A Multimodal Interaction-Driven Feature Discovery Framework for Power Demand Forecasting

Power demand forecasting is a critical and challenging task for modern power systems and integrated energy systems. Due to the absence of well-established theoretical frameworks and publicly available feature databases on power demand changes, the known interpretable features of power demand fluctua...

Full description

Saved in:
Bibliographic Details
Main Authors: Zifan Ning, Min Jin, Pan Zeng
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/11/2907
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129131966038016
author Zifan Ning
Min Jin
Pan Zeng
author_facet Zifan Ning
Min Jin
Pan Zeng
author_sort Zifan Ning
collection DOAJ
description Power demand forecasting is a critical and challenging task for modern power systems and integrated energy systems. Due to the absence of well-established theoretical frameworks and publicly available feature databases on power demand changes, the known interpretable features of power demand fluctuations are primarily derived from expert experience and remain significantly limited. This substantially hinders advancements in power demand forecasting accuracy. Emerging multimodal learning approaches have demonstrated great promise in machine learning and AI-generated content (AIGC). In this paper, we propose, for the first time, a textual-knowledge-guided numerical feature discovery (TKNFD) framework for short-term power demand forecasting by interacting text modal data—a potentially valuable yet long-overlooked resource in the field of power demand forecasting—with numerical modal data. TKNFD systematically and automatically aggregates qualitative textual knowledge, expands it into a candidate feature-type set, collects corresponding numerical data for these features, and ultimately constructs four-dimensional multivariate source-tracking databases (4DM-STDs). Subsequently, TKNFD introduces a two-stage quantitative feature identification strategy that operates independently of forecasting models. The essence of TKNFD lies in achieving reliable and comprehensive feature discovery by fully exploiting the dual relationships of synonymy and complementarity between text modal data and numerical modal data in terms of granularity, scope, and temporality. In this study, TKNFD identifies 38–50 features while further interpreting their contributions and dependency correlations. Benchmark experiments conducted in Maine, Texas, and New South Wales demonstrate that the forecasting accuracy using TKNFD-identified features consistently surpasses that of state-of-the-art feature schemes by up to 36.37% MAPE. Notably, driven by multimodal interaction, TKNFD can discover previously unknown interpretable features without relying on prior empirical knowledge. This study reveals 10–16 previously unknown interpretable features, particularly several dominant features in integrated energy and astronomical dimensions. These discoveries enhance our understanding of the origins of strong randomness and non-linearity in power demand fluctuations. Additionally, the 4DM-STDs developed for these three regions can serve as public baseline databases for future research.
format Article
id doaj-art-1166dd8dbfdf43a5b31af2a75cab4d77
institution OA Journals
issn 1996-1073
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-1166dd8dbfdf43a5b31af2a75cab4d772025-08-20T02:33:06ZengMDPI AGEnergies1996-10732025-06-011811290710.3390/en18112907A Multimodal Interaction-Driven Feature Discovery Framework for Power Demand ForecastingZifan Ning0Min Jin1Pan Zeng2College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, ChinaCollege of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, ChinaCollege of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, ChinaPower demand forecasting is a critical and challenging task for modern power systems and integrated energy systems. Due to the absence of well-established theoretical frameworks and publicly available feature databases on power demand changes, the known interpretable features of power demand fluctuations are primarily derived from expert experience and remain significantly limited. This substantially hinders advancements in power demand forecasting accuracy. Emerging multimodal learning approaches have demonstrated great promise in machine learning and AI-generated content (AIGC). In this paper, we propose, for the first time, a textual-knowledge-guided numerical feature discovery (TKNFD) framework for short-term power demand forecasting by interacting text modal data—a potentially valuable yet long-overlooked resource in the field of power demand forecasting—with numerical modal data. TKNFD systematically and automatically aggregates qualitative textual knowledge, expands it into a candidate feature-type set, collects corresponding numerical data for these features, and ultimately constructs four-dimensional multivariate source-tracking databases (4DM-STDs). Subsequently, TKNFD introduces a two-stage quantitative feature identification strategy that operates independently of forecasting models. The essence of TKNFD lies in achieving reliable and comprehensive feature discovery by fully exploiting the dual relationships of synonymy and complementarity between text modal data and numerical modal data in terms of granularity, scope, and temporality. In this study, TKNFD identifies 38–50 features while further interpreting their contributions and dependency correlations. Benchmark experiments conducted in Maine, Texas, and New South Wales demonstrate that the forecasting accuracy using TKNFD-identified features consistently surpasses that of state-of-the-art feature schemes by up to 36.37% MAPE. Notably, driven by multimodal interaction, TKNFD can discover previously unknown interpretable features without relying on prior empirical knowledge. This study reveals 10–16 previously unknown interpretable features, particularly several dominant features in integrated energy and astronomical dimensions. These discoveries enhance our understanding of the origins of strong randomness and non-linearity in power demand fluctuations. Additionally, the 4DM-STDs developed for these three regions can serve as public baseline databases for future research.https://www.mdpi.com/1996-1073/18/11/2907multimodal learningqualitative knowledgequantitative identificationprior empirical knowledgeinterpretabilityintegrated energy dimension
spellingShingle Zifan Ning
Min Jin
Pan Zeng
A Multimodal Interaction-Driven Feature Discovery Framework for Power Demand Forecasting
Energies
multimodal learning
qualitative knowledge
quantitative identification
prior empirical knowledge
interpretability
integrated energy dimension
title A Multimodal Interaction-Driven Feature Discovery Framework for Power Demand Forecasting
title_full A Multimodal Interaction-Driven Feature Discovery Framework for Power Demand Forecasting
title_fullStr A Multimodal Interaction-Driven Feature Discovery Framework for Power Demand Forecasting
title_full_unstemmed A Multimodal Interaction-Driven Feature Discovery Framework for Power Demand Forecasting
title_short A Multimodal Interaction-Driven Feature Discovery Framework for Power Demand Forecasting
title_sort multimodal interaction driven feature discovery framework for power demand forecasting
topic multimodal learning
qualitative knowledge
quantitative identification
prior empirical knowledge
interpretability
integrated energy dimension
url https://www.mdpi.com/1996-1073/18/11/2907
work_keys_str_mv AT zifanning amultimodalinteractiondrivenfeaturediscoveryframeworkforpowerdemandforecasting
AT minjin amultimodalinteractiondrivenfeaturediscoveryframeworkforpowerdemandforecasting
AT panzeng amultimodalinteractiondrivenfeaturediscoveryframeworkforpowerdemandforecasting
AT zifanning multimodalinteractiondrivenfeaturediscoveryframeworkforpowerdemandforecasting
AT minjin multimodalinteractiondrivenfeaturediscoveryframeworkforpowerdemandforecasting
AT panzeng multimodalinteractiondrivenfeaturediscoveryframeworkforpowerdemandforecasting