Evaluation of Daily Electric Load Forecasting Algorithms

سال انتشار: 1399
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 274

فایل این مقاله در 9 صفحه با فرمت PDF قابل دریافت می باشد

این مقاله در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

MECECONF02_048

تاریخ نمایه سازی: 2 دی 1399

چکیده مقاله:

Optimal power system operation requires accurate load demand prediction; so that the generation, transmission, and distribution utilities to operate securely and efficiently. In this paper, several load forecasting algorithms are detailed and their performances are compared. The objective is to use a short length training frame which is more appropriate for short term load forecasting. The problems with each forecasting algorithm is input selection, data preprocessing, feature extraction, prediction network, and training algorithms. In this respect, Empirical Mode Decomposition, neural network, and classic and intelligent training algorithms are arranged together for devisingthe best set up. Various configurations aiming at best algorithms are employed and simulation results are provided.

نویسندگان

Saeid Asghari

Electrical Engineering Department, Shahed University, Tehran, IRAN

S. Seyedtabaii

Electrical Engineering Department, Shahed University, Tehran, IRAN