Εξώφυλλο

SHORT TERM LOAD FORECASTING TECHNIQUE BASED ON INTEGRATION OF CONVOLUTIONAL NEURAL NETWORK AND LONG-SHORT-TERM MEMORY NETWORK

In this thesis work, a new technique is proposed to forecast short term electrical load. Load forecasting is an integral part of power system planning and operation. Precise forecasting of load is essential for unit commitment, capacity planning, network augmentation and demand side management. I...

Πλήρης περιγραφή

Αποθηκεύτηκε σε:
Κύριος συγγραφέας: HASAN RAFI, SHAFIUL
Μορφή: Thesis
Γλώσσα:Αγγλικά
Έκδοση: DEPARTMENT OF ELECTRICAL, ELECTRONIC AND COMMUNICATION ENGINEERING 2021
Διαθέσιμο Online:http://dspace.mist.ac.bd:8080/xmlui/handle/123456789/607
Ετικέτες: Προσθήκη ετικέτας
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!
_version_ 1868226981188861952
author HASAN RAFI, SHAFIUL
author_browse HASAN RAFI, SHAFIUL
author_facet HASAN RAFI, SHAFIUL
author_sort HASAN RAFI, SHAFIUL
collection DSpace
description In this thesis work, a new technique is proposed to forecast short term electrical load. Load forecasting is an integral part of power system planning and operation. Precise forecasting of load is essential for unit commitment, capacity planning, network augmentation and demand side management. It is significantly imperative for energy providers and other members in electric energy generation, transmission, distribution and markets. Forecasting of load demand is a complex problem as it is to solve nonlinearity with influenced external factors. Load forecasting can be generally categorized into three classes such as sort term, midterm and long term. Short term forecasting is usually done to predict load for next few hours to few weeks. In the literature various methodologies such as regression analysis, machine learning approaches, deep learning methods and artificial intelligence systems have been used for short term load forecasting. Existing forecasting techniques may not always provide higher accuracy in short term load forecasting. To overcome this challenge, a new approach is proposed in this thesis for short term load forecasting. The developed method is based on the integration of convolutional neural network and long short-term memory network. The method is applied to Bangladesh power system to provide day ahead forecasting to month ahead. It is found that in the field of short-term load forecasting, the proposed strategy results in higher precision and accuracy in terms of Mean average error (MAE), Mean average percentage error (MAPE) and root mean square error (RMSE).
format Thesis
id oai:localhost:123456789-607
institution My University
language English
publishDate 2021
publishDateRange 2021
publishDateSort 2021
publisher DEPARTMENT OF ELECTRICAL, ELECTRONIC AND COMMUNICATION ENGINEERING
publisherStr DEPARTMENT OF ELECTRICAL, ELECTRONIC AND COMMUNICATION ENGINEERING
record_format dspace
spelling oai:localhost:123456789-6072021-09-16T05:50:24Z SHORT TERM LOAD FORECASTING TECHNIQUE BASED ON INTEGRATION OF CONVOLUTIONAL NEURAL NETWORK AND LONG-SHORT-TERM MEMORY NETWORK HASAN RAFI, SHAFIUL In this thesis work, a new technique is proposed to forecast short term electrical load. Load forecasting is an integral part of power system planning and operation. Precise forecasting of load is essential for unit commitment, capacity planning, network augmentation and demand side management. It is significantly imperative for energy providers and other members in electric energy generation, transmission, distribution and markets. Forecasting of load demand is a complex problem as it is to solve nonlinearity with influenced external factors. Load forecasting can be generally categorized into three classes such as sort term, midterm and long term. Short term forecasting is usually done to predict load for next few hours to few weeks. In the literature various methodologies such as regression analysis, machine learning approaches, deep learning methods and artificial intelligence systems have been used for short term load forecasting. Existing forecasting techniques may not always provide higher accuracy in short term load forecasting. To overcome this challenge, a new approach is proposed in this thesis for short term load forecasting. The developed method is based on the integration of convolutional neural network and long short-term memory network. The method is applied to Bangladesh power system to provide day ahead forecasting to month ahead. It is found that in the field of short-term load forecasting, the proposed strategy results in higher precision and accuracy in terms of Mean average error (MAE), Mean average percentage error (MAPE) and root mean square error (RMSE). 2021-09-16T05:50:21Z 2021-09-16T05:50:21Z 2020-08 Thesis http://dspace.mist.ac.bd:8080/xmlui/handle/123456789/607 en application/pdf DEPARTMENT OF ELECTRICAL, ELECTRONIC AND COMMUNICATION ENGINEERING
spellingShingle HASAN RAFI, SHAFIUL
SHORT TERM LOAD FORECASTING TECHNIQUE BASED ON INTEGRATION OF CONVOLUTIONAL NEURAL NETWORK AND LONG-SHORT-TERM MEMORY NETWORK
title SHORT TERM LOAD FORECASTING TECHNIQUE BASED ON INTEGRATION OF CONVOLUTIONAL NEURAL NETWORK AND LONG-SHORT-TERM MEMORY NETWORK
title_full SHORT TERM LOAD FORECASTING TECHNIQUE BASED ON INTEGRATION OF CONVOLUTIONAL NEURAL NETWORK AND LONG-SHORT-TERM MEMORY NETWORK
title_fullStr SHORT TERM LOAD FORECASTING TECHNIQUE BASED ON INTEGRATION OF CONVOLUTIONAL NEURAL NETWORK AND LONG-SHORT-TERM MEMORY NETWORK
title_full_unstemmed SHORT TERM LOAD FORECASTING TECHNIQUE BASED ON INTEGRATION OF CONVOLUTIONAL NEURAL NETWORK AND LONG-SHORT-TERM MEMORY NETWORK
title_short SHORT TERM LOAD FORECASTING TECHNIQUE BASED ON INTEGRATION OF CONVOLUTIONAL NEURAL NETWORK AND LONG-SHORT-TERM MEMORY NETWORK
title_sort short term load forecasting technique based on integration of convolutional neural network and long short term memory network
url http://dspace.mist.ac.bd:8080/xmlui/handle/123456789/607
work_keys_str_mv AT hasanrafishafiul shorttermloadforecastingtechniquebasedonintegrationofconvolutionalneuralnetworkandlongshorttermmemorynetwork

Παρόμοια τεκμήρια