|
| Notation | Description | Notation | Description |
|
| DTN environment | | Number of the current node encounters nondestination nodes |
| Set of states | | Number of the current node that encounters the destination node |
| A state of | | Encounter weight |
| Set of actions | | Total number of the current node that encounters other nodes in the network |
| An action of | | Average contact interval between the current node and other nodes |
| Destination node | | The minimum contact interval between the current node and other nodes in the network |
| Future rewards of taking an action to the destination node | | The maximum contact interval between the current node and other nodes in the network |
| Current node | | Speed of the current node at the current time |
| Reward function of current node taking action of selecting as the next hop to the destination node | | The lowest speed of the current node in the network |
| Value of the future rewards | | The highest speed of the current node in the network |
| Value of the future rewards | | Aging constant of value |
| Set of neighbors of node | | Number of time units having elapsed |
| Set of neighbors of destination node | | Balance factor |
| Neighbor of node | | Scaling constant |
| Neighbor of node | | Mixed future reward |
| Neighbor of node with the maximum value of | | Time period of hot zone |
| Neighbor of node with the maximum value of | | The contact interval between the node and the destination node in the hot zone |
| Discount factor | | Hot zone strength of node in the hot zone |
| Learning rate | | Aging constant of hot zone |
| Number of hops from the source node to the destination node | | Number of time units having elapsed of hot zone |
| Fuzzy reward coefficient of current node relative to destination node | | Joint coefficient |
| Fuzzy weight | | Joint utility function |
|
