The invention discloses an online real-time optimization method and device for a
steam power system, and solves the defects in the prior art, and the method comprises the following steps: 1, collecting equipment operation data, environment data, price data and
test analysis data, storing the data in a real-time
database, carrying out the data preprocessing and steady-state detection and obtaining a
data set of the
steam power system; 2, performing
Gaussian transformation on the
data set of the
steam power system; 3, establishing a steam power
system optimization model by taking the lowest operation cost of the steam power system as a target function, and performing optimization solution on the target function within a constraint condition range; and 4, carrying out system
steady state judgment, if the system is in a
steady state, writing an optimization result in the step 3 into a real-time
database, taking the optimization result as deviation compensation of controlled variable set values of the boiler APC and the
steam turbine DEH, and adjusting a
process state to enable the
process state to reach an optimized value.