A Solar Energy Prediction Method Based on Energy Model and Dynamic Weight Factor

Abstract

The invention relates to a solar energy prediction method based on an energy model and a dynamic weight factor, and belongs to the field of wireless communication energy collection. Find the most similar energy model from the historical energy model, and use this as a basis to predict the energy of the next time slot. The most similar historical energy model is obtained according to the minimum average error between the energy value of the first K time slots of the n+1th time slot of the day and the energy difference of the corresponding time slots in the previous D days. In order to dynamically reflect the impact of weather changes on the forecast results, the present invention sets a dynamic weight factor, so that the weight factor can be adjusted accordingly with the weather changes, and better reflects the contribution of each component in the forecast model to the forecast results, so that Improving prediction accuracy for solar energy harvesting. The invention is simple, efficient, low in complexity, easy to implement on actual wireless sensor nodes, and has better practicability.

Description

technical field [0001] The invention belongs to the field of wireless communication energy collection, and relates to a solar energy prediction method based on an energy model and a dynamic weight factor. Background technique [0002] Wireless sensor networks are widely used in industrial and agricultural production, medical services, environmental monitoring, home security, military and other fields. The continuous energy supply of sensor nodes is a major bottleneck restricting the practical application of wireless sensor networks. Harvesting solar energy to supply energy for sensor nodes is an effective way to solve the continuous energy supply of wireless sensor networks. Because solar energy collection is greatly affected by factors such as daylight, weather, and region, it cannot provide a continuous and stable power supply. Therefore, in order to make rational use of solar energy, it is necessary to predict and manage solar energy collection in order to effectively us...

AI Technical Summary

Problems solved by technology

[0003] Most of the above methods use the energy value collected in the previous time slot as the basic component of energy prediction in the next time slot, but in the case of large weather fluctuations, the data in the previous time slot is far from providing powerful data for the next time slot. For reference, this will lead to a sharp increase in the prediction error and a significant reduction in the accuracy of the algorithm

At the same time, the weight factor in most forecasting methods is a fixed value. With the continuous change of the weather state, the fixed weight factor cannot follow the change of the weather and cannot well reflect the contribution of each component in the forecast model to the forecast result. will lead to a decrease in prediction accuracy

Images