Embodiments provide a power adjustment method and an access network device, and the embodiments relate to the field of communication technologies. A target power increase value is adaptively determined based on a target key characteristic of a target cell, so that a cell coverage loss and a cell capacity loss caused by channel shutdown are compensated for, and a good energy-saving effect is obtained. The access network device blocks transmit channels that are of some of a plurality of antennas and that correspond to the target cell. Then, the access network device obtains the target key characteristic of the target cell, and determines the target power increase value based on the target key characteristic. The access network device increases, based on the target power increase value, transmit power of the access network device corresponding to the target cell or a target user.

A system described herein may provide for the use of artificial intelligence/machine learning (“AI/ML”) techniques to generate models for various locations or regions (e.g., sectors) associated with one or more radio access networks (“RANs”) of a wireless network. The system may further use AI/ML techniques to generate interference models to reflect types and/or amounts of channel propagation metrics measured within the RAN. The system may further determine, based on attributes of a given sector, a sector model and/or a channel propagation model associated with the sector. Based on the sector model and/or the determined channel propagation model, one or more actions may be determined in order to enhance channel propagation metrics within the sector, such as at portions of the sector at which increased demand for wireless service is detected.

Modulating and optimizing operation parameters such as power usage of wireless networks include determining a baseline reference level for a network demand at a base station in a network during a first time interval. The transmission power of the base station corresponding to the baseline reference level is determined, and the network demand at the base station in the network is forecasted during a second time interval. A difference between the projected network demand and the baseline reference level at the second time is determined. The transmission power of the base station is adjusted by a predetermined increment during the second time interval based at least on the difference.

Methods, apparatus, systems and articles of manufacture to trigger calibration of a sensor node using machine learning are disclosed. An example apparatus includes a machine learning model trainer to train a machine learning model using first sensor data collected from a sensor node. A disturbance forecaster is to, using the machine learning model and second sensor data, forecast a temporal disturbance to a communication of the sensor node. A communications processor is to transmit a first calibration trigger in response to a determination that a start of the temporal disturbance is forecasted and a determination that a first calibration trigger has not been sent.

ML/AI configuration information for one of UL channel prediction, DL channel estimation, or cell selection/reselection includes: one or more of enabling/disabling an ML approach for the UL channel prediction, the DL channel estimation, or cell selection/reselection; one or more ML models to be used for the UL channel prediction, the DL channel estimation, or cell selection/reselection: trained model parameters for the one or more ML models for the UL channel prediction, the DL channel estimation, or cell selection/reselection; and/or whether ML model parameters for the UL channel prediction, the DL channel estimation, or cell selection/reselection received from the UE at the base station will be used. The ML/AI configuration information is transmitted from a BS to a UE, and the UE transmits UE assistance information for updating the one or more ML models for the UL channel prediction, the DL channel estimation or cell selection/reselection to the BS.

A mobile ad hoc network (MANET) includes a first MANET node having a first radio frequency (RF) transceiver and a first controller coupled thereto to generate RF transmissions. A second MANET node has a second RF transceiver configured to communicate with the first RF transceiver, and a second controller coupled to the second RF transceiver. The second controller is configured to cooperate with the second RF transceiver to receive the RF transmissions from the first MANET node, generate a normalized reception value based upon the received RF transmissions and send the normalized reception value to the first MANET node. The first controller is configured to control a transmit power level for a subsequent RF transmission based upon the normalized reception value from the second MANET node.

Methods, systems, and devices for wireless communications are described that support techniques for transmission power determination for radio frequency (RF) exposure compliance. A transmitting device, such as a user equipment (UE) may determine an uplink transmit power limit for a time window based on an RF limit and a duration of the time window. The device may use the power limit to determine an uplink transmit power based on a computed uplink transmission period for the time window that accounts for a time period during which the device is expected to actually transmit. The computed uplink transmission period may be based on one or more actual uplink transmission periods during one or more prior time windows, a predictive model, network signaling, or any combinations thereof. The device may transmit one or more uplink transmissions during the time window using the determined uplink transmit power.

Certain aspects of the present disclosure provide techniques and apparatus for determining a transmit power based on a pattern and/or future conditions for a transmission while maintaining radio frequency (RF) exposure compliance. An example method generally includes obtaining a pattern associated with one or more first transmissions, determining a transmit power for one or more second transmissions based at least in part on the pattern and an RF exposure limit, and transmitting the one or more second transmissions at the determined transmit power.

To control transmit power in a wireless device, the wireless device sends a data indication signal to the network adaptor. The data indication signal can indicate a transmission status of data to be transmitted and being located in at least one queue of a network stack of a computing device of wireless device. The network adaptor can determine using a time-averaged specific absorption rate (SAR) function, a transmit power for wireless transmission of data in the network adaptor by considering at least the data in the network adaptor and the at least one data indication signal.

Methods and apparatuses in a wireless communication system for a user equipment (UE) to perform a power management method. The method includes receiving, by the UE, one or more power parameters for a non-terrestrial network (NTN). The method also includes selecting a power management method from one of: a predictive transmit power method based on time and the distance between the UE and an NTN entity or a non-predictive transmit power method. The method also includes determining a power based on the power management method and the power management parameters. The method further includes transmitting a signal to the reception point using the power.