Exploration on the Application of Wireless Networks and Intelligent Perception in Power Load Forecasting and Dispatching

Traditional power load forecasting (PLF) usually uses statistical models or time series analysis methods, but they often only consider historical load data and ignore the impact of meteorological, temperature, humidity and other factors on load, resulting in inaccurate load forecasting. Moreover, traditional methods have limited real-time performance in power load data transmission and cannot respond to changing load demands in a timely manner, which limits the real-time and accuracy of PLF. Wireless networks (WN) and intelligent sensing technology (IST) were used to obtain real-time charge data, and these data were intelligently analyzed to improve prediction performance. WN and IST were used to improve the transmission efficiency and prediction accuracy of PLF. This article studied the transmission delay and integration delay of power load data in WN, and conducted experimental tests on the root mean square error (RMSE) of CER Electricity Data, REFIT Power Data, and Umass Smart Data Set datasets using an intelligent sensing algorithm based on sensors to study their predictive effect on power load. As the number of users continues to increase, the transmission delay and integration delay of power load data were also increasing. During the process of increasing the number of users from 0 to 500, the transmission delay increased from 389ms to 735ms; the integration delay increased from 568ms to 1086ms. The power load prediction algorithm based on intelligent perception technology had average prediction RMSEs of 0.2885, 0.2716, and 0.2618 for CER Electricity Data, REFIT Power Data, and Umass Smart Data Set datasets, respectively. In WN, the transmission delay and integration delay of power load data are relatively small, and with the increase of the number of users, the impact of this delay is relatively small, which can have the effect of supporting the transmission and integration of power data for a large number of users. The power load prediction algorithm based on intelligent perception technology has good prediction results for different datasets and can accurately predict power loads.