Real-world electricity consumption prediction may involve different tasks, e.g., prediction for different time steps ahead or different geo-locations. These tasks are often solved independently without utilizing some common problem-solving knowledge that could be extracted and shared among these tasks to augment the performance of solving each task. In this work, we propose a multi-task optimization (MTO) based co-training (MTO-CT) framework, where the models for solving different tasks are co-trained via an MTO paradigm in which solving each task may benefit from the knowledge gained from when solving some other tasks to help its solving process. MTO-CT leverages long short-term memory (LSTM) based model as the predictor where the knowledge is represented via connection weights and biases. In MTO-CT, an inter-task knowledge transfer module is designed to transfer knowledge between different tasks, where the most helpful source tasks are selected by using the probability matching and stochastic universal selection, and evolutionary operations like mutation and crossover are performed for reusing the knowledge from selected source tasks in a target task. We use electricity consumption data from five states in Australia to design two sets of tasks at different scales: a) one-step ahead prediction for each state (five tasks) and b) 6-step, 12-step, 18-step, and 24-step ahead prediction for each state (20 tasks). The performance of MTO-CT is evaluated on solving each of these two sets of tasks in comparison to solving each task in the set independently without knowledge sharing under the same settings, which demonstrates the superiority of MTO-CT in terms of prediction accuracy.
翻译:现实世界电力消耗预测可能涉及不同的任务,例如预测未来不同的时间步骤或不同的地理定位。这些任务往往是独立解决的,而没有利用某些共同的解决问题知识,而这些知识可以在这些任务中提取和分享,以提高解决每项任务的业绩。在这项工作中,我们提出一个基于多任务优化(MTO-CT)的共同培训(MTO-CT)框架,其中解决不同任务的模式通过MTO模式共同培训,其中解决每项任务的模式可能受益于在解决某些其他任务以帮助其解决过程中获得的知识。 MTO-CT利用基于长期短期记忆的比较(LSTM)模型,作为通过连接权重和偏差代表知识的预测者。在 MTO-CT中,一个跨任务转让模块旨在在不同任务之间转让知识,其中最有用的来源任务是通过概率匹配和随机共选,以及像突变和交叉任务一样的演进操作,用于在一项目标任务中重新利用选定来源任务的知识。我们使用基于长期存储(LSTMMT)的短期(LTM)的准确性模型作为预测工具。在澳大利亚五个国家中,每个阶段使用电消耗数据,在12项任务中,在预测中,每个任务中,每个任务在20个任务中,每个任务中先评估一个任务中,每个任务中,每个任务在20级中,每个任务中,每个任务在20级任务中,每个任务中,每个任务中,每个任务中,每个任务将显示一个任务,每个任务在20级,每个任务,每个任务中,每个任务在20个任务中,每个任务中,每个任务在20级的进度的进度,每个任务中,每个任务在20级,每个任务中,每个任务,每个任务中,每个任务在20级的进度,每个任务中,每个任务,每个任务的周期中,每个任务的进度的进度的进度的进度中,一个任务,一个任务,一个任务的进度的进度的进度,每个任务,每个任务在20个任务,每个任务在20级,每个任务中,一个任务在20级,每个任务在20级,每个任务中,每个任务在18级,每个任务在20级,每个任务的进度,每个任务的进度,每个任务的进度,每个任务的进度,每个任务的进度,每个任务的进度,每个任务的进度,每个任务的进度,每个任务的进度