Scholarlink

We propose a quick-and-simple procedure to augment the accuracy of 15-min Italian load forecasts disaggregated by bidding zones published by Terna, the operator of the Italian electricity system. We show that a stacked-regression multi-task combination approach using Terna and daily random walk naïve forecasts, is able to produce significantly more accurate forecasts immediately after Terna publishes on its data portal the energy load measurements for the previous day, and the forecasts for the current day.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Energy Load Forecasting Using Terna Public Data: A Free Lunch Multi-task Combination Approach

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Daniele Girolimetto,
  • Tommaso Di Fonzo

摘要

We propose a quick-and-simple procedure to augment the accuracy of 15-min Italian load forecasts disaggregated by bidding zones published by Terna, the operator of the Italian electricity system. We show that a stacked-regression multi-task combination approach using Terna and daily random walk naïve forecasts, is able to produce significantly more accurate forecasts immediately after Terna publishes on its data portal the energy load measurements for the previous day, and the forecasts for the current day.