A Novel Hybrid Prediction Model for Hourly Gas Consumption in Supply Side Based on Improved Machine Learning Algorithms

Accurate short-term prediction of the natural gas load is of great significance to the operation and allocation of the pipeline network. Because the short-term natural gas load has obvious nonlinearity and randomness, the traditional regression model is difficult to predict accurately. Therefore, this paper proposes a hybrid prediction model that integrates an improved whale swarm algorithm (IWOA) and relevance vector machine (RVM). In addition, empirical mode decomposition (EMD), approximate entropy (ApEn), and C-C method are introduced to aid the calculation. In this paper, the IWOA is used to test the four functions and compared with the other five algorithms. The results show that the convergence accuracy and convergence speed of the new algorithm are higher than other algorithms, indicating that it has better global optimization ability. Second, the IWOA-RVM model is used to predict the supply data of two natural gas stations in Anhui Province, China. The prediction results are compared with the five algorithms including RBFNN, GRNN, ELMANNN, LSSVM, and SMOSVM. The results show that: 1) through the test of four functions, IWOA has better ability to jump out of local optimum, has higher optimization performance, and the calculation speed is at a medium level and 2) compared with other models, the IOWA-RVM model has higher prediction accuracy when the amount of data is larger or smaller, but the calculation time is relatively long, but the calculation time is acceptable in engineering.