This paper develops learning-augmented algorithms for energy trading in volatile electricity markets. The basic problem is to sell (or buy) $k$ units of energy for the highest revenue (lowest cost) over uncertain time-varying prices, which can framed as a classic online search problem in the literature of competitive analysis. State-of-the-art algorithms assume no knowledge about future market prices when they make trading decisions in each time slot, and aim for guaranteeing the performance for the worst-case price sequence. In practice, however, predictions about future prices become commonly available by leveraging machine learning. This paper aims to incorporate machine-learned predictions to design competitive algorithms for online search problems. An important property of our algorithms is that they achieve performances competitive with the offline algorithm in hindsight when the predictions are accurate (i.e., consistency) and also provide worst-case guarantees when the predictions are arbitrarily wrong (i.e., robustness). The proposed algorithms achieve the Pareto-optimal trade-off between consistency and robustness, where no other algorithms for online search can improve on the consistency for a given robustness. Further, we extend the basic online search problem to a more general inventory management setting that can capture storage-assisted energy trading in electricity markets. In empirical evaluations using traces from real-world applications, our learning-augmented algorithms improve the average empirical performance compared to benchmark algorithms, while also providing improved worst-case performance.

翻译：本文针对波动性电力市场中的能源交易问题，提出了学习增强型算法。核心问题是在不确定的时变价格下，以最高收益（最低成本）卖出（或买入）k单位能源。该问题可归结为竞争分析文献中的经典在线搜索问题。现有最先进算法在每时隙做出交易决策时，假设对未来市场价格一无所知，旨在保证最坏情况价格序列下的性能。然而，实际中通过机器学习方法可普遍获取未来价格预测。本文旨在融合机器学习预测，为在线搜索问题设计竞争算法。所提算法的重要特性在于：当预测准确时（即一致性），其性能可与事后最优离线算法相媲美；当预测出现任意偏差时（即鲁棒性），仍能提供最坏情况下的性能保障。所提算法实现了一致性与鲁棒性之间的帕累托最优权衡——在给定鲁棒性水平下，任何其他在线搜索算法均无法提升其一致性。此外，本文将基础在线搜索问题扩展至更通用的库存管理场景，可刻画电力市场中带储能辅助的能源交易。基于真实应用场景数据轨迹的实证评估表明，与基准算法相比，我们的学习增强型算法在提升平均实证性能的同时，也带来了更优的最坏情况性能。