Economic Analysis Of Thermal Power Plants Based On Big Data Mining

In China’s power industry,it is difficult to completely change the way of thermal power generation with coal as raw material.As the main primary energy,coal is the key to achieve the goal of energy conservation and emission reduction in China.With the rapid development of science and technology and the continuous improvement of the degree of information in the power industry,the amount of data stored in thermal power plants has exploded,and the limitations of traditional data analysis methods have forced every researcher to seek new solutions.Using modeling method based on big data mining technology to deeply explore the economy of thermal power units is of great significance to reduce the power generation cost and pollutant emission of thermal power plants.Firstly,the offline and real-time calculation frameworks were developed for the study of the economics of thermal power plants,and the examples show that the calculation framework can operate efficiently and stably.The model is then pre-processed with the collected data,effectively eliminating the interference of irrelevant data and laying the foundation for the subsequent model building.Secondly,an economic model of the optimal value of energy consumption in thermal power plants was developed for determining the optimal value of controllable operating parameters and the coal consumption rate of the supply.In the offline computing phase,the OCF-MBK-means algorithm and the FP-growth algorithm based on the Offline Computing Framework（OCF）were constructed by using the distributed computing framework and the K-means++ idea to address the limitations of the traditional Mini Batch K-means algorithm and the OCF-FP-growth algorithm.The OCF-MBK-means algorithm is first used to divide the data into working conditions and discretize the data respectively,and finally the OCF-FP-growth algorithm is used to explore the economics of the unit.In the real-time phase,a new online economy model is developed,supported by a knowledge base,to obtain the optimal values under real-time data.The case study shows that the analysis of unit economics can obtain optimal values for the full operating conditions,which can effectively reduce the supply coal consumption rate and improve the economics of thermal power plants.Thirdly,a sensitivity analysis of the thermal power plant was carried out in order to determine the order of regulation of the controllable operating parameters.Firstly,the DWT-OA-SVR model is proposed based on Discrete Wavelet Transform（DWT）,Optimization Algorithm（OA）and Support Vector Regression（SVR）,and compared with the SVR model and the OA-SVR model were compared.In terms of model accuracy,the established DWT-ES-SVR model is superior to other models.The DWT-ES-SVR model was then used as the input model for the sensitivity analysis to obtain the order of regulation of the parameters.The experimental analysis shows that the sensitivity analysis can determine the regulation order of different parameters to ensure the fastest optimal operation of the unit.Finally,in order to further explore the economics of thermal power plants and the impact of grid-connected wind power,a new model combining an improved Non dominated Sorting Genetic Algorithm-II（NSGA-II）and an Entropy method（EM）-TOPSIS is proposed for solving the plant-level multi-objective load optimization allocation problem.Firstly,new congestion distance,elite selection,crossover operator and variational operator are constructed to address the limitations of the original NSGA-II,and tested using test functions to conclude that the improved NSGA-II is more likely to jump out of the local optimum than the original NSGA-II.The EM-TOPSIS algorithm was then used to determine the unique optimal solution.Finally,the multi-objective plant-level optimal load allocation model is applied to the actual unit.Experimental analysis shows that the proposed model can not only reduce the cost of power generation in thermal power plants,but also reduce the randomness and volatility of wind power.