Central air conditioner load forecasting method, intelligent terminal and storage medium

Abstract

The invention discloses a central air conditioner load forecasting method. The central air conditioner load forecasting method comprises the following steps of: acquiring at least more than two load forecasting values at time t obtained by a central air conditioner system via a common load forecasting algorithm; acquiring an actual load measurement value of a central air conditioner at the time t;forming a forecasting matrix from the plurality of load forecasting values to obtain a combined load forecasting value at the time t; solving a deviation coefficient of load forecasting; and calculating a final load forecasting value of the central air conditioner system at time t+1 via the combined load forecasting value at the time t+1 and the deviation coefficient. The invention also providesan intelligent terminal and a storage medium containing the method. High-precision load forecasting is realized on a load of the central air conditioner, the load forecasting weight is automatically adjusted by utilizing a weight distribution principle, and the forecasting method with high load forecasting precision always has a high weight, so that the overall load forecasting precision of the system is always maintained at a high precision level, the operating condition of the air conditioning system is adjusted in time, and the operating energy consumption of the air conditioning system isreduced.

Description

technical field [0001] The invention relates to a central air-conditioning technology, in particular to a central air-conditioning load forecasting method with high-precision real-time load forecasting capability, an intelligent terminal and a storage medium. Background technique [0002] The cooling load of the central air-conditioning system can be predicted in advance, and the operation strategy of the corresponding equipment of the air-conditioning system can be adjusted in time, the cooling capacity of the system can be adjusted in advance, and unnecessary energy consumption can be reduced, so as to realize the energy-saving operation of the central air-conditioning system. The central air-conditioning load forecasting method is not only timely and accurate, but also has high forecasting accuracy, can automatically adjust the weight ratio of various load forecasting methods, and perfects the technical supplement of central air-conditioning system operating load forecasti...

AI Technical Summary

Problems solved by technology

[0004] At present, the central air-conditioning system load forecasting technology is single. For example, the neural network forecasting uses the steepest descent method to search for the optimal solution in the training phase.

The characteristic of the steepest descent method is that it has a strong search ability in the local search space, but for the global search space, it has the disadvantages of slow convergence speed and easy to fall into local minimum points, which leads to the failure of neural network load prediction. Realize high-precision load forecasting globally

Time series prediction is easy to rely on the influence of seasons and climate. Once a large change in climate parameters occurs, the prediction accuracy will decrease rapidly.

[0005] In view of the characteristics of hysteresis, nonlinearity, and randomness of the central air-conditioning system load, it is impossible to guarantee high-precision load prediction results for different system operating conditions. When the predicted load value deviates seriously from the actual operating load value, It will lead to insufficient cooling load or overcooling of the system, resulting in energy waste, so it is impossible to maximize the energy saving of the central air conditioning system operation technology

Images