The power adjustment includes coefficient scaling of users' precoding vector and power allocation of users' data stream.
The allocation of users to these priority bands (i.e., the assignment of x-priority RBs to MSs) is discussed in Section 5.
COC State: The state (mathcal {S}_{3}) is defined based on the result of the scheduling scheme, which defines (1) the allocation of users to RBs and (2) UE measurements (e.g., RSRP, RSRQ, etc).
State: The state is defined based on the result of the scheduling scheme, which defines: (1) the allocation of users to RBs (RB1,RB2,…,RB R ) to the N users and (2) the values of SINR measured for each user in the corresponding RB.
State: The state is defined based on the result of the scheduling scheme, which defines: (1) the allocation of users to RBs (RB1,RB2,…,RB R ) to the N users, (2) the values of CQI of each user in the corresponding RB.
State: The state (mathcal {S}_{1}) is defined based on the result of the scheduling scheme, which defines (1) the allocation of users to RBs, (2) the values of CQI of each user in the corresponding RB, and (3) UE measurements (e.g., RSRP, RSRQ, etc).
CCO State: The state (mathcal {S}_{1}) is defined based on the result of the scheduling scheme, which defines (1) the allocation of users to RBs, (2) the values of CQI of each user in the corresponding RB, and (3) UE measurements (e.g., RSRP, RSRQ, etc).
ICIC State: The state (mathcal {S}_{2}) is defined based on the result of the scheduling scheme, which defines (1) the allocation of users to RBs, (2) the values of SINR of each user in the corresponding RB, and (3) UE measurements (e.g., RSRP, RSRQ, etc).
The state space is defined by a set of state variables X defined, among others, by: (1) the allocation of users to RBs, (2) the values of CQI, (3) UE measurements in terms of RSRP and the values of RSRQ, (4) resource status information, (5) handover and RLF statistics and information, and (6) interference coordination information in terms of HII, OI, and RNTP.
We define the state and action spaces, together with one of the possible reward functions of each subMDP as follows: 1. CCO State: The state (mathcal {S}_{1}) is defined based on the result of the scheduling scheme, which defines (1) the allocation of users to RBs, (2) the values of CQI of each user in the corresponding RB, and (3) UE measurements (e.g., RSRP, RSRQ, etc).
