An adaptive prediction method for ultra-short-term generation power of power system based on the improved long- and short-term memory network of sparrow algorithm

Abstract To achieve adaptive and accurate ultra-short-term power generation forecasting in power systems, this study proposes a novel prediction method combining Sparrow Search Algorithm (SSA) with Long Short-Term Memory (LSTM) networks. The methodology involves the following steps: (1) Collecting h...

Full description

Saved in:
Bibliographic Details
Main Authors: Peipei Yang, Zhidong Chen, Wen Tang, Zongyang Liu, Bingrui He
Format: Article
Language:English
Published: SpringerOpen 2025-06-01
Series:Energy Informatics
Subjects:
Online Access:https://doi.org/10.1186/s42162-025-00543-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850100532876673024
author Peipei Yang
Zhidong Chen
Wen Tang
Zongyang Liu
Bingrui He
author_facet Peipei Yang
Zhidong Chen
Wen Tang
Zongyang Liu
Bingrui He
author_sort Peipei Yang
collection DOAJ
description Abstract To achieve adaptive and accurate ultra-short-term power generation forecasting in power systems, this study proposes a novel prediction method combining Sparrow Search Algorithm (SSA) with Long Short-Term Memory (LSTM) networks. The methodology involves the following steps: (1) Collecting historical ultra-short-term power generation data from photovoltaic systems, where outlier detection and data cleaning are performed using horizontal processing methods; (2) Applying Pearson correlation analysis to identify key meteorological factors significantly influencing power output as feature inputs; (3) Developing an Adaptive Sparrow Search Algorithm (ASSA) by dynamically adjusting the quantities of discoverers and followers in traditional SSA; (4) Optimizing LSTM network parameters through ASSA to enhance prediction accuracy. The experimental results demonstrate superior performance with Root Mean Square Error (RMSE) values of 0.075, 0.088, and 0.089 for sunny, cloudy, and variable weather conditions respectively. The corresponding Mean Absolute Percentage Error (MAPE) values are 0.21 MW, 0.52 MW, and 0.13 MW, while Absolute Error (AE) values reach 0.17 MW, 0.46 MW, and 0.18 MW. These findings confirm the method’s effectiveness in achieving precise ultra-short-term power generation forecasting across diverse weather conditions.
format Article
id doaj-art-94046c024450424f9788af155eff9d2e
institution DOAJ
issn 2520-8942
language English
publishDate 2025-06-01
publisher SpringerOpen
record_format Article
series Energy Informatics
spelling doaj-art-94046c024450424f9788af155eff9d2e2025-08-20T02:40:17ZengSpringerOpenEnergy Informatics2520-89422025-06-018111810.1186/s42162-025-00543-3An adaptive prediction method for ultra-short-term generation power of power system based on the improved long- and short-term memory network of sparrow algorithmPeipei Yang0Zhidong Chen1Wen Tang2Zongyang Liu3Bingrui He4State Grid Lanzhou Electric Power Supply CompanyState Grid Lanzhou Electric Power Supply CompanyState Grid Gansu Electric Power CompanyState Grid Gansu Electric Power CompanyState Grid Lanzhou Electric Power Supply CompanyAbstract To achieve adaptive and accurate ultra-short-term power generation forecasting in power systems, this study proposes a novel prediction method combining Sparrow Search Algorithm (SSA) with Long Short-Term Memory (LSTM) networks. The methodology involves the following steps: (1) Collecting historical ultra-short-term power generation data from photovoltaic systems, where outlier detection and data cleaning are performed using horizontal processing methods; (2) Applying Pearson correlation analysis to identify key meteorological factors significantly influencing power output as feature inputs; (3) Developing an Adaptive Sparrow Search Algorithm (ASSA) by dynamically adjusting the quantities of discoverers and followers in traditional SSA; (4) Optimizing LSTM network parameters through ASSA to enhance prediction accuracy. The experimental results demonstrate superior performance with Root Mean Square Error (RMSE) values of 0.075, 0.088, and 0.089 for sunny, cloudy, and variable weather conditions respectively. The corresponding Mean Absolute Percentage Error (MAPE) values are 0.21 MW, 0.52 MW, and 0.13 MW, while Absolute Error (AE) values reach 0.17 MW, 0.46 MW, and 0.18 MW. These findings confirm the method’s effectiveness in achieving precise ultra-short-term power generation forecasting across diverse weather conditions.https://doi.org/10.1186/s42162-025-00543-3Long- and short-term memory networksSparrow algorithmGeneration powerAdaptive predictionUltra-short-term
spellingShingle Peipei Yang
Zhidong Chen
Wen Tang
Zongyang Liu
Bingrui He
An adaptive prediction method for ultra-short-term generation power of power system based on the improved long- and short-term memory network of sparrow algorithm
Energy Informatics
Long- and short-term memory networks
Sparrow algorithm
Generation power
Adaptive prediction
Ultra-short-term
title An adaptive prediction method for ultra-short-term generation power of power system based on the improved long- and short-term memory network of sparrow algorithm
title_full An adaptive prediction method for ultra-short-term generation power of power system based on the improved long- and short-term memory network of sparrow algorithm
title_fullStr An adaptive prediction method for ultra-short-term generation power of power system based on the improved long- and short-term memory network of sparrow algorithm
title_full_unstemmed An adaptive prediction method for ultra-short-term generation power of power system based on the improved long- and short-term memory network of sparrow algorithm
title_short An adaptive prediction method for ultra-short-term generation power of power system based on the improved long- and short-term memory network of sparrow algorithm
title_sort adaptive prediction method for ultra short term generation power of power system based on the improved long and short term memory network of sparrow algorithm
topic Long- and short-term memory networks
Sparrow algorithm
Generation power
Adaptive prediction
Ultra-short-term
url https://doi.org/10.1186/s42162-025-00543-3
work_keys_str_mv AT peipeiyang anadaptivepredictionmethodforultrashorttermgenerationpowerofpowersystembasedontheimprovedlongandshorttermmemorynetworkofsparrowalgorithm
AT zhidongchen anadaptivepredictionmethodforultrashorttermgenerationpowerofpowersystembasedontheimprovedlongandshorttermmemorynetworkofsparrowalgorithm
AT wentang anadaptivepredictionmethodforultrashorttermgenerationpowerofpowersystembasedontheimprovedlongandshorttermmemorynetworkofsparrowalgorithm
AT zongyangliu anadaptivepredictionmethodforultrashorttermgenerationpowerofpowersystembasedontheimprovedlongandshorttermmemorynetworkofsparrowalgorithm
AT bingruihe anadaptivepredictionmethodforultrashorttermgenerationpowerofpowersystembasedontheimprovedlongandshorttermmemorynetworkofsparrowalgorithm
AT peipeiyang adaptivepredictionmethodforultrashorttermgenerationpowerofpowersystembasedontheimprovedlongandshorttermmemorynetworkofsparrowalgorithm
AT zhidongchen adaptivepredictionmethodforultrashorttermgenerationpowerofpowersystembasedontheimprovedlongandshorttermmemorynetworkofsparrowalgorithm
AT wentang adaptivepredictionmethodforultrashorttermgenerationpowerofpowersystembasedontheimprovedlongandshorttermmemorynetworkofsparrowalgorithm
AT zongyangliu adaptivepredictionmethodforultrashorttermgenerationpowerofpowersystembasedontheimprovedlongandshorttermmemorynetworkofsparrowalgorithm
AT bingruihe adaptivepredictionmethodforultrashorttermgenerationpowerofpowersystembasedontheimprovedlongandshorttermmemorynetworkofsparrowalgorithm