Radio-network self-optimization based on data from radio network and spatiotemporal sensors

An apparatus comprising:

• at least one processor;
• and
• at least one memory including computer program code;
• the at least one memory and computer program code configured to, with the at least one processor, cause the apparatus at least to:
• receive, from one or more sensors associated with a physical environment, sensor data samples indicating a state of the physical environment or a change of the physical environment;
• receive radio network information data samples associated with a radio network, including at least one radio network performance indicator;
• determine, based on a time relationship of one or more received sensor data samples with one or more of the received radio network information data samples such that both the one or more received sensor data samples and the one or more received radio network information data samples arrived or have a time stamp within a time window, a first set of one or more associated sensor and radio network information data samples;
• select a portion of the first set of one or more associated sensor and radio network information data samples that are relevant to performance of the radio network, including select one or more associated sensor and radio network information data samples that are associated with a change in radio network performance;
• label a reason for selection of the selected associated sensor and radio network information data samples that are relevant to performance of the radio network;
• develop a model that is trained based on at least the portion of the first set of one or more associated sensor and radio network information data samples that are relevant to performance of the radio network;
• and
• improve performance of the radio network based on at least the model.

A method comprising:

• receiving, from one or more sensors associated with a physical environment, sensor data samples indicating a state of the physical environment or a change of the physical environment;
• receiving radio network information data samples associated with a radio network, including at least one radio network performance indicator;
• determining, based on a time relationship of one or more received sensor data samples with one or more of the received radio network information data samples such that both the one or more received sensor data samples and the one or more received radio network information data samples arrived or have a time stamp within a time window, a first set of one or more associated sensor and radio network information data samples;
• selecting a portion of the first set of one or more associated sensor and radio network information data samples that are relevant to performance of the radio network, including selecting one or more associated sensor and radio network information data samples that are associated with a change in radio network performance;
• labeling a reason for selection of the selected associated sensor and radio network information data samples that are relevant to performance of the radio network;
• developing a model that is trained based on at least the portion of the first set of one or more associated sensor and radio network information data samples that are relevant to performance of the radio network;
• and
• improving performance of the radio network based on at least the model.

A non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause a computing system to:

• receive, from one or more sensors associated with a physical environment, sensor data samples indicating a state of the physical environment or a change of the physical environment;
• receive radio network information data samples associated with a radio network, including at least one radio network performance indicator;
• determine, based on a time relationship of one or more received sensor data samples with one or more of the received radio network information data samples such that both the one or more received sensor data samples and the one or more received radio network information data samples arrived or have a time stamp within a time window, a first set of one or more associated sensor and radio network information data samples;
• select a portion of the first set of one or more associated sensor and radio network information data samples that are relevant to performance of the radio network, including select one or more associated sensor and radio network information data samples that are associated with a change in radio network performance;
• label a reason for selection of the selected associated sensor and radio network information data samples that are relevant to performance of the radio network;
• develop a model that is trained based on at least the portion of the first set of one or more associated sensor and radio network information data samples that are relevant to performance of the radio network;
• and
• improve performance of the radio network based on at least the model.