The invention belongs to the technical field of power dispatching and operation, and particularly provides a negative
electricity price scene-oriented source-grid-load-storage
collaborative interaction and marginal
cost optimization system and method, and the method comprises the steps: monitoring the state of a
power market through a data collection module, predicting the supply and demand conditions of the
system, and judging that there is a negative
electricity price risk; calculating real-time marginal cost of the schedulable resources, wherein the real-time marginal cost comprises power generation resource marginal cost,
energy storage resource marginal cost and
load regulation marginal cost; establishing an optimization model by taking the minimization of the total marginal cost of the
system as a target, and solving to obtain an
optimal scheduling scheme of each resource; converting the
optimal scheduling scheme into a specific control instruction, issuing the specific control instruction to each resource main body of a source, a network, a load and a storage, and executing power generation adjustment, charging and discharging or load interruption operation; and monitoring the execution effect of each resource instruction and the actual clearing
electricity price of the market in real time, calculating the execution deviation, and carrying out rolling correction in the next optimization period. According to the invention, early warning of the negative
electricity price risk can be realized, and
global optimization scheduling is carried out on the source network load storage resources.