Abstract Power producers use a wide range of decision support systems to manage and plan for sales in the day-ahead electricity market. The available tools have advantages and disadvantages and the operators are often faced with the challenge of choosing the most advantageous bidding strategy for any given day. Since only one bid can be submitted each day, this choice can not be avoided. The optimal solution is not known until after spot clearing. Results from the models and strategy used, and their impact on profitability, can either be continuously registered, or simulated with use of historic data. Access to an increasing amount of data opens for the application of machine learning models to predict the best combination of models and strategy for any given day. In this article, historical performance of two given bidding strategies over several years have been analyzed with a combination of domain knowledge and machine learning techniques. A wide range of model variables accessible prior to bidding have been evaluated to predict the optimal strategy for a given day. Results indicate that a machine learning model can learn to slightly outperform a static strategy where one bidding method is chosen based on overall historic performance.

中文翻译：

---

水库水电竞价策略优化选择的监督学习方法

摘要 电力生产商使用广泛的决策支持系统来管理和计划日前电力市场的销售。可用的工具有优点也有缺点，运营商经常面临为任何一天选择最有利的投标策略的挑战。由于每天只能提交一个投标，因此无法避免这种选择。最佳解决方案直到斑点清除之后才知道。所使用的模型和策略的结果及其对盈利能力的影响可以连续记录，也可以使用历史数据进行模拟。访问越来越多的数据为机器学习模型的应用打开了大门，以预测任何一天的模型和策略的最佳组合。在本文中，已经结合领域知识和机器学习技术分析了两种给定投标策略在几年内的历史表现。已经评估了在投标之前可访问的各种模型变量，以预测给定日期的最佳策略。结果表明，机器学习模型可以学习稍微优于静态策略，其中根据整体历史性能选择一种投标方法。