检索结果-南通市图书馆

Investigating Periodic Dependencies to Improve Short-Term load forecasting

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy Engineering 2024年第3期121卷 789-806页

作者： Jialin Yu Xiaodi Zhang Qi Zhong Jian Feng State Grid Zhejiang Jiaxing Electric Power Co. Ltd.Jiaxing314000China State Grid Zhejiang Electric Power Co. Ltd.Hangzhou310000China

With a further increase in energy flexibility for customers,short-term load forecasting is essential to provide benchmarks for economic dispatch and real-time alerts in power *** electrical load series exhibit periodic patterns and share high associations with metrological ***,current studies have merely focused on point-wise models and failed to sufficiently investigate the periodic patterns of load series,which hinders the further improvement of short-term load forecasting ***,this paper improved Autoformer to extract the periodic patterns of load series and learn a representative feature from deep decomposition and *** addition,a novel multi-factor attention mechanism was proposed to handle multi-source metrological and numerical weather prediction data and thus correct the forecasted electrical *** paper also compared the proposed model with various competitive *** the experimental results reveal,the proposed model outperforms the benchmark models and maintains stability on various types of load consumers.

关键词： load forecasting transformer attention mechanism power grid

Optimization of a photovoltaic-battery system using deep reinforcement learning and load forecasting

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy and AI 2024年第2期16卷 168-183页

作者： António Corte Real G.Pontes Luz J.M.C.Sousa M.C.Brito S.M.Vieira IDMEC Instituto Superior TécnicoUniversidade de LisboaLisboa1049-001Portugal Instituto Dom Luiz Faculdade de CiênciasUniversidade de LisboaCampo Grande1749-016LisboaPortugal

Home Energy Management Systems(HEMS)are increasingly relevant for demand-side management at the residential level by collecting data(energy,weather,electricity prices)and controlling home appliances or storage *** control can be performed with classical models that find optimal solutions,with high real-time computational cost,or data-driven approaches,like Reinforcement Learning,that find good and flexible solutions,but depend on the availability of load and generation data and demand high computational resources for *** this work,a novel HEMS is proposed for the optimization of an electric battery operation in a real,online and data-driven environment that integrates state-of-the-art load forecasting combining CNN and LSTM neural networks to increase the robustness of *** Reinforcement Learning agents are trained with different algorithms(Double DQN,Dueling DQN,Rainbow and Proximal Policy Optimization)in order to minimize the cost of electricity purchase and to maximize photovoltaic self-consumption for a PV-Battery residential *** show that the best Reinforcement Learning agent achieves a 35%reduction in total cost when compared with an optimization-based agent.

关键词： Energy management system Deep reinforcement learning Demand-side management load forecasting Deep learning Energy storage systems

Typical load profile-supported convolutional neural network for short-term load forecasting in the industrial sector

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy and AI 2021年第3期5卷 242-254页

作者： Thilo Walser Alexander Sauer Fraunhofer Institute for Manufacturing Engineering and Automation IPA Nobelstraße 1270569 StuttgartGermany Institute for Energy Efficiency in Production EEP University of StuttgartNobelstraße 1270569 StuttgartGermany

This paper investigates how existing forecasting models can be enhanced to accurately forecast the electric load at factory level,enabling industrial companies to shift consumption to times of low energy *** model architecture must outperform state-of-the-art models and be sufficiently robust for use in multiple factories with low effort for specific ***,this work focuses on the processing of high-resolution input data available almost in real time from multiple submeters after the main *** theory of load forecasting and related works are summarized in a first step including the requirements of forecasting models applied at factory *** on existing models,a new hybrid machine-learning model is proposed,combining a decision tree-based typical load profiler with a convolutional neural network that extracts features from multidimensional endogenous inputs with measurements of the preceding two weeks for multi-step-ahead load forecasts updated almost in real ***,a multi-model approach is presented for calculating bottom-up forecasts with submeter data aggregated to a main-meter *** a case study,the forecasting accuracy of the hybrid model is compared to both base models and a seasonal naïve model calculating the load forecasts for three *** results indicate that the proposed typical-load-profile-supported convolutional neural network for all three factories achieves the lowest forecasting ***,it is validated that a reduction in data transfer delay leads to better forecasts,as the forecasting accuracy is higher with near real time data than with a data transfer delay of one ***,a model architecture is proposed for robust forecasting in digitalized factories.

关键词： Electricity Machine learning load forecasting Hybrid model Industrial energy systems Energy flexibility Submetering Real time data

A Novel Ultra Short-Term load forecasting Method for Regional Electric Vehicle Charging load Using Charging Pile Usage Degree

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy Engineering 2023年第5期120卷 1107-1132页

作者： Jinrui Tang Ganheng Ge Jianchao Liu Honghui Yang School of Automation Wuhan University of TechnologyWuhan430070China

Electric vehicle(EV)charging load is greatly affected by many traffic factors,such as road *** ultra short-term load forecasting(STLF)results for regional EV charging load are important to the scheduling plan of regional charging load,which can be derived to realize the optimal vehicle to grid *** this paper,a regional-level EV ultra STLF method is proposed and *** usage degree of all charging piles is firstly defined by us based on the usage frequency of charging piles,and then constructed by our collected EV charging transactiondata in ***,these usagedegrees are combinedwithhistorical charging loadvalues toform the inputmatrix for the deep learning based load ***,long short-termmemory(LSTM)neural network is used to construct EV charging load forecastingmodel,which is trained by the formed *** comparison experiment proves that the proposed method in this paper has higher prediction accuracy compared with *** addition,load characteristic index for the fluctuation of adjacent day load and adjacent week load are proposed by us,and these fluctuation factors are used to assess the prediction accuracy of the EV charging load,together with the mean absolute percentage error(MAPE).

关键词： Electric vehicle charging load density-based spatial clustering of application with noise long-short termmemory load forecasting

Spatial load forecasting of Distribution Network Based on Artificial Intelligent Algorithm 32

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Spatial Load Forecasting of Distribution Network Based on Ar...

load forecasting Technique for System Expansion in Isolated Area Using Time Invariant Socio-Economic Factors of Identical Agglomerations

第32届中国控制与决策会议

作者： SHAO Yuying PENG Peng LIU Weiyang WEI Lingyan WANG Bing State grid Shanghai electric power company

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

For the influence of the popularity of rooftop photovoltaic(PV) and the use of large-scale electric vehicles(EVs) on the power grid load, a space load forecasting method of urban distribution power grid was proposed, which took into accounts the spatial and temporal distribution of PV and EVs. Through analytic hierarchy process and fuzzy comprehensive evaluation method, various factors affecting the rooftop distributed PV output power were fully considered, and the rooftop PV output power of each planning area was forecasted by combining the least squares support vector machine and particle swarm optimization. Based on the time-space transfer probability matrix of EVs in different planning areas, Monte Carlo algorithm was used to simulate the time-space distribution of charging load with high probability. Taking an urban area as an example, the forecasted rooftop PV output power, EV charging load and traditional power load are superimposed on different planning areas to obtain the forecasted spatial load values.

关键词： load forecasting fuzzy comprehensive evaluation rooftop photovoltaic electric vehicle spatial and temporal distribution urban distribution network planning

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Energy and Power Engineering 2013年第9期7卷 1778-1785页

作者： Asif Islam Mohammad Shariful Islam Kanica Rani Mondal Mohammad Mahabub Hossain Electrical and Electronic Engineering Bangladesh University Dhaka 1207 Bangladesh Electrical and Electronic Engineering Bangladesh University of Engineering and Technology Dhaka 1000 Bangladesh

load forecasting is a critical issue for operational planning as well as grid expansion to ensure an uninterruptable electric power system. Being a small but densely populated country in South Asia, Bangladesh has many isolated places which are not connected to national grid yet. If concern authority opts to expand grid to those areas, they need reliable demand data for designing and dimensioning of different power system entities, e.g., capacity, overhead line capacity, tie line capacity, spinning reserve, load-shedding scheduling, etc., for reliable operation and to prevent possible obligatory redesigning. This paper represents an analysis to forecast the electricity demand of an isolated island in Bangladesh where past history of electrical load demand is not available. The analysis is based on the identification of factors, e.g., population, literacy rate, per capita income, occupation, communication, etc., on which electrical load growth of an area depends. Data has been collected from the targeted isolated area and form a grid connected area which is similar to target area from social and geographical perspective. Weights of those factors on load have been calculated by matrix inversion. Demand of the new area is forecasted using these weights factors by matrix multiplication.

关键词： load forecasting socio-economic factors isolated area matrices multiplication matrices inversion.

load forecasting for Control of the Use of Transmission System for Electric Distribution Utilities

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Energy and Power Engineering 2013年第1期7卷 139-147页

作者： Vitor Hugo Ferreira Alexandre Rasi Aoki Silvio Michel de Rocco Electrical Engineering Department Fluminense Federal University (UFF) Niter6i 24210-240 Brazil Electric and Electronic Department Institute of Technology for Development (LACTEC) Curitiba 80215-090 Brazil Companhia Paranaense de Energia (COPEL) Curitiba 80420-170 Brazil

The Brazilian electric sector reform established that the remuneration of distribution utilities must be through the management of their systems. This fact increased the necessity of control and management of load flows through the connection points between the distribution systems and the basic grid as a function of the contracted amounts. The objective of this control is to avoid that these flows exceed some thresholds along the contracted values, avoiding monetary penalties to the utility or unnecessary amounts of contracted flows that overrates the costumers. This question highlights the necessity of forecast the flows in these connection points in sufficient time to permit the operator to take decisions to avoid flows beyond the contracted ones. In this context, this work presents the development of a neural network based load flow forecaster, being tested two time-series neural models： support vector machines and Bayesian inference applied to multilayered perceptron. The models are applied to real data from a Brazilian distribution utility.

关键词： load forecasting artificial neural networks complexity control input selection Bayesian methods support vector machines.

Research on Natural Gas Short-Term load forecasting Based on Support Vector Regression

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2004年第5期12卷 732-736页

作者：刘涵刘丁郑岗梁炎明 School of Automation and Information Engineering Xi'an University of Technology Xi'an 710048 China

Natural gas load forecasting is a key process to the efficient operation of pipeline network. An accurate forecast is required to guarantee a balanced network operation and ensure safe gas supply at a minimum *** learning techniques have been increasingly applied to load forecasting. A novel regression technique based on the statistical learning theory, support vector machines (SVM), is investigated in this paper for natural gas shortterm load forecasting. SVM is based on the principle of structure risk minimization as opposed to the principle of empirical risk minimization in conventional regression techniques. Using a data set with 2 years load values we developed prediction model using SVM to obtain 31 days load predictions. The results on city natural gas short-term load forecasting show that SVM provides better prediction accuracy than neural network. The software package natural gas pipeline networks simulation and load forecasting (NGPNSLF) based on support vector regression prediction has been developed, which has also been applied in practice.

关键词： structure risk minimization support vector machines support vectorregression load forecasting neural network

Autonomous Kernel Based Models for Short-Term load forecasting

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Energy and Power Engineering 2012年第12期6卷 1984-1993页

作者： Vitor Hugo Ferreira Alexandre Pinto Alves da Silva Electrical Engineering Department Fluminense Federal University (UFF) Niteroi 24210-240 Brazil Federal University of Rio de Janeiro Rio de Janeiro 21945-972 Brazil

The application of support vector machines to forecasting problems is becoming popular, lately. Several comparisons between neural networks trained with error backpropagation and support vector machines have shown advantage for the latter in different domains of application. However, some difficulties still deteriorate the performance of the support vector machines. The main one is related to the setting of the hyperparameters involved in their training. Techniques based on meta-heuristics have been employed to determine appropriate values for those hyperparameters. However, because of the high noneonvexity of this estimation problem, which makes the search for a good solution very hard, an approach based on Bayesian inference, called relevance vector machine, has been proposed more recently. The present paper aims at investigating the suitability of this new approach to the short-term load forecasting problem.

关键词： load forecasting artificial neural networks input selection kernel based models support vector machine relevancevector machine.