Method of utilizing artificial intelligence to perform air interface algorithms in a wireless communication network

Abstract

A wireless communication network 202 including a Network Node (NW) (204, 402, 602) a Receiver Node (RX) (206, 404, 606) and a Transmitter Node (TX) (208, 406, 610) configured to utilize Artificial Intelligence to perform air interface algorithms is provided. The wireless communication network is configured to (i) obtain channel state information, CSI, and environment state information, ESI, at the global time (t) corresponding with internal sampling index (ℓ) (408, 626) (ii) tokenize the CSI and ESI into state information tokens (x(t)), (iii) predict a future sequence of state information tokens ŷ [ℓ + ]) for a future internal sampling index (ℓ + ), (iv) generate a set of air interface representation inputs (Z[ℓ + ]) for the future internal sampling index (ℓ + ) by performing representation learning on at least some of the channel propagation properties, the environmental properties, and the predicted future sequence of state information tokens, and (iv) performing the air interface algorithms by utilizing the Artificial Intelligence based on the set of air interface representation inputs (Z[ℓ + ]). Additionally, local state information from each node is tokenized and fused to create a comprehensive ESI, ensuring the network operates efficiently in varying conditions.

Description

[0001] METHOD OF UTILIZING ARTIFICIAL INTELLIGENCE TO PERFORM AIR INTERFACE ALGORITHMS IN A WIRELESS COMMUNICATION NETWORK TECHNICAL FIELD

[0002] The disclosure generally relates to wireless communication networks and more particularly, a wireless communication network configured to utilize Artificial Intelligence, Al to perform air interface algorithms by obtaining an Al based representation of channel state information and environment state information. The disclosure also relates to a Network Node (NW) configured to be used in a wireless communication system to obtain and tokenize local network node state information (SINW). The disclosure also relates to a Receiver Node (RX) configured to be used in a wireless communication system to obtain and tokenize local receiver node state information (SIRX). The disclosure also relates to a Transmitter Node (TX) configured to be used in a wireless communication system to obtain and tokenize local transmitter node state information (SITX). Moreover, the disclosure also relates to a method of utilizing Artificial Intelligence, Al to perform air interface algorithms in a wireless communication network by obtaining an Al based representation of channel state information and environment state information.

[0003] BACKGROUND

[0004] In an existing wireless communication network, Artificial Intelligence, Al-based air interface algorithm relies on Channel State Information (CSI) training data to facilitate Al-driven enhancements. Additionally, a Network Node (NW), a transmitter node (TX), and a receiver node (RX) in the existing wireless communication network have access to additional State Information (SI) or Environment Information. When the additional Environment Information is combined with the CSI, the additional Environment Information may improve the characterization of the current wireless propagation conditions and enhance the performance of Al-based algorithms. The additional Environment Information may be User Equipment (UE) position data, rain sensor data, camera inputs, or geographic maps. However, challenges arise in determining how to collect and integrate the additional Environment Information across all nodes, and making it accessible to the Al-based air interface algorithm is difficult. Another challenge is validating the acquired SI, and ensuring time synchronization of the additional Environment Information with the CSI, which is critical for the optimal performance of the Al-based air interface algorithm.

[0005] FIG. 1 illustrates a block diagram of an existing wireless communication network 100 utilizing an Artificial Intelligence (Al) based air interface algorithm 116 in accordance with a prior art. The wireless communication network 100 includes a receiver node (RX) 102, and a transmitter node (TX) 110. The receiver node 102 includes a local receiver State Information (SI) acquisition module 104. The transmitter node 110 includes a receiver SI acquisition module 106, a channel SI (CSI) acquisition module 108, a CSI prediction module 114, and the Al-based air interface algorithms 116. The local receiver node SI acquisition module 104 obtains local receiver node environment SI (ESI) at a time (£RX) or SIRX(tRX) from a source device. The receiver node 102 transmits the SIRX(t) to the transmitter node 110. The receiver SI acquisition module 106 obtains the local receiver node ESI at the internal sampling index ( ), ESIRX[T], The CSI acquisition module 108 obtains the CSI at the internal sampling index ( ) from the source device. The CSI at the internal sampling index ( ) is represented as h(T). The CSI prediction module 114 predicts CSI or h[T + P], The ESIRX[T] and the h[T + P] are fed to the Al-based air interface algorithms 116 by the receiver SI acquisition module 106 and the CSI prediction module 114. The Al-based air interface algorithms 116 make informed decisions on managing communications between the receiver node 102, and the transmitter node 110 based on the ESIRX[ℓ + P] and the h[T + P],

[0006] However, a challenge arises when the timestamp (t) attached to each SI is inaccurate due to communication delays between the receiver node 102 and the transmitter node 110, especially in a rapidly changing wireless environment. These delays complicate real-time synchronization between the ESI and the CSI, leading to potential discrepancies in the representation of the wireless conditions. If these two types of information are not properly synchronized, the Al-based air interface algorithms 116 may fail to accurately reflect the current state of the wireless environment, resulting in outdated or irrelevant data being used by the Al-based air interface algorithms 116. Another limitation is that each Al-based air Interface algorithm has to retrain its model when an additional ESI is added.

[0007] Therefore, there arises a need to address the aforementioned technical problem / drawbacks in acquiring current state information of a wireless environment / network.

[0008] SUMMARY

[0009] It is an object of the disclosure to provide a wireless communication network configured to utilize Artificial Intelligence, Al to perform air interface algorithms by obtaining an Al based representation of channel state information and environment state information, and a method of utilizing Artificial Intelligence, Al to perform air interface algorithms in a wireless communication network by obtaining an Al based representation of channel state information and environment state information.

[0010] This object is achieved by the features of the independent claims. Further, implementation forms are apparent from the dependent claims, the description, and the figures.

[0011] According to a first aspect, a wireless communication network is provided. The wireless communication network includes a Network Node (NW), a Receiver Node (RX), and a Transmitter Node (TX). The wireless communication network is configured to utilize Artificial Intelligence air interface algorithms. The wireless communication network is further configured to obtain channel state information (CSI), at a global time (t) corresponding with internal sampling index ( ). The channel state information includes information on channel propagation properties. The wireless communication network is further configured to obtain environment state information (ESI), at the global time (t) corresponding with internal sampling index ( ). The environment state information includes information on environmental properties. The wireless communication network is further configured to tokenize the CSI and ESI together into a state information token (x(t)). The wireless communication network is further configured to predict a future sequence of state information tokens (ŷ[ℓ + P]) for a future internal sampling index (T + P) based on the sequence of past state information tokens until the global time t ({x(t) }). The wireless communication network is further configured to generate a set of air interface representation inputs (Z[ℓ + P]) for the future internal sampling index (T + P) by performing representation learning on at least some of the channel propagation properties, the environmental properties, and the predicted future sequence of state information tokens, and performing the air interface algorithm(s) utilizing the Artificial Intelligence air interface algorithm(s) based on the set of air interface representation inputs (Z[£ + P]). Each property on which representation learning is performed to provide one air interface representation input (property i → Z(i)[ℓ + P] ). The global time t is a global time reference used by the Network Node (NW), the Receiver Node (RX), and the Transmitter Node (TX). The wireless communication network is further configured to (i) obtain the CSI and (ii) obtain the ESI by obtaining local network node state information (SINW) at the Network Node (NW), obtaining local receiver node state information ( SIRX.) at the Receiver Node (RX), obtaining local transmitter node state information (SITX) at the Transmitter Node (TX), tokenizing the local network node state information (SINW) into network node environment state information (ESINW), tokenizing the local receiver node state information (SIRX) into receiver node environment state information (ESIRX), tokenizing the local transmitter node state information (SITX) into transmitter node environment state information (ESITX), and fusing the network node environment state information (ESINW), the receiver node environment state information (ESIRX), and the transmitter node environment state information (ESITX) into the ESI(t). The wireless communication network accurately synchronizes the data across all nodes (i.e., network node, receiver node, and transmitter node) through the use of a global time reference and different acquisition blocks. By leveraging over-the-air (OTA) updates, the wireless communication network ensures that the network node environment state information (ESINW), the receiver node environment state information (ESIRX). and the transmitter node environment state information (ESITX) are accurately updated in real-time whenever changes are detected in the local network node state information (SINW), the local receiver node state information (SIRX),or the local transmitter node state information (SITX). The wireless communication network ensures that all nodes operate with the most current data, and optimize decision-making for enhanced communication performance. By integrating the global time reference and different acquisition blocks at the network node (NW), the receiver node (RX), and the transmitter node (TX), the wireless communication network ensures synchronized, time-stamped data collection and updates. The use of OTA update procedures and standardized packet formats facilitates continuous communication and timely updates across all nodes, enhancing the overall performance of the wireless communication network. The wireless communication network is particularly used in dynamic environments where accurate, real-time state information is critical for optimizing performance.

[0012] Optionally, the wireless communication network is further configured to obtain the CSI at the Transmitter Node (TX). Optionally, the wireless communication network is further configured to obtain the CSI at the Receiver Node (RX). Optionally, the wireless communication network is further configured to tokenize the local network node state information (SINW) into the network node environment state information (ESINW) at the Network Node (NW), tokenize the local receiver node state information (SIRX) into the receiver node environment state information (ESIRX) at the Receiver Node (RX), and tokenize the local network node state information (SITX) into the transmitter node environment state information (ESITX) at the Transmitter Node (TX).

[0013] Optionally, the wireless communication network is further configured to tokenize the local network node state information (SINW) into the network node environment state information (ESINW), tokenize the local receiver node state information (SIRX) into the receiver node environment state information (ESIRX). and tokenize the local network node state information (SITX) into the network node environment state information (ESITX) at the Transmitter Node (TX). Optionally, the wireless communication network is further configured to tokenize any, some, or all of the local state information utilizing a data modality-specific tokenizer. Optionally, the wireless communication network is further configured to tokenize any, some, or all of the local state information based on RAW state information.

[0014] Optionally, the wireless communication network is further configured to replace any missing element in any, some, or all of the local state information with an empty element symbol (0). Optionally, the wireless communication network is further configured to replace any out-of-date element in any, some, or all of the local state information with an empty element symbol (0).

[0015] Optionally, the wireless communication network is further configured to store any, some, or all of the local state information in a table where each property of the local state information is associated with a variable identifier, ID, an over-the-air (OTA) update timestamp (τ□), an acquisition timestamp (ta), a validity time (T), property data, and property format. Optionally, the property format indicates a data representation used.

[0016] Optionally, the wireless communication network is further configured to, at a global time (t), at the network node (NW), and / or the receiver node (RX), determine if the global time t does not exceed the sum of the acquisition timestamp (ta) and the validity time (T) for a property, and if so, determine if the acquisition timestamp (ta) exceeds the OTA update timestamp (r) for that property, and if so, set the OTA update timestamp (r) for that property to be the current global time (t) and send the property to the transmitter node (TX). Optionally, the wireless communication network is further configured to, at a global time (t) at the network node (NW), the transmitter node (TX), and / or the receiver node (RX), determine if the global time t exceeds the sum of the acquisition timestamp (ta) and the validity time (T) for a property, and if so, trigger a new measurement of that property.

[0017] Optionally, the CSI is a time-stamped vector of size F · N, out of which F(t) · N(t) elements contain frequency domain propagation channels connecting N(t) out of the N = NTX· NRXantenna pairs for a subset of F(t) out of F resources contained in a resource block. The remaining (F − F(t)) · (N − N(t)) entries are filled with the special symbol 0csi to indicate missing elements / information.

[0018] According to a second aspect, a network node configured to be used in a wireless communication system is provided. The network node is configured to obtain local network node state information (SINW). Optionally, the network node is further configured to tokenize the local network node state information (SINW) into network node environment state information (ESINW).

[0019] According to a third aspect, a receiver node configured to be used in a wireless communication system is provided. The receiver node is configured to obtain local receiver node state information (SIRX). Optionally, the receiver node is further configured to tokenize the local receiver node state information ( SIRX) into receiver node environment state information (ESIRX).

[0020] According to a fourth aspect, a transmitter node configured to be used in a wireless communication system is provided. The transmitter node is configured to obtain local transmitter node state information (SITX) and tokenize SITXinto transmitter node environment state information (ESITX). Optionally, the transmitter node is further configured to receive local network node state information (SINW) from a network node and tokenize SINWinto network node environment state information (ESINW). Optionally, the transmitter node is further configured to receive local receiver node state information (SIRX) from a receiver node and tokenize SIRXinto receiver node environment state information (ESIRX).

[0021] According to a fifth aspect, a method for a wireless communication network including a Network Node (NW), a Receiver Node (RX) and a Transmitter Node (TX) is provided. The method includes utilizing Artificial Intelligence air interface algorithms in the wireless communication network. The method further includes obtaining channel state information (CSI), at a global time (t) corresponding with internal sampling index ( ). The channel state information includes information on channel propagation properties. The method further includes obtaining environment state information (ESI), at the global time (t) corresponding with internal sampling index ( ). The environment state information includes information on environmental properties. The method further includes tokenizing the CSI and ESI together into a state information token (x(t)). The method further includes predicting a future sequence of state information tokens (ŷ[ℓ + P]) for a future internal sampling index (£ + P) based on the sequence of past state information tokens until the global time t ({x(t)}). The method further includes generating a set of air interface representation inputs (Z[ℓ + P]) for the future internal sampling index (ℓ + P) by performing representation learning on at least some of the channel propagation properties, the environmental properties, and the predicted future sequence of state information tokens, and performing the air interface algorithm(s) utilizing the Artificial Intelligence air interface algorithm(s) based on the set of air interface representation inputs (Z[£ + P]). Each property on which representation learning is performed to provide one air interface representation input (property i → Z(i)[ℓ + P]). The global time t is a global time reference used by the Network Node (NW), the Receiver Node (RX), and the Transmitter Node (TX). The method further includes (i) obtaining the CSI at a global time t and (ii) obtaining the ESI at the global time t by obtaining local network node state information (SINW) at the network node (NW), obtaining local receiver node state information (SIRX) at the receiver node (RX), obtaining local transmitter node state information (SITX) at the transmitter node (TX), and tokenizing SINWinto network node environment state information (ESINW), tokenizing SIRXinto receiver node environment state information (ESIRX). tokenizing SITXinto transmitter node environment state information (ESITX), and fusing the network node environment state information (ESINW), the receiver node environment state information (ESIRX), and the transmitter node environment state information (ESITX) into the ESI.

[0022] The method accurately synchronizes the data across all nodes (i.e. network node, receiver node, and transmitter node) through the use of a global time reference and different acquisition blocks. By leveraging over-the-air (OTA) updates, the method ensures that the network node environment state information (ESINW), the receiver node environment state information (ESIRX). and the transmitter node environment state information (ESITX) are accurately updated in real-time whenever changes are detected in the local network node state information (SINW), the local receiver node state information (SIRX),or the local transmitter node state information (SITX). The method ensures that all nodes operate with the most current data, and optimize decision-making for enhanced communication performance. By integrating the global time reference and different acquisition blocks at the network node (NW), the receiver node (RX), and the transmitter node (TX), the method ensures synchronized, time-stamped data collection and updates. The use of OTA update procedures and standardized packet formats facilitates continuous communication and timely updates across all nodes, enhancing the overall performance of the wireless communication network. The method is particularly used in dynamic environments where accurate, real-time state information is critical for optimizing performance.

[0023] According to a sixth aspect, a computer program product includes program instructions for performing all the steps of the method when executed by one or more processors in a wireless communication network.

[0024] Therefore, in contradistinction to the existing solutions, the wireless communication system accurately synchronizes data across the network node, the receiver node, and the transmitter node with optimized and enhanced communication performance. By leveraging over-the-air (OTA) updates, the wireless communication network ensures that the network node environment state information (ESINW), the receiver node environment state information (ESIRX). and the transmitter node environment state information (ESITX) are accurately updated in real-time whenever changes are detected in the local network node state information (SINW), the local receiver node state information (SIRX), or the local transmitter node state information (SITX). These and other aspects of the disclosure will be apparent from the implementation s) described below.

[0025] BRIEF DESCRIPTION OF DRAWINGS

[0026] Implementations of the disclosure will now be described, by way of example only, with reference to the accompanying drawings, in which:

[0027] FIG. 1 illustrates a block diagram of an existing wireless communication network utilizing Artificial Intelligence (Al) based air interface algorithm in accordance with a prior art;

[0028] FIG. 2 illustrates a block diagram of a wireless communication network in accordance with an implementation of the disclosure; FIG. 3A illustrates an air interface apparatus using a Wireless Environment State Information, WESI, architecture, implementing prediction and representation in a wireless communication network in accordance with an implementation of the disclosure;

[0029] FIG. 3B illustrates a block diagram of a wireless communication network for processing Wireless Environment State Information (WESI) in accordance with an implementation of the disclosure; FIG. 4 depicts a block diagram of a wireless communication network for acquiring Wireless Environment State Information (WESI) when a tokenizer is positioned at a Network Node (NW), a Receiver Node (RX), a Transmitter Node (TX) in accordance with an implementation of the disclosure;

[0030] FIG. 5 depicts a block diagram of a wireless communication network for acquiring a Wireless Environment State Information (WESI) when a tokenizer is positioned at a Transmitter Node (TX) in accordance with an implementation of the disclosure; FIG. 6 is a flowchart that illustrates a process for acquiring updated Wireless Environment State Information (WESI) using a wireless communication network in accordance with an implementation of the disclosure;

[0031] FIGS. 7A and 7B are flowcharts that illustrate storing and over-the-air (OTA) updates methods used to make the network environment state information available at the transmitter node in accordance with an implementation of the disclosure; FIGS. 8A and 8B are flowcharts that illustrate storing and over-the-air (OTA) updates methods used to make the receiver environment state information available at the transmitter node in accordance with an implementation of the disclosure; FIG. 9 illustrates a block diagram of a process for storing locally at the transmitter node a measurement corresponding with transmitter node state information variable with ID i in accordance with an implementation of the disclosure;

[0032] FIG. 10 illustrates a block diagram of a process for storing locally, at the transmitter node, the update of a local network node state information variable with ID i received via OTA update at global time t in accordance with an implementation of the disclosure;

[0033] FIG. 11 illustrates a block diagram of a process for storing locally, at the transmitter node, the update of a local receiver node state information variable with ID i received via OTA update at global time t in accordance with an implementation of the disclosure;

[0034] FIG. 12 illustrates a block diagram of a method for acquiring a structured representation of Channel State Information (CSI) at a Transmitter node (TX) in a wireless communication network in accordance with an implementation of the disclosure; FIG. 13 illustrates a block diagram of a method for acquiring a structured representation of Environmental State Information (ESI) at a Transmitter node (TX) in a wireless communication network at timestamp ℓ (ESI(ℓ)) in accordance with an implementation of the disclosure;

[0035] FIG. 14 illustrates an exemplary Artificial intelligence (Al) based air interface algorithm implemented in an air interface apparatus in accordance with an implementation of the disclosure;

[0036] FIG. 15 illustrates an architecture for a structured W ireless Environment State Information (WESI) representation in accordance with an implementation of the disclosure;

[0037] FIG. 16 illustrates how a Wireless Environment State Information, WESI, structured representation / air interface representation input features are mapped into the time-frequency grid associated with a transmission block in accordance with an implementation of the disclosure;

[0038] FIG. 17 illustrates how ithfeature of a Wireless Environment State Information, WESI, structured representation / air interface representation input are mapped into the transmission time-frequency grid in accordance with an implementation of the disclosure; FIG. 18 illustrates an exemplary view of Air interface algorithms’ decisions granularities in accordance with an implementation of the disclosure;

[0039] FIGS. 19A-19B illustrate flow diagrams of a method for a wireless communication network including a Network Node (NW), a Receiver Node (RX), and a Transmitter Node (TX) in accordance with an implementation of the disclosure; and FIG. 20 is an illustration of a computer system (e.g., a wireless communication network, tokenizer, network node, transmitter node, and receiver node) in which the various architectures and functionalities of the various previous implementations may be implemented.

[0040] DETAILED DESCRIPTION OF THE DRAWINGS

[0041] Implementations of the disclosure provide a wireless communication network configured to utilize Artificial Intelligence, Al to perform air interface algorithms for obtaining channel state information and environment state information. The disclosure also relates to a Network Node (NW) configured to be used in a wireless communication system to obtain and tokenize local network node state information. The disclosure also relates to a Receiver Node (RX) configured to be used in a wireless communication system to obtain and tokenize local receiver node state information. The disclosure also relates to a Transmitter Node (TX) configured to be used in a wireless communication system to obtain and tokenize local transmitter node state information. Moreover, the disclosure also relates to a method of utilizing Artificial Intelligence, Al to perform air interface algorithms in a wireless communication network by obtaining an Al based representation of channel state information and environment state information.

[0042] To make solutions of the disclosure more comprehensible for a person skilled in the art, the following implementations of the disclosure are described with reference to the accompanying drawings.

[0043] Terms such as “a first”, “a second”, “a third”, and “a fourth” (if any) in the summary, claims, and foregoing accompanying drawings of the disclosure are used to distinguish between similar objects and are not necessarily used to describe a specific sequence or order. It should be understood that the terms so used are interchangeable under appropriate circumstances, so that the implementations of the disclosure described herein are, for example, capable of being implemented in sequences other than the sequences illustrated or described herein. Furthermore, the terms “include” and “have” and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, a method, a system, a product, or a device that includes a series of steps or units, is not necessarily limited to expressly listed steps or units but may include other steps or units that are not expressly listed or that are inherent to such process, method, product, or device.

[0044] Definition:

[0045] Air Interface: An Air Interface is defined as the specification of technologies and protocols (usually involving algorithms from the physical layer (LI) and data link layer (L2) of the OSI model) enabling the wireless communication between a transmitter node and a receiver node in a wireless communication network using a set of radio resources elements in a time-frequency grid, denoted as a transmission block. Examples of Air Interface algorithms are as follows: precoder design, scheduler design, user localization, beamforming, etc.

[0046] Artificial Intelligence, Al, based air interface: An Al-based air interface refers to an air interface, in which the set of protocols or algorithms implementing the specific wireless functionalities is Al-based. That is, they use pre-trained models based on data to take the corresponding actions / decisions. Resource Element: A resource element, RE, is a communication resource considered in the standard specification of specified duration TREseconds and is specified frequency bandwidth BREHz. This is the highest / elementary considered granularity (e.g., in time and frequency) in the 3GPP standard. The following disclosure describes the time and frequency instants using this granularity.

[0047] Transmission block is defined as a set of L • F radio resource elements in the time-frequency grid. A transmission block contains F resource frames, each one including L consecutive resource elements in the time domain. A transmission block contains L resource blocks, each one including F consecutive resource elements in the frequency domain.

[0048] Air interface algorithm: An air interface algorithm or wireless functionality is defined as a process or a set of rules taking decisions / actions enabling the transmission between a transmitter node and a receiver node using a Transmission Block. Note that each wireless functionality may choose a Transmission Block of different sizes (i.e., different L and F) depending on the needed properties. Indeed, in modem communications systems, the actions performed by a wireless functionality usually depend on the propagation channel over which the communication takes place and the dynamics of this channel is dependent on the considered Resource Block.

[0049] Feature representation learning: In machine learning, feature learning, representation learning, or feature representation learning, is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. The feature learning is motivated by the fact that machine learning tasks such as prediction or inference often require input that is mathematically and computationally convenient to process.

[0050] Global time t is a global time reference used by a network node (NW), a receiver node (RX) and a transmitter node (TX). FIG. 2 illustrates a block diagram of a wireless communication network 202 in accordance with an implementation of the disclosure. The wireless communication network 202 includes a Network Node (NW) 204, a Receiver Node (RX) 206 and the Transmitter Node (TX) 208. The network node 204 serves as a control center within the wireless communication network 202.

[0051] The network node 204 manages network resources, coordinates the communication between the transmitter node 208 and the receiver node 206, and ensures seamless data exchange across the network 202. The network node 204 may also collect Channel State Information, CSI, and Environment State Information, ESI, to optimize the communication process and improve network performance. The transmitter node 208 is responsible for generating and transmitting data signals over the air to other nodes within the network 202. The receiver node 206 is responsible for receiving and decoding the signals transmitted by the transmitter node 208.

[0052] The wireless communication network 202 includes Artificial Intelligence (Al) air interface algorithm. The network node 204 is configured to obtain channel state information (CSI), at a global time (t) corresponding with internal sampling index ( / ) to optimize the communication process and improve network performance. The channel state information includes information on channel propagation properties. The wireless communication network 202 is configured to obtain environment state information (ESI), at the global time (t) corresponding with internal sampling index ( / ). The wireless communication network 202 is configured to tokenize the CSI and ESI into a state information token (x(t)). The wireless communication network 202 is configured to predict a future sequence of state information tokens (y[F + P]) for a future internal sampling index (T + P) based on the sequence of past state information tokens until the global time t ({x(t)}). The wireless communication network 202 is configured to generate a set of air interface representation inputs (Z\f + P]) for the future internal sampling index (T + P). The set of air interface representation inputs (Z[F + P]) for the future internal sampling index (T + P) is generated by performing representation learning on at least some of the channel propagation properties, environmental properties, and the p

[0053]

[0054] redicted future sequence of state information tokens. Each property on which representation learning is performed provides one air interface representation input (property i → Z(i)[ℓ + P]). The wireless communication network 202 is configured to perform the air interface algorithm(s) utilizing the Artificial Intelligence air interface algorithm based on the air interface representation inputs (Z[£ + P]).

[0055] The wireless communication network 202 is further configured to (i) obtain the CSI and (ii) obtain the ESI by obtaining local network node state information (SINW) at the Network Node (NW), obtaining local receiver node state information (SI RX) at the Receiver Node (RX), obtaining local transmitter node state information (SITX) at the Transmitter Node (TX), tokenizing the local network node environment state information to obtain network node environment state information (ESINW), tokenizing the local receiver node state information to obtain receiver node environment state information (ESIRX), tokenizing the local transmitter node state information (SITX) into transmitter node environment state information (ESITX), and fusing the network node environment state information (ESINW), the receiver node environment state information (ESIRX), and the transmitter node environment state information (ESITX) into the ESI(ℓ).

[0056] The wireless communication network 202 accurately synchronizes the data across the network node (NW) 204, the receiver node (RX) 206, and the transmitter node (TX) 208, through the use of a global time reference and different acquisition blocks. By leveraging over-the-air (OTA) updates, the wireless communication network 202 ensures that the network node environment state information (ESINW), the receiver node environment state information (ESIRX), and the transmitter node environment state information (ESITX) are accurately updated in real-time whenever changes are detected in the local network node state information (SINW), the local receiver node state information (SIRX), or the local transmitter node state information (SITX). The wireless communication network 202 ensures that all nodes operate with the most current data, and optimize decision-making for enhanced communication performance. By integrating the global time reference and different acquisition blocks at the network node (NW) 204, receiver node (RX) 206, and transmitter node (TX) 208, the wireless communication network 202 ensures synchronized, time-stamped data collection and updates. The use of OTA update procedures and standardized packet formats facilitates continuous communication and timely updates across all nodes, enhancing the overall performance of the wireless communication network 202. The wireless communication network 202 is particularly used in dynamic environments where accurate, real-time state information is critical for optimizing performance.

[0057] Optionally, the wireless communication network 202 is further configured to obtain the CSI at the Transmitter Node (TX) 208.

[0058] Optionally, the wireless communication network 202 is further configured to obtain the CSI at the Receiver Node (RX) 206.

[0059] Optionally, the wireless communication network is further configured to tokenize the local network node state information (SINW) into the network node environment state information (ESINW) at the Network Node (NW) 204, tokenize the local receiver node state information (SIRX) into the receiver node environment state information (ESIRX) at the Receiver Node (RX) 206, and tokenize the local network node state information (SITX) into the transmitter node environment state information (ESITX) at the Transmitter Node (TX) 208.

[0060] Optionally, the wireless communication network 202 is further configured to tokenize the local network node state information (SINW) into the network node environment state information (ESINW), tokenize the local receiver node state information (SIRX) into the receiver node environment state information (ESIRX), and tokenize the local network node state information (SITX) into the network node environment state information (ESITX) at the Transmitter Node (TX) 208. Optionally, the wireless communication network 202 is further configured to tokenize any, some, or all of the local state information utilizing a data modality-specific tokenizer. Optionally, the wireless communication network 202 is further configured to tokenize any, some, or all of the local state information based on RAW state information.

[0061] Optionally, the wireless communication network 202 is further configured to replace any missing element in any, some, or all of the local state information with an empty element symbol (0). Optionally, the wireless communication network 202 is further configured to replace any out-of-date element in any, some, or all of the local state information with an empty element symbol (0).

[0062] Optionally, the wireless communication network 202 is further configured to store any, some, or all of the local state information in a table where each property of the state information is associated with a variable identifier, ID, an over-the-air (OTA) update timestamp (τ□), an acquisition timestamp (ta), a validity time (T), property data, and property format. Optionally, the property format indicates a data representation used.

[0063] Optionally, the wireless communication network 202 is further configured to, at a global time (t), at the network node (NW) 204, and / or the receiver node (RX) 206, determine if the global time t exceeds the sum of the acquisition timestamp (ta) and the validity time (T) for a property, and if not, determine if the acquisition timestamp (ta) exceeds the OTA update timestamp (r), and if so, set the OTA update timestamp (r) for that property to be the current global time (t) and send the property to the transmitter node (TX) 208. Optionally, the wireless communication network 202 is further configured to, at a global time (t) at the network node (NW) 204, the receiver node (RX) 206, and / or the transmitter node (TX) 208, determine if the global time t exceeds the sum of the acquisition timestamp (ta) and the validity time (T) for a property, and if so, trigger a new measurement of that property.

[0064] Optionally, the CSI is a time-stamped vector of size F ■ N, out of which F(t) · N(t) elements contain the frequency domain propagation channels connecting N(t) out of the N = NTX·

[0065]

[0066] antenna pairs for a subset of F(t) out of F resources contained in a resource block. The remaining (F − F(ℓ)) · (N − N(t)) entries are filled with the special symbol 0csi to indicate missing elements / information.

[0067] The network node 204 is configured to be used in a wireless communication system, and is configured to obtain local network node state information (SINW). Optionally, the network node 204 is further configured to tokenize the local network node state information (SINW) into network node environment state information (ESINW). The receiver node 206 is configured to be used in a wireless communication system, and is configured to obtain local receiver node state information (SIRX). Optionally, the receiver node 206 is further configured to tokenize the local receiver node state information (SIRX.) into receiver node environment state information (ESIRX).

[0068] The transmitter node 208 is configured to be used in the wireless communication system, and is configured to obtain local transmitter node state information (SITX) and tokenize SITXinto network node environment state information (ESITX). Optionally, the transmitter node 208 is further configured to receive local network node state information (SINW) from a network node 204 and tokenize SINWinto network node environment state information (ESINW). Optionally, the transmitter node 208 is further configured to receive local receiver node state information (SIRX) from a receiver node 206 and tokenize SIRXinto receiver node environment state information (ESIRX).

[0069] FIG. 3A illustrates an air interface apparatus 314A using a Wireless Environment State Information, WESI, architecture 300A, implementing prediction and representation in a wireless communication network in accordance with an implementation of the disclosure. The WESI architecture 300A includes a WESI acquisition block including a channel state information (CSI) acquisition block 302A, and an environment state information (ESI) acquisition block 304A, a WESI tokenizer block 306A, a WESI sequence predictor block 308A, a WESI property list 310A, a WESI structured representation block 312A. The output of the WESI representation block 312 A represent the input of the artificial intelligence, Al, based air interface algorithms 316 A.

[0070] The CSI acquisition block 302A obtains the CSI at a global time (t) corresponding with internal sampling index (ℓ). The CSI includes information on channel propagation properties. The ESI acquisition block 304A obtains the ESI at the global time (t) corresponding with internal sampling index (ℓ). The ESI includes information includes information on environmental properties. The environment state information may contain at least any one information captured by sensors such as cameras, lidars, weather-related sensors, GPS sensors at a network node, a receiver node, and a transmitter node. Optionally, the environment state information may contain prior information available at a transmitter node, TX, a receiver node, RX, and a network node, NW. The prior information may be at least any of a geographical map and a site-specific hardware information, at the network node, the receiver node, and the transmitter node. Optionally, the ESI is a time-synchronized ESI. The ESI acquisition block 304A may collect, clean, timestamp, tokenize, and store the ESI from the environmental property and the prior information.

[0071] CSI (t) is a time-stamped CSI vector of size F • N obtained either at the transmitter node or the receiver node and containing the frequency-domain propagation channels in h(T), connecting N(t) of the N = NTX· NRXantenna pairs for a subset of F(t) out of the F resources contained in a resource block. The remaining (F — F(t)) · (N — N(t)) entries are filled with the special symbol 0csi to indicate missing elements / information.

[0072] ESI(t) is a time-stamped environment state information vector with S = SNW+ SRX+ STXstate information variables, which fuses the environment state information acquired at the NW node, at the RX node and at the TX node, denoted by ESINW(t). ESIRX(t), and ESITX( t), respectively. ESINW(t) is obtained from the local NW node state information acquired at global time tNW, SINW(tNW), and received by the TX node at global time τNW, which is a time-stamped vector gathering SNW(tNW) out of SNWpossible local state information variables (i.e., with 0 < SNW(tNW) < SNW), by applying data-modality specific tokenizers to the SNW(tNW) state variables and by filling the remaining (SNW— SNW(tNW)) state variables with special symbol 0NWto indicate missing information. ESIRX(t) is obtained from the local RX node state information acquired at global time tRX, SIRX(tRX), and received by the TX node at global time τRX, which is a time-stamped vector gathering SRX(tRX) out of SRXpossible local state information variables (i.e., with 0 ≤ SRX(tRX) ≤ SRX), by applying data-modality specific tokenizers to the SRX(tRX) state variables and by filling the remaining (SRX— SRX(tRX)) state variables with special symbol ØRXto indicate missing information. ESITX(t) is obtained from the local TX node state information acquired at global time tTX, SITX(tTX), which is a time-stamped vector gathering STX(tTX) out of STXpossible local state information variables (i.e., with 0 < STX(tTX) < STX), by applying data-modality specific tokenizers to the STX(tTX) state variables and by filling the remaining (STX— STX(tTX)) state variables with special symbol ØTXto indicate missing information.

[0073] The WESI tokenizer block 306A includes a combination of pre-processing and embedding techniques that are configured to (i) handle hardware impairments (e.g., phase offset) in the CSI data and address special symbols in the ESI data, (ii) combine the ESI and CSI data, and (iii) provide an embedding block to map WESI into a lower-dimensional space. The WESI tokenizer block 306A may tokenize the CSI and ESI data into a state information token (x(t)) using a pre-trained model. The WESI tokenizer block 306A applies an embedding process to map the WESI data into a lower-dimensional space. Optionally, x(t) is a token vector of size d < F • N, including a token joint representation of ESI and CSI for all N antenna pairs and all F resource elements within the resource block.

[0074] The WESI sequence predictor block 308A predicts a future sequence of state information tokens (ŷ[ℓ + P]) for a future internal sampling index (ℓ + P) based on the sequence of past state information tokens until the global time t ({x(t)}). The WESI sequence predictor block 308A obtains a length L sequence of state information tokens (ŷ[ℓ + P]) by predicting the state information tokens for the next transmission frame (of length L) at time ℓ + P.

[0075] The predicted future sequence of state information tokens (ŷ[ℓ + P]) is used to obtain the structured WESI representation (Z[ℓ + P]) at internal sampling index ℓ + P, which gathers the D individual features (Z(i)[ℓ + P] for i = 1,..., D) defined in the WESI property list 310A at a specific time and frequency granularity covering the transmission block starting at internal sampling index ℓ + P. The WESI property list 310A defines each feature characterizing a physical quantity of a wireless environment. The feature may be a signal strength, an interference level, a channel conditions, and other environmental metrics. The predicted future sequence of state information tokens (ŷ[ℓ + P]) is represented in minimum time granularity for the whole transmission block starting at time ℓ + P. Each wireless environment property in the WESI property list specifies a representation dimensionality such as an output dimension, a representation size, and a time-frequency span of property validity.

[0076] The WESI structured representation block 312A generates a set of air interface representation inputs (Z[ℓ + P]) for the future internal sampling index (T + P) by performing representation learning on at least some of the channel propagation properties and environmental properties and the predicted future sequence of state information tokens (ŷ[ℓ + P]). Each property on which representation learning is performed on provides one air interface representation input (property i →

[0077]

[0078] [ℓ + P]).

[0079] The air interface apparatus 314A takes decisions on the transmission parameters to enable communication at internal sampling index ℓ + P between the transmitter node (e.g., a wireless transmitter node) and the receiver node (e.g., a wireless receiver node) within the transmission block using the Al- based air interface algorithm 316 A. The transmission block is a set of resource elements in a time-frequency grid. Each of the Al-based algorithms adapt its decision to the wireless channel propagation conditions based on a subset of individual features in the WESI property list 310A. The Al-based air interface algorithms 316A may include a precoder design, a scheduler design, a user localization, and a beamforming.

[0080] FIG. 3B illustrates a block diagram of a wireless communication architecture 300B for processing Wireless Environment State Information (WESI) in accordance with an implementation of the disclosure. The wireless communication architecture 300B includes a WESI acquisition block 302B, a WESI tokenizer 304B, and a WESI sequence predictor 306B. The WESI acquisition block 302B acquires WESI a global time (t) corresponding with internal sampling index (ℓ) from sensors, prior information, and measurements at different points in the wireless communication architecture 300B such as a transmitter node (TX), a receiver node (RX), and a network node (NW). The WESI includes Channel State Information (CSI) and Time-Synchronized Environment State Information (ESI). The wireless communication architecture 300B assigns timestamp (t) to the WESI. The wireless communication architecture 300B preprocess the WESI with the timestamp (t) to remove noise and irrelevant information. The wireless communication architecture 300B stores the preprocessed WESI with the timestamp (t) in its database. The WESI tokenizer 304B tokenizes the WESI data to obtain tokenized sequence / vector. The WESI sequence predictor 306B predicts states of the wireless environment / communication based on the tokenized sequence / vector. The wireless communication architecture 300B organizes the tokenized sequence / vector into a structured format that is utilized by Al based air-interface models for the establishing the wireless communication.

[0081] FIG.4 depicts a block diagram of a wireless communication network 400 for acquiring Wireless Environment State Information (WESI) when a tokenizer is positioned at a Network Node (NW) 402, a Receiver Node (RX) 404, a Transmitter Node (TX) 406 in accordance with an implementation of the disclosure. The wireless communication network 400 includes the network node 402, the receiver node 404, and the transmitter node 406. The network node 402 includes local network state information (SI) acquisition block 410, and a network SI tokenizer 412. The receiver node 404 includes local receiver SI acquisition block 414, and a receiver SI tokenizer 416. The transmitter node 406 includes channel state information (CSI) acquisition block 418, a transmitter SI acquisition block 420, a transmitter SI tokenizer 422, and a ESI update and data fusion block 424. The wireless communication network 400 is configured to receive RAW state information from a source device over the air. The RAW state information may be a local network node state information (SINW), local receiver node state information (SIRX), and local transmitter node state information (SITX).

[0082] At the network node 402, the local network SI acquisition block 410 obtains the local network node state information (SINW) at a global time (tNW) 408, that is SINW(tNW). At the receiver node 404, the local receiver SI acquisition block 414 obtains the local receiver node state information ( SIRX) at a global time (tRX) 408, that is SIRX(tRX). At the transmitter node 406, the transmitter SI acquisition block 420 obtains the local transmitter node state information (SITX) at a global time (tTX) 408, that is SITX(tTX). For each node (i.e., the network node 402, the receiver node 404, or the transmitter node 406), SINW, SIRX, SITXare sets of fields or state information variables that describe specific aspects of SI relevant to that node. The SI may be information captured by different sensors such as cameras, lidars, weather-related sensors, GPS sensors and other prior information such as geographical maps, site-specific hardware information.

[0083] The wireless communication network 400 is configured to store the local state information in a table where each property of the local state information is associated with a variable identifier, ID, an OTA update timestamp (τ□), an acquisition timestamp (ta), a validity time (T), property data, and property format. The table may be a network SI table (Table 1 A), a receiver SI table (Table IB), or a transmitter SI table (Table 1C). The transmitter SI table does not include OTA update timestamp (τ□). The OTA update timestamp (τ□) indicates the timestamp of the last over-the-air update for any change or modification to a variable associated with the variable ID. The acquisition timestamp (ta) indicates a timestamp at which state information (SI) or data associated with the variable related to the variable ID is acquired. The validity time (T) indicates the duration for which the data, associated with the variable related to the variable ID, is considered valid after it is acquired, i.e., how long the acquired data remains usable before it needs to be updated or refreshed. The property data indicates that the data corresponding to the variable associated with the variable ID is stored. The property format indicates the data representation method used. This means how the data is structured, formatted, or transformed for storage, transmission, or processing.

[0084] Table: 1 A illustrates the storing format of the local network node state information in the network SI table.

[0085] Table: 1 A Network SI table

[0086] ID OTA ACQUISITION TIME DATA FORMAT TIMESTAMP TIMESTAMP VALIDITY

[0087] 1 T 'n(lCNC1W))

[0088] LNW ' NW

[0089] i TC0'p(i)

[0090] CNWLNW ' NW aU® f VtL® ) TOKENIZER NWJ

[0091] T(SNW) +(5NW) 'p(

[0092] 5N5Nw)

[0093] W6TOKENIZER NWLNW ' NW «(SNw)(tNWWb

[0094]

[0095] Table: IB illustrates the storing format of the local receiver node state information in the receiver SI table.

[0096] Table: IB receiver SI table

[0097] ID OTA TIMESTAMP TIME DATA FORMAT TIMESTAMP VALIDITY

[0098] 1 TCRC1X)'n(l)

[0099] LRX7TOKENIZER

[0100] RX

[0101] i T 'p(iC C0)

[0102] LTOKENIZER RX RX7RX

[0103] T(5RX) f(SRx) 'T(SRX)

[0104] ■$RX6TOKENIZER

[0105] RXLRX1RX

[0106]

[0107] Table: 1C illustrates the storing format of the local transmitter node state information in the transmitter SI table. The same format is used at the transmitter node 406 to store the received network node state information and the received receiver node state information. ID ACQUISITION TIME VALIDITY DATA FORMAT

[0108] TIMESTAMP

[0109] 1 LTXfpCO

[0110] JTOKENIZER TX rw(4x)

[0111] i LTX'p(i)

[0112] JTOKENIZER TX rw(4x)

[0113] ■$TX LTX'p(i)

[0114] JTX rwTOKENIZER

[0115] (4x)

[0116]

[0117] The wireless communication network 400 is configured to tokenize local state information based on RAW state information. The local state information may be the local transmitter node state information (SITX), the local receiver node state information (SIRX), or the local network node state information (SINW). The network SI tokenizer 412 tokenizes the local network node state information with acquisition timestamp (tNW) to obtain the network node environment state information ESINW(tNW) and transmits ESINW(tNW) to the transmitter node 406 over air. The receiver SI tokenizer 416 tokenizes the local receiver node state information with acquisition timestamp (tRX) to obtain the receiver node environment state information ESIRX(tRX) and transmits ESIRX( tRX) to the transmitter node 406 over air. The transmitter SI tokenizer 422 tokenizes the local transmitter node state information with acquisition timestamp (tTX) to obtain the transmitter node environment state information ESITX(tTX)

[0118] At the transmitter node 406, at the global time (t) 408, with t ≥ tNW≥ tRX≥ tTX, the CSI acquisition module 418 obtains CSI (t) and the ESI update and data fusion module 424 obtains ESI(t). The ESI update and data fusion module 424 checks the network environment state information ESINW(tNW), obtained from the local NW node state information acquired at the global time tNW, for missing or outdated local state information variables and substitutes them by special symbol 0NWand obtains ESINW(t). The ESI update and data fusion module 424 checks the receiver environment state information ESIRX(tRX), obtained from the local RX node state information acquired at the global time tRX, for missing or outdated local state information variables, substitutes them by special symbol ØRXand obtains ESIRX(t). The ESI update and data fusion module 424 checks the transmitter environment state information ESITX(tTX), obtained from the local TX node state information acquired at the global time tTX, for missing or outdated local state information variables, substitutes them by special symbol 0TXand obtains ESITX(t). The ESI update and data fusion module 424 fuses the resulting network environment state information ESINW(t), receiver environment state information ESIRX(t), and transmitter environment state information ESITX(t) at the global time (t) 408 into ESI(t). The wireless communication system acquires the WESI(t) at the global time (t) by concatenating the ESI(t) and CSI(t).

[0119] FIG. 5 depicts a block diagram of a wireless communication network 500 for acquiring a Wireless Environment State Information (WESI) when a tokenizer is positioned at a Transmitter Node (TX) 510 in accordance with an implementation of the disclosure. The wireless communication network 500 includes a network node (NW) 502, a receiver node (RX) 506, and the transmitter node (TX) 510. The network node 502 includes local network state information (SI) acquisition block 504. The receiver node 506 includes local receiver SI acquisition block 508. The transmitter node 510 includes a channel state information (CSI) acquisition block 512, a transmitter SI acquisition block 514, a transmitter SI tokenizer 520, a receiver SI tokenizer 518, a network SI tokenizer 516 and a data fusion block 522. The wireless communication network 500 is configured to receive RAW state Information from a source device over the air. The RAW state information may be a local network node state information (SINW), local receiver node state information (SIRX), and local transmitter node state information (SITX). At the network node 502, the local network SI acquisition block 504 obtains the local network node state information (SINW) at a global time (tNW) 526, that is SINW(tNW), stores the SINW(tNW), and transmits the SINW(tNW) to the transmitter node over the air. At the receiver node 506, the local receiver SI acquisition block 508 obtains the local receiver node state information (SIRX) at a global time (tRX) 526, that is SIRX(tRX), stores the SI

[0120]

[0121] and transmits the SIRX(tRX) to the transmitter node over the air. At the transmitter node 510, the transmitter SI acquisition block 514 obtains the local transmitter node state information (SITX) at a global time (tTX) 526, that is SITX(tTX), and stores the SITX(tTX).

[0122] The wireless communication network 500 is configured to store the local state information in a table where each property of the local state information is associated with a variable identifier, ID, an OTA update timestamp (τ□), an acquisition timestamp (ta), a validity time (T), property data, and property format. The OTA update timestamp indicates for a variable identifier (ID) the time of the last update. The table may be a network SI table (Table 1A), a receiver SI table (Table IB), or a transmitter SI table (Table 1C). The transmitter SI table does not include OTA update timestamp (τ□).

[0123] At the transmitter node 510, the network SI tokenizer 516 tokenizes the local network node state information SINW(tNW) and obtains ESINW(tNW). The receiver SI tokenizer 518 tokenizes the local receiver node state information SIRX(tRX) and obtains ESIRX(tRX). The transmitter SI tokenizer 520 tokenizes the local transmitter node state information SITX(tTX) and obtains ESITX(tTX).

[0124] At the transmitter node 510, at the global time (t) 526, with t ≥ tNW≥ tRX≥ tTX, the CSI acquisition module 512 obtains CSI(t) and the ESI update and data fusion module 522 obtains ESI(t). The ESI update and data fusion module 522 checks ESINW(tNW) for missing or outdated local state information variables, substitutes them by special symbol 0NW, and obtains ESINW(t). The ESI update and data fusion module 522 checks ESIRX(tRX) for missing or outdated local state information variables, substitutes them by special symbol ØRX, and obtains ESIRX(t). The ESI update and data fusion module 522 checks the transmitter environment state information ESITX(tTX) for missing or outdated local state information variables, substitutes them by special symbol 0TXand obtains ESITX(t). The ESI update and data fusion module 522 fuses the resulting network environment state information ESINW(t), receiver environment state information ESIRX(t), and transmitter environment state information ESITX(t) at the global time (t) 526 into ESI(t). The wireless communication system 500 acquires the WESI(t) at the global time (t) by concatenating the ESI(t) and CSI(t).

[0125] FIG. 6 is a flowchart that illustrate a process for acquiring updated Wireless Environment State Information (WESI) using a wireless communication network in accordance with an implementation of the disclosure.

[0126] In step 602, at a network node, at a global time

[0127]

[0128] the wireless communication network (i) detects a change or measurement in a network state information field for identifier (ID) i, (ii) updates the network state information corresponding to the field of the ID i based on the detected change or measurement in the local network SI table (according to the format in Table 1 A), and (iii) transmits the updated network state information over the air to a transmitter node (TX) using the OTA packet format in Table 2A.

[0129] In step 604, at a receiver node, at a global time

[0130]

[0131] the wireless communication network (i) detects a change or measurement in a receiver state information field for identifier (ID) i, (ii) updates the receiver state information corresponding to the field of the ID i based on the detected change or measurement in the local receiver SI table (according to the format in Table IB), and (iii) transmits the updated receiver state information over the air to the transmitter node using the OTA packet format in Table 2B. In step 606, at the transmitter node, at a global time, the transmitter node (i) receives the updated network state information for the ID i, (ii) stores it in the network SI table (according to the format in Table 1C), and (iii) tokenizes it by applying a data-modality specific tokenizer.

[0132] In step 606, at the transmitter node, at a global time tRX(i), the transmitter node receives (i) the updated receiver state information for the ID i, (ii) stores it in the network SI table (according to the format in Table 1C), and (iii) tokenizes it by applying a data-modality specific tokenizer.

[0133] In step 606, at the transmitter node, at a global time tTX(i), the wireless communication network (i) detects a change or measurement in a transmitter state information field for identifier (ID) i, and (ii) updates the transmitter state information corresponding to the field of the ID i based on the detected change or measurement in the local transmitter SI table (according to the format in Table 1C), and (iii) tokenizes it by applying a data-modality specific tokenizer.

[0134] In step 606, at the transmitter node, at a global time ( t), with t >

[0135]

[0136] > t^v the wireless communication network obtains Channel State Information (CSI) at the global time (t) from the measured CSI h(t). The CSI vector consists of F · N entries, where F is the number of REs contained in a resource block and N is the number of antenna pairs or spatial streams. The wireless communication network inserts a special symbol 0CSIin the CSI vector to represent unavailable data in the CSI vector for any missing or incomplete CSI in h(t).

[0137] In step 606, at the transmitter node (TX), at the global time (t), the ESI update and data fusion module 522 checks the local network node state information SINWat the stored at the TX in the network SI table for missing or outdated local state information variables, substitutes them by special symbol ØNW, and obtains ESINW(t). The ESI update and data fusion module 522 checks the local receiver node state information SIRXat the stored at the TX in the receiver SI table for missing or outdated local state information variables, substitutes them by special symbol ØRX, and obtains ESIRX(t). checks the local receiver node state information SITXat the stored at the TX in the transmitter SI table for missing or outdated local state information variables, substitutes them by special symbol ØTXand obtains ESITX(t). The wireless communication network fuses the ESINW(t), ESIRX(t), ESITX(t) to obtain the environment state information at the global time t, or timestamped ESI vector or ESI(t). The ESI vector consists of S = SNW+ SRX+ STXstate information variables that is obtained from ESINW(t), ESIRX(t), and ESITX(t). The SNWrepresents the number of network state information variables. The S|! Xrepresents the number of receiver state information variables. The STXrepresents the number of transmitter state information variables. The wireless communication network obtains the updated WESI by combining the ESI(t), and CSI(t).

[0138] Table: 2A illustrates the structure of a packet used for OTA updates of a network node state information variable associated with a specific ID i.

[0139] Table 2A data row: NW | i | t_NW^(i) | T_NW^(i) | α^(i)(t_NW^(i)) | TOKENIZER

[0140]

[0141] “t0C)

[0142] Table: 2B illustrates the structure of a packet used for OTA updates of a receiver node state information variable associated with a specific ID i.

[0143] SRC. ID ACQUISITION TIME DATA FORMAT TIMESTAMP VALIDITY

[0144]

[0145] RX i 'p(i)

[0146] L7TOKENIZER RX RX

[0147]

[0148] The tables 2A and 2B illustrate the structure of a packet used for OTA updates of a variable associated with a specific ID. The packet includes one or more fields. The one or more fields include source, SRC, the ID, acquisition timestamp, time validity, data, and format. The SRC field indicates a source of the update. The source of the update can either be from the network node or the transmitter node, which specifies where the update is originating. The ID is a unique identifier for the variable being updated which is used for distinguishing between different variables that may require updates. The acquisition timestamp field captures the time when the data for the variable is acquired. The acquisition timestamp is used for tracking when the data is acquired. The time validity indicates the duration for which the acquired data is considered valid. The time validity is used in determining whether the data is still applicable or if it has expired. The data is related to SI that corresponds to the variable of the ID which is being updated. The format field describes how the data is represented or the method used for tokenization. FIGS. 7A and 7B are flowcharts that illustrate storing and over-the-air (OTA) updates methods used to make the network environment state information available at the transmitter node in accordance with an implementation of the disclosure, as it is required to generate a Wireless Environment State Information (WESI). FIG 7A illustrates the procedure for storing locally at the network node a measurement corresponding with network node state information variable with ID i in accordance with an implementation of the disclosure. FIG 7B illustrates the procedure for checking if an OTA update or a new local measurement is required for any of the network node state information variables in accordance with an implementation of the disclosure after network node state information variable with ID i has been received and stored.

[0149] At step 702, at a global time t^y, a RAW measurement aW(t^) for the local network node state information variable with ID i is obtained. At step 704, the RAW measurement data a(l)(t y) for local network node state information variable with ID i is tokenized using the corresponding tokenizer at the network node. In the absence of a specific tokenizer, the corresponding data is converted using the corresponding data format. In either case, the storing representation data a^(t^y) for the local network node state information variable with ID i is obtained. At step 706, the local network node state information variable with ID i update is stored in the network SI table (Table 1 A) by setting the acquisition timestamp to t^y, time validity to T$y, data to a® (t^) and format either to the tokenizer or representation used in step 704. At this point, the OTA timestamp update is not modified and remains to be

[0150]

[0151] which corresponds to the time stamp of the latest OTA update for the local network node state information variable with ID i. Optionally, the method, in FIG 7B, is executed to check if an OTA update or a new local measurement is required for any of the network node state information variables.

[0152] In FIG. 7B, an exemplary procedure for checking at a global time t the validity status of all SNWlocal network node state information variables, that is, variable with ID j for j = 1,..., SNW. At step 708, it is determined whether local network node state information variable with ID j is outdated or not by determining if the global time (t) exceeds the sum of its acquisition timestamp and its validity time (7^). At step 710, if yes, a new measurement is triggered for the local network node state information variable with ID j. At step 712, if no, it is determined whether the local network node state information variable with ID j is outdated at the transmitter node by determining if its acquisition timestamp

[0153]

[0154] exceeds its OTA update timestamp (r^w) or not. At step 714, if yes, the local network node state information variable with ID j stored in the network SI Table is communicated to the transmitter node via an OTA update using the packet format in Table 2A. At step 716, the OTA update timestamp (τNW(j)) for the local network node state information variable with ID j stored in the network SI Table is set to the global time (t). FIGS. 8A and 8B are flowcharts that illustrate storing and over-the-air (OTA) updates methods used to make the receiver environment state information available at the transmitter node in accordance with an implementation of the disclosure, as it is required to generate a Wireless Environment State Information (WESI). FIG 8A illustrates the procedure for storing locally a measurement corresponding with receiver node state information variable with ID i in accordance with an implementation of the disclosure. FIG 8B illustrates the procedure for checking if an OTA update or a new local measurement is required for any of the receiver node state information variables in accordance with an implementation of the disclosure after receiver node state information variable with ID i has been received and stored.

[0155] At step 802, at a global time

[0156]

[0157] a RAW measurement /

[0158]

[0159] ? W (t^) for the local receiver node state information variable with ID i is obtained. At step 804, the RAW measurement data

[0160]

[0161] for local receiver node state information variable with ID i is tokenized using the corresponding tokenizer at the receiver node. In the absence of a specific tokenizer, the corresponding data is converted using the corresponding data format. In either case, the storing representation data /

[0162]

[0163] ? W (t^) for the local receiver node state information variable with ID i is obtained. At step 806, the local receiver node state information variable with ID i update is stored in the receiver SI table (Table IB) by setting the acquisition timestamp to

[0164]

[0165] time validity to TRX(i), data to β(i)(tRX(i)) and format either to the tokenizer or representation used in step 804. At this point, the OTA timestamp update is not modified and remains to be τRX(i), which corresponds to the time stamp of the latest OTA update for the local network node state information variable with ID i. Optionally, the method, in FIG 8B, is executed to check if an OTA update or a new local measurement is required for any of the network node state information variables.

[0166] In FIG 8B, an exemplary procedure for checking at global time t the validity status of all SRXlocal receiver node state information variables, that is, variable with ID j for j = 1,..., SRX. At step 808, it is determined whether local network node state information variable with ID j is outdated or not by determining if the global time (t) exceeds the sum of its timestamp and its validity time (T^). At step 810, if yes, a new measurement is triggered for the local network node state information variable with ID j. At step 812, if no, it is determined whether the local network node state information variable with ID j is outdated at the transmitter node by determining if if its acquisition timestamp

[0167]

[0168] exceeds its OTA update timestamp (r^) or not. At step 814, if yes, the local network node state information variable with ID j stored in the network SI Table is communicated to the transmitter node via an OTA update using the packet format in Table 2B. At step 816, the OTA update timestamp (τRX(j)) for the local receiver node state information variable with ID j stored in the network SI Table is set to the global time (t).

[0169] FIG. 9 illustrates a block diagram of a process for storing locally at the transmitter node a measurement corresponding with transmitter node state information variable with ID i in accordance with an implementation of the disclosure. At step 902, at a global time tTX(i), a RAW measurement γ̃(i)(tTX(i)) for the local transmitter node state information variable with ID i is obtained. At step 904, the RAW measurement data γ̃(i)(tTX(i)) for local transmitter node state information variable with ID i is tokenized using the corresponding tokenizer at the transmitter node. The tokenized data γ(i)(tNW(i)) for the local transmitter node state information variable with ID i is obtained. At step 906, the local transmitter node state information variable with ID i update is stored in the transmitter SI table (Table 1C) by setting the acquisition timestamp to tNW(i), time validity to TNW(i), data to α(i)(tNW(i)) and format either to the tokenizer or representation used in step 904.

[0170] FIG. 10 illustrates a block diagram of a process for storing locally, at the transmitter node, the update of a local network node state information variable with ID i received via OTA update at global time t in accordance with an implementation of the disclosure. At step 1002, at a global time (t), the network node receives an OTA update packet with SRC field equal to NW. At step 1004, the transmitter node tokenizes the data contained in the DATA field of the OTA if the format / tokenizer specified in the FORMAT field is not the required one. At step 1006, the transmitter node updates the information for the local network node state information variable with ID equal to the ID field in the OTA update packet stored in the network SI table. ID is set to the ID field in the OTA update packet, ACQUISITION TIMESTAMP is set to the ACQUISITION TIMESTAMP field in the OTA update packet, DATA is set to the result of step 1004, and format is set to either the FORMAT field in the OTA update packet if the data was not modified in step 1004 or to the tokenizer applied in step 1004, otherwise.

[0171] FIG. 11 illustrates a block diagram of a process for storing locally, at the transmitter node, the update of a local receiver node state information variable with ID i received via OTA update at global time t in accordance with an implementation of the disclosure. At step 1102, at a global time (t), the network node receives an OTA update packet with SRC field equal to RX. At step 1104, the transmitter node tokenizes the data contained in the DATA field of the OTA if the format / tokenizer specified in the FORMAT field is not the required one. At step 1106, the transmitter node updates the information for the local receiver node state information variable with ID equal to the ID field in the OTA update packet stored in the network SI table. ID is set to the ID field in the OTA update packet, ACQUISITION TIMESTAMP is set to the ACQUISITION TIMESTAMP field in the OTA update packet, DATA is set to the result of step 1104, and format is set to either the FORMAT field in the OTA update packet if the data was not modified in step 1004 or to the tokenizer applied in step 1104, otherwise.

[0172] FIG. 12 illustrates a block diagram a method for acquiring a structured representation of Channel State Information (CSI) at a transmitter node (TX) in a wireless communication network in accordance with an implementation of the disclosure. At step 1202, a value of the CSI at global time (t) is measured. The value of CSI is represented by h(t). For instance, the value of the CSI is measured at received signals at a receiver node while the transmitter node transmits the signals to the receiver node. At step 1204, the measured value h(t) of the CSI is inserted at a corresponding position of a CSI vector CSI(t). This means, that once the value of the CSI is measured at the global time (t), the value of the CSI is inserted into a predefined position in the CSI vector that corresponds to the global time (t). At step 1206, when certain frequencies are missing from the CSI measurement h(t), a special symbol, 0Fis inserted at the corresponding positions in the CSI vector for the certain frequencies. This symbol acts as a placeholder, indicating that the information for the certain frequencies is not available at the global time (t). At step 1208, when certain antenna pairs are missing from the CSI measurement h(t), a special symbol, 0Ais inserted at the corresponding positions in the CSI vector for the missing antenna pairs.

[0173] At step 1210, a vector representation of the CSI or CSI(t) is acquired at the transmitter node. The CSI(t) includes the measured values of the CSI at the global time (t) along with the inserted special symbols 0Fand 0Afor the missing frequencies and antenna pairs, respectively. At step 1212, environment state Information, ESI acquisition is triggered at the transmitter node after measuring the value of the CSI at the global time (t).

[0174] FIG. 13 illustrates a block diagram of a method for acquiring a structured representation of Environmental State Information (ESI) at a Transmitter node (TX) in a wireless communication network at a global time t l'ESI(t)) in accordance with an implementation of the disclosure.

[0175] Steps 1302, 1304, 1306, and 1308 illustrate a method to obtain the NW node environment state information at the global time t (ESINW(t)) from the local NW node state information stored at the TX node. For all SNWlocal network node state information variables, that is, variable with ID i for i = 1,..., SNW, in step 1302, it is determined whether the state information variable associated with ID i is outdated or not. The outdated is determined by checking whether the global time (t) exceeds the sum of its timestamp and its validity time (7^). If it is outdated, in step 1304, a special symbol ØNWis inserted into network environment state information vector ESINW(ℓ) at the position corresponding to ID i. If it is updated, in step 1306, a measurement process is triggered to obtain local network node state information from the NW node for state information variable with ID i. If it is not updated, in step 1308, the data for that variable stored at the TX node in the network SI table is inserted at into network environment state information vector ESINW(ℓ) at the position corresponding to ID i. Steps 1310, 1312, 1314, and 1316 illustrate a method to obtain the RX node environment state information at the global time t (ESIRX (t) ) from the local RX node state information stored at the TX node. For all SRXlocal receiver node state information variables, that is, variable with ID i for i = 1,..., SRX, in step 1310, it is determined whether the state information variable associated with ID i is outdated or not. The outdated is determined by checking whether the global time (t) exceeds the sum of its timestamp and its validity time (

[0176]

[0177] T^). If it is outdated, in step 1312, a special symbol ØRXis inserted into receiver environment state information vector ESIRX(t) at the position corresponding to ID i. If it is updated, in step 1314, a measurement process is triggered to obtain local receiver node state information from the RX node for state information variable with ID i. If it is not updated, in step 1316, the data for that variable stored at the TX node in the receiver SI table is inserted at into receiver environment state information vector ESIRX(t) at the position corresponding to ID i.

[0178] Steps 1318, 1320, 1322, and 1324 illustrate a method to obtain the TX node environment state information at the global time t ( ESITX( t) ) from the local TX node state information stored at the TX node. For all STXlocal transmitter node state information variables, that is, variable with ID i for i = 1,..., STX. in step 1318, it is determined whether the state information variable associated with ID i is outdated or not. The outdated is determined by checking whether the global time (t) exceeds the sum of its timestamp (tTX(i)) and its validity time (TTX(i)). If it is outdated, in step 1320, a special symbol ØTXis inserted into transmitter environment state information vector ESITX(t) at the position corresponding to ID i. If it is updated, in step 1322, a measurement process is triggered to obtain local transmitter node state information from the TX node for state information variable with ID i. If it is not updated, in step 1324, the data for that variable stored at the TX node in the receiver SI table is inserted at into transmitter environment state information vector ESITX(t) at the position corresponding to ID i.

[0179] In step 1326, the NW node environment state information vector at the global time t (ESINW(ℓ)), the RX node environment state information vector at the global time t (ESIRX(ℓ)), and the TX node environment state information vector at the global time t (ESITX(ℓ)) are fused into environment state information vector, ESI(t).

[0180] FIG. 14 illustrates an exemplary Artificial intelligence, Al, based air interface algorithm implemented in an air interface apparatus in accordance with an implementation of the disclosure. The predicted Wireless Environment State Information, WESI, sequence tokens 1402 (ŷ[ℓ + P]) is given as input to the WESI Structured Representation Block 1404 including D WESI feature representation learning modules, each one corresponding to a one of D properties contained in the WESI property list 1408 (property i → Z(i)[ℓ + P]). FIG. 14 explicitly shows a WESI feature 1 representation learning module 1404A, a WESI feature 2 representation learning module 1404B, a WESI feature i representation learning module 14041, a WESI feature D — 1 representation learning module 1404D, and a WESI feature D representation learning module 1404C.

[0181] A possibly different subset of the set of air interface representation inputs (Z[£ + P]) are combined to generate an air interface representation input to each one of the A Al-based air interface algorithms 1406 to make decisions on transmission parameters for communication. For instance, in FIG. 14, the output of the WESI feature 1 representation learning module 1404A represented as Z(1)[ℓ + P] and the WESI feature 2 representation learning module 1404B represented as Z(2)[ℓ + P] combines with the output of the WESI feature D — 1 representation learning module 1404D represented as

[0182]

[0183] Z(D-1)[ℓ + P] to generate an air interface representation input and communicates the air interface representation input to an AI-based air interface algorithm 1406A to make decisions on transmission parameters for communication. The output of the WESI feature i representation learning module 14041 represented as Z(i)[ℓ + P] generates and sends an air interface representation input to an Al based air interface algorithm 1406C to make decisions on transmission parameters for communication. The output of the WESI feature D representation learning module 1404C represented as Z(D)[ℓ + P] and WESI feature D — 1 representation learning module 1404D represented as

[0184]

[0185] Z(D-1)[ℓ + P] are combined to generate an air interface representation input and communicates the air interface representation input to the Al based air interface algorithm 1406B to make decisions on transmission parameters for communication.

[0186] FIG. 15 illustrates an architecture for structured Wireless Environment State Information (WESI) representation in accordance with an implementation of the disclosure. The architecture shows a predicted WESI sequence tokens 1502 (y\P + P]), a WESI Property List 1504 and a WESI structured representation block 1506. The WESI Property List 1504 includes a WESI Property 1, a WESI Property i, and a WESI Property D. Each WESI property specifies a representation dimensionality such as an output dimension, a representation size, and a time-frequency span of property validity associated with the corresponding WESI feature representation learning module.

[0187] The WESI structured representation block 1506 includes a WESI feature 1 representation learning 1506A, a WESI feature i representation learning 15061, and a WESI D representation learning 1506D. The predicted WESI sequence tokens 1502 fl / [T + P]), at minimum time granularity for the whole resource frame starting at internal sampling index T + P, in which transmission is taking place, and is transferred to the property to each one of the WESI feature representation learning modules for performing representation learning on the D WESI properties specified in the WESI property list 1504 and to generate a set of air interface representation inputs. Such air interface representation input is provided as input to an Al-based air interface algorithm. For instance, for the predicted WESI token sequence of length L for time T + P,y[P + P], containing the L predicted WESI tokens at minimum time granularity for a transmission block starting at time T + P, the WESI structured representation block 1506 obtains the air interface representation input (i.e., WESI structured representation) as Z[ℓ + P] = {Z(1)[ℓ + P],..., Z(i)[ℓ + P],..., Z(D)[ℓ + P]}, where Z(i)[ℓ + P] denotes the ith individual feature, which corresponds to the ith WESI property specified in the WESI property list 1504 for the transmission block starting at time ℓ + P at its specified time and frequency granularity, as shown in FIG. 16.

[0188] FIG. 16 illustrates how a Wireless Environment State Information, WESI, structured representation / air interface representation input features are mapped into the time-frequency grid associated with a transmission block in accordance with an implementation of the disclosure. For example, the WESI structured representation of feature 1 1602 includes a time granularity of 4 and a frequency granularity of F / 4. Hence, the WESI representation learning of feature 1 is {z® [P + Pj.z^lP + P],..., z

[0189]

[0190] ^ / 4, [P + P], z® [P + P],..., z^4[P + P] J. Similarly, the WESI structured representation of feature D 1604 includes a time granularity of L RE and a frequency granularity of F / 2 REs. Hence, the WESI representation learning of feature D 1604 i

[0191]

[0192] s [z^[F + P], z^[F + P]}.

[0193] FIG. 17 illustrates how ithfeature of a Wireless Environment State Information, WESI, structured representation / air interface representation are mapped into the time-frequency grid associated with a transmission block in accordance with an implementation of the disclosure. The WESI structured representation of feature i 1702 has time granularity r;= L / Lt, where L is the total number of REs in a resource frame, and frequency granularity A,- = F / F,- where F is total number of REs in a resource block. Then, the WESI structured representation is obtained asL>[P + P] = {z® [P + P], zS,1^ [P + P],..., z^ [P + P], z® [P + P],..., Z

[0194]

[0195] p^L. [P + P] J, where z®. [P + P] G is the feature vector characterizing the (th WESI property for time frequency block containing F;x Ltresource elements starting at the resource element at position ( / — 1)F;+ 1 of the resource block at position (y — 1)L;+ 1 in the time of the transmission block.

[0196] FIG. 18 illustrates an exemplary view of an Air interface algorithm’s decisions granularities in accordance with an implementation of the disclosure. A set of A Al-based air interface algorithms 1802 take decision on the transmission parameters for a transmission block to be used for communication. Each air interface algorithm 1802 has a time granularity and a frequency granularity to take decisions on non-overlapping time frequency blocks inside the transmission block. The time and frequency granularities of a WESI structure representation required by an air interface algorithm 1802 are not smaller than the time and frequency granularities of the algorithm’s decisions.

[0197] FIGS. 19A-19B illustrate flow diagrams of a method for a wireless communication network including a Network Node (NW), a Receiver Node (RX), and a Transmitter Node (TX) in accordance with an implementation of the disclosure. At step 1902, the method includes obtaining channel state information, CSI, at a global time (t) corresponding with internal sampling index ( ). The channel state information includes information on channel propagation properties. At step 1904, the method includes obtaining environment state information, ESI, at the global time (t) corresponding with internal sampling index ( ). The environment state information includes information on environmental properties. At step 1906, the method further includes tokenizing the CSI and ESI together into a state information token (x(t)). At step 1908, the method further includes predicting a future sequence of state information tokens (ŷ[ℓ + P]) for a future internal sampling index (T + P) based on the sequence of past state information tokens until the global time t ({x(t)}).

[0198] At step 1910, the method includes generating a set of air interface representation inputs (Z(T + P)) for the future internal sampling index (T + P) by performing representation learning on at least some of the channel propagation properties and environmental properties, and the predicted future sequence of state information tokens. Each property on which representation learning is performed on provides one air interface representation input (property i -> Z^[f + P]). The global time t is a global time reference used by the Network Node (NW), the Receiver Node (RX), and the Transmitter Node (TX). At step 1912, the method includes performing the air interface algorithm(s) utilizing the Artificial Intelligence air interface algorithm(s) based on the air interface representation inputs Z(£ + P)).

[0199] The method further includes (i) obtaining the CSI at a global time t and (ii) obtaining the ESI at the global time t by obtaining local network node state information (SINW) at the network node (NW), obtaining local receiver node state information (SI RX) at the receiver node (RX), obtaining local transmitter node state information (SITX) at the transmitter node (TX), and tokenizing SINWinto network node environment state information (ESINW), tokenizing SIRXinto receiver node environment state information (ESIRX), tokenizing SITXinto transmitter node environment state information (ESITX), and fusing the network node environment state information (ESINW), the receiver node environment state information (ESIRX), and the transmitter node environment state information (ESITX) into the ESI (P).

[0200] The method accurately synchronizes the data across all nodes (network, receiver, and transmitter) through the use of a global time reference and different acquisition blocks. By leveraging over-the-air (OTA) updates, the method ensures that the network node environment state information (ESINW), the receiver node environment state information (ESIRX), and the transmitter node environment state information (ESITX) are accurately updated in real-time whenever changes are detected in the local network node state information (SINW), the local receiver node state information (SIRX), or the local transmitter node state information (SITX). The wireless communication network ensures that all nodes operate with the most current data, and optimize decision-making for enhanced communication performance. By integrating the global time reference and different acquisition blocks at the network node (NW), receiver node (RX), and transmitter node (TX), the method ensures synchronized, time-stamped data collection and updates. The use of OTA update procedures and standardized packet formats facilitates continuous communication and timely updates across all nodes, enhancing the overall performance of the wireless communication network. The method including the wireless communication network is particularly used in dynamic environments where accurate, real-time state information is critical for optimizing performance.

[0201] In an embodiment, a computer program product including program instructions for performing all the steps of the method when executed by one or more processors in a wireless communication network is provided. FIG. 20 is an illustration of a computer system (e.g., a wireless communication network, tokenizer, network node, transmitter node, and receiver node) 2000 in which the various architectures and functionalities of the various previous implementations may be implemented. As shown, the computer system 2000 includes at least one processor 2004 that is connected to a bus 2002, wherein the computer system 2000 may be implemented using any suitable protocol, such as Peripheral Component Interconnect, PCI, Express, Accelerated Graphics Port, AGP, Hyper Transport, or any other bus or point-to-point communication protocol. The computer system 2000 also includes a memory 2006.

[0202] Control logic (software) and data are stored in the memory 2006 which may take a form of random-access memory, RAM. In the disclosure, a single semiconductor platform may refer to a sole unitary semiconductor-based integrated circuit or chip. It should be noted that the term single semiconductor platform may also refer to multi-chip modules with increased connectivity which simulate on-chip modules with increased connectivity which simulate on-chip operation and make substantial improvements over utilizing a conventional central processing unit, CPU, and bus implementation. Of course, the various modules may also be situated separately or in various combinations of semiconductor platforms per the desires of the user. The computer system 2000 may also include a secondary storage 2010. The secondary storage 2010 includes, for example, a hard disk drive and a removable storage drive, representing a floppy disk drive, a magnetic tape drive, a compact disk drive, a digital versatile disk, a DVD drive, a recording device, a universal serial bus, a USB flash memory. The removable storage drives at least one of reads from and writes to a removable storage unit in a well-known manner.

[0203] Computer programs, or computer control logic algorithms, may be stored in at least one of the memory 2006 and the secondary storage 2010. Such computer programs, when executed, enable the computer system 2000 various functions as described in the foregoing. The memory 2006, the secondary storage 2010, and any other storage are possible examples of computer-readable media.

[0204] In an implementation, the architectures and functionalities depicted in the various previous figures may be implemented in the context of the processor 2004, a graphics processor coupled to a communication interface 2012, an integrated circuit (not shown) that is capable of at least a portion of the capabilities of both the processor 2004 and a graphics processor, a chipset (namely, a group of integrated circuits designed to work and sold as a unit for performing related functions, and so forth). Furthermore, the architectures and functionalities depicted in the various previous-described figures may be implemented in a context of a general computer system, a circuit board system, a game console system dedicated to entertainment purposes, an application-specific system. For example, the computer system 2000 may take the form of a desktop computer, a laptop computer, a server, a workstation, a game console, or an embedded system.

[0205] Furthermore, the computer system 2000 may take the form of various other devices including, but not limited to a personal digital assistant, PDA, device, a mobile phone device, a smart phone, a television, and so forth. Additionally, although not shown, the computer system 2000 may be coupled to a network (for example, 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, or the like) for communication purposes through an I / O interface 2008.

[0206] It should be understood that the arrangement of components illustrated in the figures described is exemplary and that other arrangements may be possible. It should also be understood that the various system components (and means), defined by the claims, described below, and illustrated in the various block diagrams, represent components in some systems configured according to the subject matter disclosed herein. For example, one or more of these system components (and means) may be realized, in whole or in part, by at least some of the components illustrated in the arrangements illustrated in the described figures. In addition, while at least one of these components is implemented at least partially as an electronic hardware component, and therefore constitutes a machine, the other components may be implemented in software that when included in an execution environment constitutes a machine, hardware, or a combination of software and hardware.

[0207] Although the disclosure and its advantages have been described in detail, it should be understood that various changes, substitutions, and alterations can be made herein without departing from the spirit and scope of the disclosure as defined by the appended claims.

Claims

CLAIMS1. A wireless communication network (202) comprising a Network Node (NW) (204, 402, 602), a Receiver Node (RX) (206, 404, 606) and a Transmitter Node (TX) (208, 406, 610), wherein the wireless communication network is configured to utilize Artificial Intelligence to perform air interface algorithms, wherein the wireless communication network is characterized in that the wireless communication network is further configured to,obtain channel state information (CSI), at a global time (t) corresponding with an internal sampling index ( ) (408, 626), wherein the channel state information comprises information on channel propagation properties,obtain environment state information (ESI), at the global time (t) corresponding to the internal sampling index ( ), wherein the environment state information comprises information on environmental properties,tokenize the CSI and ESI together into a state information token (x(t)),predict a future sequence of state information tokens (y[-t + P]) for a future internal sampling index (T + P) based on the sequence of past state information tokens until the global time t ({x(t)}),generate a set of air interface representation inputs (Z[£ + P]) for the future internal sampling index (T + P) by performing representation learning on at least some of the channel propagation properties and environmental properties, and the predicted future sequence of state information tokens, wherein each property on which representation learning is performed on provides one air interface representation input (property i → Z(i)[ℓ + P]), and then toperform the air interface algorithm(s) utilizing the Artificial Intelligence based on the air interface representation inputs (Z[£ + P]), wherein the global time is a global time reference used by the Network Node (NW), the Receiver Node (RX) and the Transmitter Node (TX) and wherein the wireless communication network is further configured toobtain the CSI andobtain the ESI by:at the Network Node (NW), obtaining local network node environment state information (SINW),at the Receiver Node (RX), obtaining local receiver node environment state information (SIRX),at the Transmitter Node (TX), obtaining local transmitter node environment state information (SITX), andtokenizing the local network node state information (SINW) into network node environment state information (ESINW),tokenizing the local receiver node state information (SIRX) into receiver node environment state information (ESIRX).tokenizing the local transmitter node state information (SITX) into transmitter node environment state information (ESITX), andfusing the network node environment state information (ESINW), the receiver node environment state information (ESIRX) and the transmitter node environment state information (ESITX) into the ESI(t).

2. The wireless communication network (202) according to claim 1, wherein the wireless communication network is further configured to obtain the CSI at the Transmitter Node (TX).

3. The wireless communication network (202) according to claim 1, wherein the wireless communication network is further configured to obtain the CSI at the Receiver Node (RX).

4. The wireless communication network (202) according to any preceding claim, wherein the wireless communication network is further configured totokenize the local network node state information (SINW) into the network node environment state information (ESINW) at the Network Node (NW),tokenize the local receiver node state information (SIRX) into the receiver node environment state information (ESIRX) at the Receiver Node (RX), andtokenize the local transmitter node state information (SITX) into the transmitter node environment state information (ESITX) at the Transmitter Node (TX).

5. The wireless communication network (202) according to any of claims 1 to 3, wherein the wireless communication network is further configured to tokenizethe local network node state information (SINW) into the network node environment state information (ESINW),the local receiver node state information (SIRX) into the receiver node environment state information (ESIRX), andthe local transmitter node state information (SITX) into the transmitter node environment state information (ESITX) at the Transmitter Node (TX).

6. The wireless communication network (202) according to any preceding claim, wherein the wireless communication network is further configured to tokenize any, some, or all of the local state information utilizing a data modality-specific tokenizer.

7. The wireless communication network (202) according to any preceding claim, wherein the wireless communication network is further configured to tokenize any, some, or all of the local state information based on RAW state information.

8. The wireless communication network (202) according to any preceding claim, wherein the wireless communication network is further configured to replace any missing element in any, some or all of the local state information with an empty element symbol (0).

9. The wireless communication network (202) according to any preceding claim, wherein the wireless communication network is further configured to replace any out-of-date element in any, some or all of the local state information with an empty element symbol (0).

10. The wireless communication network (202) according to any preceding claim, wherein the wireless communication network is further configured to store any, some, or all of the local state information in a table where each property of the local state information is associated witha variable identifier, ID,an over-the-air (OTA) update timestamp (r) indicating the time for the last update, an acquisition timestamp (ta),a validity time (T),property data, andproperty format.

11. The wireless communication network (202) according to claim 10, wherein the property format indicates a data representation used.

12. The wireless communication network(202) according to any preceding claim, wherein the wireless communication network is further configured to at the network node, and / or the receiver node, determine if the global time (t) does not exceed the sum of the acquisition timestamp (ta) and the validity time (T) for a property, and if so, determine if the acquisition timestamp (ta) exceeds the OTA update timestamp (r) for that property, and if so,set the over-the-air update timestamp (r) for that property to be the current global time (t) andsend the property to the transmitter node.

13. The wireless communication network (202) according to any preceding claim, wherein the wireless communication network is further configured to at the network node, the transmitter node and / or the receiver node, determine if the global time t exceeds the sum of the acquisition timestamp (ta) and the validity time (T) for a property, and if so, trigger a new measurement of that property.

14. The wireless communication network (202) according to any preceding claim, wherein the CSI is a time-stamped vector of size F · N, out of which F(t) · N(t) elements contain frequency domain propagation channels connecting, N(t) out of the N = NTX· NRXantenna pairs for a subset of F(t) out of F resources contained in a resource block.

15. A network node (204, 402, 602) configured to be used in a wireless communication system, wherein the network node is configured to obtain local network node state information (SINW).

16. The network node (204, 402, 602) according to claim 15, further configured to tokenize the local network node state information (SINW) into network node environment state information (ESINW).

17. A receiver node (206, 404, 606) configured to be used in a wireless communication system, wherein the receiver node is configured to obtain local receiver node state information (SIRX).

18. The receiver node (206, 404, 606) according to claim 17, further configured to tokenize the local receiver node state information (SI RX) into receiver node environment state information (ESI RX).

19. A transmitter node (208, 406, 610) configured to be used in a wireless communication system, wherein the transmitter node is configured toobtain local transmitter node state information (SITX) and tokenize the local transmitter node state information into transmitter node environment state information (ESITX).

20. The transmitter node (208, 406, 610) according to claim 19, further configured toreceive local receiver node state information (SIRX) from a receiver node (206, 404, 606) and tokenize the local receiver node state information into receiver node environment state information (ESIRX).

21. The transmitter node (208, 406, 610) according to claim 19 or 20, further configured toreceive local network node state information (SINW) from a network node (204, 402, 602) and tokenize the local network node state information (SINW) into network node environment state information (ESINW).

22. A method for a wireless communication network (202) comprising a Network Node (NW) (204, 402, 602), a Receiver Node (RX) (206, 404, 606), and a Transmitter Node (TX) (208, 406, 610), wherein the method comprises utilizing Artificial Intelligence to perform air interface algorithms in the wireless communication network, wherein the method is characterized in that the method further comprisesobtaining channel state information (CSI), an internal sampling index (P) (408, 626), wherein the channel state information comprises information on channel propagation properties,obtaining environment state information (ESI), at the global time (t) corresponding with the internal sampling index (P), wherein the environment state information comprises information on environmental properties,tokenizing the CSI and ESI together into a state information token (x(t))predicting a future sequence of state information tokens (y\P + P\ for a future internal sampling index (P + P) based on the sequence of past state information tokens until the global time t ({x(t)}),generating a set of air interface representation inputs (Z\P + P]) for the future internal sampling index (P + P) by performing representation learning on at least some of the channel propagation properties and environmental properties and the predicted future sequence of state information tokens, wherein each property on which representation learning is performed on provides one air interface representation input property i ->\P + P]), and then performing the air interface algorithm(s) utilizing the Artificial Intelligence based on the air interface representation inputs (Z\f + P]), wherein the global time is a global time reference used by the Network Node (NW), the Receiver Node (RX), and the Transmitter Node (TX) and wherein the method further comprisesobtaining the CSI andobtaining the ESI by:at the Network Node (NW), obtaining local network node environment state information (SINW),at the Receiver Node (RX), obtaining local receiver node environment state information (SIRX),at the Transmitter Node (TX), obtaining local transmitter node environment state information (SITX), andtokenizing the local network node state information (SINW) into network node environment state information (ESINW),tokenizing the local receiver node state information (SIRX) into receiver node environment state information (ESIRX).tokenizing the local transmitter node state information (SITX) into transmitter node environment state information (ESITX), andfusing the network node environment state information (ESINW), the receiver node environment state information (ESIRX) and the transmitter node environment state information (ESITX) into the ESI(t).

23. A computer program product comprising program instructions for performing the method according to claim 22, when executed by one or more processors in a wireless communication network (202).

Images