A heat exchange
station heat load correction method considering building heat characteristics mainly comprises the following steps that S1, operation parameters and weather parameters of a heating
station and a user position are obtained, and the operation parameters and the weather parameters mainly comprise the
heat supply amount of the heat exchange
station, the secondary network
water supply temperature, the secondary network water return temperature, the
heat supply area of the user and the outdoor dry-
bulb temperature; s2, the indoor temperature
Tin, 0 of a user at a certain moment or in a certain period of time is collected, and a building heat exchange characteristic parameter BC0 is calculated according to the outdoor dry-
bulb temperature and the two-network supply and return
water temperature at the current moment or in the
current period of time; and S3, complementing the indoor temperature of the user at other moments according to the building heat exchange characteristic parameter BC0. And S4, according to the two-network supply and return
water temperature and the outdoor dry-
bulb temperature at each moment and the building heat exchange characteristic parameter BC0 obtained through calculation in the step S2, actual indoor temperatures at all moments are obtained through calculation. And S5, according to the outdoor dry-bulb temperature, the indoor temperature of the user and the
heat supply area of the user, a relation model of the indoor temperature of the user and the
heat load of the heat exchange station is constructed. And according to the existing operation parameters, identifying the
heat capacity C'of the unit heat supply area in the model and the indoor heat loss mu under the unit
temperature difference of the unit heat supply area by adopting a
particle swarm algorithm. And S6, the
heat load of the heat exchange station is corrected by using the relation model of the indoor temperature of the user and the heat load of the heating station, and the corrected heat load can be used as input data of load prediction.