapping between the energy consumption related parameters and the energy consumption using all the reported local mappings.

[0091] This method improves the accuracy of network energy consumption estimation, thus improving network energy saving optimization. This method uses network and energy related information collected at each of the RRUs or AAUs, which allows for the capture of (i) specific network operating conditions, such as traffic, massive MIMO, and (ii) characteristics, such as manufacturing differences and temperature effects, at each of the RRUs or AAUs locally.

[0092] This method enables the acquisition of generalization characteristics crucial for network energy efficiency optimization. This method generalizes across multiple products and parameter configurations, so that, for example, in a scenario where the configuration of a first RRU or AAU has not been measured and is not available in the data used to build the estimator, but this configuration is available for other RRUs or AAUs (e.g., a second RRU or AAU, or a third RRU or AAU), an accurate energy consumption estimate for the first RRU or AAU can be generated.

[0093] Optionally, the method includes: the optimization node reporting the refined local mapping to the primary carrier in each of one or more RRUs and / or AAUs in the RAN.

[0094] Optionally, the method includes: the primary carrier in each of one or more RRUs or AAUs updates the local AI- or ML-based energy consumption estimator using refined local mapping; repeating the steps of claim 1 using the updated local AI- or ML-based energy consumption estimator.

[0095] Optionally, the method includes: the optimization node uses the current state of the general AI- and / or ML-based energy consumption estimator to apply a predefined network energy efficiency optimization policy to the RRUs or AAUs in the RAN.

[0096] Optionally, the optimization node includes the controller of the RAN or the primary carrier of the primary RRU or AAU in the RAN.

[0097] Optionally, the primary RRU or AAU in the RAN is preselected by the controller of the RAN among all the RRUs and / or AAUs in the RAN.

[0098] Optionally, the primary carrier in each of one or more RRUs and / or AAUs is preselected by the controller of the RAN among all the carriers in each of one or more RRUs and / or AAUs.

[0099] Optionally, the method includes: the controller of the RAN defines the architecture of the local AI- or ML-based energy consumption estimator in each primary carrier in each of one or more RRUs and / or AAUs, the architecture including the input and output of the local AI- or ML-based energy consumption estimator, and the time period for other carriers in each of one or more RRUs and / or AAUs to report energy consumption-related parameters; the controller of the RAN defines the architecture of the general AI- or ML-based energy consumption estimator for the optimization node, the architecture including the input and output of the general AI- or ML-based energy consumption estimator. Based on the date values included in the data fields in each row, the table is split into shards consisting of rows.

[0100] Optionally, the method includes: the primary carrier in each of one or more RRUs and / or AAUs defines the energy consumption-related parameters to be reported by other carriers of the RRU or AAU based on the defined input of the local AI- or ML-based energy consumption estimator.

[0101] Optionally, the energy consumption-related parameters reported by the carriers in each of one or more RRUs and / or AAUs include the configuration parameters of the RRU or AAU related to the energy consumption of the RRU or AAU and the carrier-level key performance indicators (KPIs).

[0102] Optionally, two cells exchange information related to the power consumption of their RRU or AAU or AI / ML-based mapping via the air interface or the Xn interface. The exchange of information can be checked by monitoring such an interface using a test device. The test cell can be deployed in a test RRU or AAU, adjacent to another cell of the deployed RRU or AAU, and the test cell can send data on information related to the power consumption of its RRU or AAU or AI / ML-based mapping via the air interface or the Xn interface.

[0103] Optionally, the method does not require standardization and can be implemented on top of existing network energy efficiency platforms. Optionally, standardization of inter-BS information exchange is required to enhance performance and allow interoperability.

[0104] Figure 11 FIG. is a diagram of a computer system (such as a database management system) in which various architectures and functions of the various implementations described above can be implemented. As shown, computer system 1100 includes at least one processor 1104 connected to a bus 1102, where computer system 1100 can be implemented using any suitable protocol, such as Peripheral Component Interconnect (PCI), PCI-Express, Accelerated Graphics Port (AGP), HyperTransport, or any other one or more bus or point-to-point communication protocols. Computer system 1100 also includes a memory 1106.

[0105] The control logic (software) and data are stored in the memory 1106, and the memory 1106 can take the form of a Random-Access Memory (RAM). In the present disclosure, a single semiconductor platform can refer to an integrated circuit or chip based on a sole unitary semiconductor. It should be noted that the term "single semiconductor platform" can also refer to a multi-chip module with enhanced connectivity, which simulates an on-chip module with enhanced connectivity and on-chip operation, and makes substantial improvements compared to using traditional Central Processing Unit (CPU) and bus implementations. Of course, according to the needs of the user, various modules can also be placed separately or in various combinations of semiconductor platforms.

[0106] The computer system 1100 may also include auxiliary storage 1110. The auxiliary storage 1110 includes, for example, hard disk drives and removable storage drives, including floppy disk drives, magnetic tape drives, optical disk drives, digital versatile disk (DVD) drives, recording devices, and universal serial bus (USB) flash memories. The removable storage drives read from and / or write to removable storage units in a well-known manner.

[0107] A computer program or computer control logic algorithm may be stored in at least one of the memory 1106 and the auxiliary storage 1110. When executed, these computer programs enable the computer system 1100 to perform the various functions described above. The memory 1106, the auxiliary storage 1110, and any other memory are possible examples of computer-readable media.

[0108] In one embodiment, the architecture and functionality depicted in the previous various figures may be implemented in the context of a processor 1104, a graphics processor coupled to the communication interface 1112, an integrated circuit (not shown) capable of having at least a portion of the capabilities of the processor 1104 and the graphics processor, and a chipset (i.e., a group of integrated circuits designed to work and be sold as a unit for performing related functions, etc.).

[0109] Furthermore, the architecture and functionality depicted in the previous various figures may be implemented in the context of a general computer system, a circuit board system, a game console system dedicated to entertainment purposes, and an application-specific system. For example, the computer system 1100 may take the form of a desktop computer, a laptop computer, a server, a workstation, a game console, or an embedded system.

[0110] In addition, the computer system 1100 may take the form of various other devices including, but not limited to, personal digital assistant (PDA) devices, mobile phone devices, smartphones, televisions, etc. Additionally, although not shown, the computer system 1100 may be coupled to a network (e.g., a telecommunications network, a local area network (LAN), a wireless network, a wide area network (WAN) such as the Internet, a peer-to-peer network, a cable network, etc.) via the I / O interface 1108 for communication.

[0111] It should be understood that the arrangement of components shown in the described drawings is exemplary, and other arrangements are possible. It should also be understood that the various system components (and devices) defined by the claims, described below and shown in the various block diagrams, represent components in some of the systems configured in accordance with the subject matter disclosed herein. For example, one or more of these system components (and devices) may be implemented, in whole or in part, by at least some of the components shown in the arrangement shown in the described drawings.

[0112] In addition, while at least one of these components is implemented, at least in part, as an electronic hardware component and thus constitutes a machine, other components may be implemented in software, which, when included in an execution environment, constitutes a machine, hardware, or a combination of software and hardware.

[0113] Although the present disclosure has been described in detail along with its advantages, it should be understood that various changes, substitutions, and alterations can be made without departing from the spirit and scope of the present disclosure as defined by the appended claims.

Claims

1. A method for estimating energy consumption in a radio access network (RAN) (102), comprising: Each carrier (105A - 105Z) in each of one or more remote radio units (RRUs) (104A - 104N) and / or one or more active antenna units (AAUs) (106A - 106N) in the RAN (102) reports energy consumption - related parameters of the carrier (105A - 105Z) to a primary carrier (108A - 108Z) of the RRU (104A) or the AAU (106A). Each primary carrier (108A - 108Z) in each of the one or more RRUs (104A - 104N) and / or AAUs (106A - 106N) uses a local artificial - intelligence (AI) - or machine - learning (ML) - based energy - consumption estimator to create a local mapping between the reported energy - consumption - related parameters of the carriers (105A - 105Z) in the RRU (104A) or the AAU (106A) and the energy consumption of the RRU (104A) or the AAU (106A). Each primary carrier (108A - 108Z) in each of the one or more RRUs (104A - 104N) and / or AAUs (106A - 106N) reports the local mapping to an optimization node (110, 306) of the RAN (102). The optimization node (110, 306) uses a general AI - and / or ML - based energy - consumption estimator to create a general mapping between the energy - consumption - related parameters and the energy consumption of all the RRUs (104A - 104N) and / or the AAUs (106A - 106N) in the RAN (102) using all the reported local mappings. The optimization node (110, 306) uses the local AI - and / or ML - based energy - consumption estimator of the RRU (104A) or the AAU (106A) to refine the local mapping between the energy - consumption - related parameters and the energy consumption of each of the RRUs (104A - 104N) and / or the AAUs (106A - 106N) using all the reported local mappings.

2. The method according to claim 1, further comprising: The optimization node (110, 306) reports the refined local mapping to each primary carrier (108A - 108Z) in each of the one or more RRUs (104A - 104N) and / or AAUs (106A - 106N) in the RAN (102).

3. The method according to claim 1 or 2, further comprising: Each primary carrier (108A - 108Z) in each of the one or more RRUs (104A - 104N) or AAUs (106A - 106N) updates the local AI - or ML - based energy - consumption estimator using the refined local mapping. Repeat the steps of claim 1 using the updated local AI- or ML-based energy consumption estimator.

4. The method according to any one of claims 1 to 3, further comprising: The optimization node (110, 306) applies a predefined network energy efficiency optimization strategy to the RRU (104A-104N) or the AAU (106A-106N) in the RAN (102) using the current state of the general AI- and / or ML-based energy consumption estimator.

5. The method according to any one of claims 1 to 4, wherein the optimization node (110, 306) comprises a controller of the RAN (102) or a primary carrier (108A-108Z) of a primary RRU or AAU in the RAN (102).

6. The method according to claim 5, wherein the primary RRU or AAU in the RAN (102) is preselected by the controller of the RAN (102) from all the RRUs (104A-104N) and / or the AAUs (106A-106N) in the RAN (102).

7. The method according to any one of claims 1 to 6, wherein the primary carrier (108A-108Z) in each of the one or more RRUs (104A-104N) and / or AAUs (106A-106N) is preselected by the controller of the RAN (102) from all the carriers (105A-105Z) in each of the one or more RRUs (104A-104N) and / or AAUs (106A-106N).

8. The method according to any one of claims 1 to 7, further comprising: The controller of the RAN (102) defines the architecture of the local AI- or ML-based energy consumption estimator in each primary carrier (108A-108Z) in each of the one or more RRUs (104A-104N) and / or AAUs (106A-106N), the architecture including the input and output of the local AI- or ML-based energy consumption estimator, and the time period for other carriers in each of the one or more RRUs (104A-104N) and / or AAUs (106A-106N) to report the energy consumption related parameters, The controller of the RAN (102) defines the architecture of the general AI- or ML-based energy consumption estimator for the optimization node (110, 306), the architecture including the input and output of the general AI- or ML-based energy consumption estimator.

9. The method according to claim 8, further comprising: The primary carriers (108A-108Z) in each of the one or more RRU (104A-104N) and / or AAU (106A-106N) define the energy consumption related parameters to be reported by other carriers of the RRU (104A) or AAU (106A) based on the defined inputs of the local AI or ML-based energy consumption estimator.

10. The method according to any one of claims 1 to 9, wherein the energy consumption related parameters reported by the carriers (105A-105Z) in each of the one or more RRU (104A-104N) and / or AAU (106A-106N) include the configuration parameters of the RRU (104A) or AAU (106A) related to the energy consumption thereof and the carrier-level key performance indicators (KPIs).

11. A system (100) for estimating energy consumption in a radio access network (RAN) (102), comprising one or more remote radio units (RRU) (104A-104N) and / or one or more active antenna units (AAU) (106A-106N), the system (100) comprising: Carriers (105A-105Z) in each of the one or more RRU (104A-104N) and / or AAU (106A-106N) for reporting energy consumption related parameters of each carrier to the primary carrier (108A-108Z) of the RRU (104A) or the AAU (106A); Wherein, the primary carriers (108A-108Z) in each of the one or more RRU (104A-104N) and / or AAU (106A-106N) are used for: Using a local artificial intelligence (AI) or machine learning (ML)-based energy consumption estimator to create a local mapping between the reported energy consumption related parameters and the energy consumption of the RRU (104A) or the AAU (106A) by using the reported energy consumption related parameters of the carriers (105A-105Z) in the RRU (104A) or the AAU (106A); Reporting the local mapping to the optimization node (110, 306) of the RAN (102); Wherein, the optimization node (110, 306) is used for: Using a general AI and / or ML-based energy consumption estimator to create a general mapping between the energy consumption related parameters and the energy consumption of all the RRU (104A-104N) and / or the AAU (106A-106N) in the RAN (102) by using all the reported local mappings; The local AI- and / or ML-based energy consumption estimator using the RRU (104A) or the AAU (106A) refines the local mapping between the energy consumption related parameters and the energy consumption of each of the RRU (104A - 104N) and / or the AAU (106A - 106N) using all the reported local mappings.

12. The system (100) according to claim 11, wherein the optimization node (110, 306) is further configured to report the refined local mapping to the primary carrier (108A - 108Z) in each of the one or more RRUs (104A - 104N) and / or AAUs (106A - 106N) in the RAN (102).

13. The system (100) according to claim 12, wherein the primary carrier (108A - 108Z) in each of the one or more RRUs (104A - 104N) or AAUs (106A - 106N) is further configured to update the local AI- or ML-based energy consumption estimator using the refined local mapping.

14. The system (100) according to any one of claims 11 to 13, wherein the optimization node (110, 306) is further configured to apply a predefined network energy efficiency optimization strategy to the RRUs (104A - 104N) or the AAUs (106A - 106N) in the RAN (102) using the current state of the general AI- and / or ML-based energy consumption estimator.

15. The system (100) according to any one of claims 11 to 14, wherein the optimization node (110, 306) comprises a controller of the RAN (102) or the primary carrier (108) of the primary RRU or AAU in the RAN (102).

16. The system (100) according to claim 15, wherein, The primary RRU or AAU in the RAN (102) is preselected by the controller of the RAN (102) among all the RRUs (104A - 104N) and / or the AAUs (106A - 106N) in the RAN (102).

17. The system (100) according to any one of claims 11 to 16, wherein the primary carrier (108A - 108Z) in each of the one or more RRUs (104A - 104N) and / or AAUs (106A - 106N) is preselected by the controller of the RAN (102) among all the carriers (105A - 105Z) in each of the one or more RRUs (104A - 104N) and / or AAUs (106A - 106N).

18. The system (100) according to any one of claims 11 to 17, wherein the controller of the RAN (102) is configured to: Define the architecture of the local AI- or ML-based energy consumption estimator in each of the one or more RRUs (104A - 104N) and / or AAUs (106A - 106N), where the architecture includes the input and output of the local AI- or ML-based energy consumption estimator, and the time period during which other carriers in each of the one or more RRUs (104A - 104N) and / or AAUs (106A - 106N) report the energy consumption related parameters. Define the architecture of the general AI- or ML-based energy consumption estimator for the optimization node (110, 306), where the architecture includes the input and output of the general AI- or ML-based energy consumption estimator.

19. The system (100) according to claim 18, wherein each of the main carriers (108A - 108Z) in each of the one or more RRUs (104A - 104N) and / or AAUs (106A - 106N) is used to define the energy consumption related parameters to be reported by the other carriers of the RRU (104A) or AAU (106A) based on the defined input of the local AI- or ML-based energy consumption estimator.

20. The system (100) according to any one of claims 11 to 19, wherein the energy consumption related parameters reported by each of the carriers (105A - 105Z) in each of the one or more RRUs (104A - 104N) and / or AAUs (106A - 106N) include the configuration parameters of the RRU (104A) or AAU (106A) related to the energy consumption of the RRU (104A) or AAU (106A) and the carrier-level key performance indicators (KPIs).

Images