Ultrashort-Term Multistep Photovoltaic Power Forecasting Based on Whole-Sky Images and Conditional Temporal Fusion

计算机科学 光伏系统 代表(政治) 灵敏度(控制系统) 卷积神经网络 均方误差 功率(物理) 人工智能 天空 模棱两可 人工神经网络 传输(电信) 关系(数据库) 数据建模 算法 机器学习 数据挖掘 太阳能 发电 深度学习 编码(内存) 模式识别(心理学) 传感器融合 钥匙(锁) 风电预测 风力发电
作者
Zhiyu Zhang,Wenying Han,Xuanchang Liu
出处
期刊:Journal of Energy Engineering-asce [American Society of Civil Engineers]
卷期号:153 (1)
标识
DOI:10.1061/jleed9.eyeng-7190
摘要

Abstract Photovoltaic (PV) power output is strongly affected by the rapid evolution of clouds. Traditional methods that rely only on historical power sequences or low-spatiotemporal-resolution meteorological data struggle to accurately characterize rapid fluctuations and ramp events within a 10–20 min horizon, where PV power rises or drops sharply over a short period. To address this issue, this paper develops an ultra-short-term multistep forecasting framework centered on whole-sky images (WSIs) and recent PV observations. We first design a static image model and a static hybrid model based on the large-small network (LSNet) to mine spatial structural information from single-frame WSIs and use power-conditioned cross-attention to alleviate the representation ambiguity that similar sky appearances may correspond to different output levels. We further propose a dynamic image learning model based on LSNet and a temporal convolutional network, which models short-term cloud-motion evolution on top of frame-wise spatial encoding and introduces a multiscale radiative transmission index (RTI) and a ramp-aware multistep training objective to enhance sensitivity to rapid cloud-occlusion progression and high-risk samples. Experiments on the public Sky Images and Photovoltaic Power Generation Dataset (SKIPP’D) show that the proposed method outperforms the persistence model, single-layer neural network, long short-term memory, and recent baselines such as RTI-Net, SolNet, and SolarNexus in both general forecasting and ramp-event scenarios. Under general forecasting conditions, our method achieves a root mean square error (RMSE) of 27.48 and a mean absolute percentage error (MAPE) of 9.07, which are 29.1% and 28.1% lower than those of the smart persistence model (SPM), respectively. Under ramp-event scenarios, balanced performance reaches 76.84%, a 52.4% improvement over SPM, while ramp-event RMSE and ramp-event MAPE are reduced to 58.93 and 17.11, corresponding to decreases of 47.7% and 62.2%, respectively. These results indicate that jointly exploiting the spatial structure of sky images, recent power context, and ramp-oriented modeling strategies can substantially improve the accuracy and dispatch usefulness of ultra-short-term multistep PV power forecasting.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
13zhan完成签到,获得积分10
刚刚
04d的应助被hbzyydx46采纳,获得10
刚刚
珍珠发布了新的文献求助30
1秒前
windfall完成签到,获得积分10
1秒前
斯文败类的应助被怡然汽车采纳,获得10
1秒前
心理学小学生完成签到,获得积分10
2秒前
NexusExplorer的应助被龙弟弟采纳,获得10
2秒前
风笛发布了新的文献求助10
2秒前
科研通AI6.3的应助被万骛采纳,获得10
2秒前
lkk发布了新的文献求助20
2秒前
3秒前
苗条的乞完成签到 ,获得积分10
3秒前
宓天问完成签到,获得积分10
3秒前
Holly完成签到,获得积分10
4秒前
chenyican完成签到 ,获得积分10
4秒前
4秒前
哈哈哈哈哈噶完成签到 ,获得积分10
5秒前
lcdamoy完成签到,获得积分10
5秒前
俏皮的若剑完成签到,获得积分10
6秒前
蜗牛杨y发布了新的文献求助10
6秒前
6秒前
ldx完成签到,获得积分10
6秒前
6秒前
6秒前
希望天下0贩的0的应助被Sunjz采纳,获得10
6秒前
6秒前
执着从灵完成签到 ,获得积分10
7秒前
xiang完成签到,获得积分10
7秒前
wangzong完成签到,获得积分20
7秒前
宓天问发布了新的文献求助10
7秒前
bkagyin的应助被无问西东采纳,获得20
7秒前
脑洞疼的应助被以州采纳,获得10
7秒前
沐子发布了新的文献求助20
7秒前
YF完成签到,获得积分10
8秒前
8秒前
亚米完成签到,获得积分10
8秒前
8秒前
完美世界的应助被FanLab采纳,获得10
8秒前
脑洞疼的应助被路路采纳,获得30
8秒前
充电宝的应助被江江采纳,获得20
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8181014
求助须知:如何正确求助?哪些是违规求助? 9571039
关于积分的说明 21816042
捐赠科研通 7777369
什么是DOI,文献DOI怎么找? 3433378
关于科研通互助平台的介绍 2557621
邀请新用户注册赠送积分活动 2479385