.png){kind=icon}
.png){kind=icon}
Return
Power Consumption Prediction Using an Enhanced Fruit-fly Optimization Algorithm
.png){kind=icon}
PRE
AI
DOI：10.1007/s42835-026-02660-9.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In today's environment, the task of predicting power consumption is essential since it aids in improving the system's performance in terms of efficiency and productivity. Nature-inspired algorithms are now frequently utilized to produce precise forecasts. In line with how people utilize energy in their daily lives, the power system is becoming increasingly sophisticated and adaptable. Monitoring the state of the electricity load and early detection of abnormal loads is the most challenging component. To estimate electricity usage on an annual basis, we implement the proposed model for feature selection using the Enhanced Fruit-fly Optimization Algorithm (EFOA) and a deep belief network for classification. The proposed model is tested using a benchmark dataset, and the results show that it is in good agreement with the experimental values, with accuracy, precision, false negative rate, and false positive rate values of 96.03%, 95.91%, 2.13%, and 1.03%, respectively. The proposed model performed the best when measured against other machine learning techniques currently in use.
Keywords:
Fruit-fly optimization algorithm
Deep belief network
Energy prediction
Journal
J
IF:
1.6
Papers:
283
Citations:
0