scholarly journals A hybrid approach to very small scale electrical demand forecasting

ISGT 2014 ◽  
2014 ◽  
Author(s):  
Andrei Marinescu ◽  
Colin Harris ◽  
Ivana Dusparic ◽  
Vinny Cahill ◽  
Siobhan Clarke
Keyword(s):  
Demand Forecasting ◽  
Hybrid Approach ◽  
Small Scale ◽  
Electrical Demand

k-Nearest Patterns for Electrical Demand Forecasting in Residential and Small Commercial Buildings

2021 ◽  
pp. 111396
Author(s):  
Meritxell Gomez-Omella ◽  
Iker Esnaola-Gonzalez ◽  
Susana Ferreiro ◽  
Basilio Sierra
Keyword(s):  
Demand Forecasting ◽  
Commercial Buildings ◽  
Electrical Demand

scholarly journals Hour-Ahead Energy Trading Management with Demand Forecasting in Microgrid Considering Power Flow Constraints

Energies ◽  
2019 ◽  
Vol 12 (18) ◽  
pp. 3494
Author(s):  
Kuo Feng ◽  
Chunhua Liu ◽  
Zaixin Song
Keyword(s):  
Power Flow ◽  
Low Voltage ◽  
Supply And Demand ◽  
Demand Forecasting ◽  
Distribution Networks ◽  
Small Scale ◽  
Energy Trading ◽  
Medium Voltage ◽  
The Neural Network ◽  
Flow Constraints

Multiple small-scale low-voltage distribution networks with distributed generators can be connected in a radial pattern to form a multi-bus medium voltage microgrid. Additionally, each bus has an independent operator that can manage its power supply and demand. Since the microgrid operates in the market-oriented mode, the bus operators aim to maximize their own benefits and expect to protect their privacy. Accordingly, in this paper, a distributed hour-ahead energy trading management is proposed. First, the benefit optimization problem of the microgrid is solved, which is decomposed into the local benefit optimization sub problems of buses. Then, the local sub problems can be solved by the negotiation of operators with their neighbors. Additionally, the reference demand before negotiation is forecasted by the neural network rather than given in advance. Furthermore, the power flow constraints are considered to guarantee the operational stability. Meanwhile, the power loss minimization is considered in the objective function. Finally, the demonstration and simulation cases are given to validate the effectiveness of the proposed hour-ahead energy trading management.

Experimental Study for Establishing Metal-to-Metal Seal Evaluation Criteria for Tubular Connections in Thermal and HPHT Applications

2021 ◽  
Author(s):  
Jueren Xie ◽  
Dale Friesen ◽  
Mark Droessler ◽  
Tim Roth ◽  
Junfeng Xie
Keyword(s):  
Experimental Study ◽  
Surface Roughness ◽  
Structural Integrity ◽  
Research Work ◽  
Hybrid Approach ◽  
Product Line ◽  
Constitutive Relationship ◽  
Small Scale ◽  
Well Completion ◽  
Metal Seal

Abstract Qualification of tubular connections is an important task in well completion design for thermal wells, which experience peak temperatures of 180°C to 350°C, as well as high pressure and high temperature (HPHT) wells, which experience peak temperatures up to 180°C and pressures greater than 70 MPa. Industry protocols (such as ISO/PAS 12835:2013 for thermal wells, and ISO 13679:2019 and API RP 5C5:2017 for HPHT wells) have been developed for the purposes of evaluating the structural integrity and sealability of premium connections. In recognition of the the time and capital expense associated with completing "product line validation" for a connection design per these standards for multiple physical configurations (i.e for combinations of various sizes, weights, and grades), industry is developing a hybrid approach that supplements results from physical qualification tests with numerical simulation, such as Finite Element Analysis (FEA). To facilitate numerical modeling, extensive research work has been performed recently (e.g. Xie, Matthew, and Hamilton (2016) and Xie and Matthew (2017)) to establish a constitutive relationship for evaluating metal-to-metal sealability. It was noted in previous studies that further experimental work is required to better understand connection sealing behavior, especially the effects of surface roughness and thread compounds. This paper presents an experimental study with a series of small-scale metal-to-metal seal tests under various levels of seal contact stress and gas pressures representative of thermal and HPHT operational conditions. These tests incorporated the effects of surface roughness and thread compound. FEA was performed to model the stress conditions in the test specimens. Based on the experimental and analytical study, an updated metal-to-metal seal evaluation criterion with calibrated parameters is proposed for tubular connections used in thermal and HPHT applications.

Modeling of elasticity effects of sandstone compaction using coated inclusions

Geophysics ◽  
2011 ◽  
Vol 76 (3) ◽  
pp. E69-E79 ◽  
Author(s):  
Remy Agersborg ◽  
Tor Arne Johansen ◽  
Gary Mavko ◽  
Tiziana Vanorio
Keyword(s):  
Hybrid Approach ◽  
Rock Physics ◽  
Frequency Dispersion ◽  
Basic Feature ◽  
Hydrocarbon Exploration ◽  
Small Scale ◽  
Filling Material ◽  
Seismic Velocities ◽  
Pore Filling ◽  
Physical Foundation

Compaction of siliciclastic sediments leads to an increase in their stiffness parameters and seismic velocities. Although mechanical compaction implies a reduction of porosity and closing of compliant pores, chemical compaction may alter the mineral properties, the cementing of grain contacts, and the pore volume. The ability of rock physics models to quantify such effects on seismic observables will aid hydrocarbon exploration. A framework was designed for modeling compaction effects by use of a so-called coated inclusion model that eliminates the need of using a hybrid approach through combining different theories. A basic feature of the model is that the inclusion is defined by a kernel representing the pore, which is surrounded by shells that may individually have different elastic properties from those of the pore-filling material and the background matrix. The modeling can be designed to explore seismic effects of various texture perturbations, including contact cementing and pore-filling processes. The numerical modelings seem to be consistent with the results obtained from other rock physics models. The model allows for the possibility of including small-scale heterogeneities within the rock texture and estimating frequency dispersion together with attenuation due to pore fluid flow. A basic weakness of the method is the relatively large number of parameters needed to describe a porous rock, which will always limit its practical usage. However, its basic physical foundation may provide a reference for understanding the qualitative and quantitative effects of various cementation scenarios on seismic parameters.

scholarly journals Spatiotemporal Demand Prediction Model for E-Scooter Sharing Services with Latent Feature and Deep Learning

2021 ◽  
pp. 036119812110038
Author(s):  
Seung Woo Ham ◽  
Jung-Hoon Cho ◽  
Sangwoo Park ◽  
Dong-Kyu Kim
Keyword(s):  
Service Quality ◽  
Short Term Memory ◽  
Mean Squared Error ◽  
Demand Forecasting ◽  
Sparse Data ◽  
Walking Distance ◽  
Small Scale ◽  
Demand Prediction ◽  
Service Areas ◽  
Convolutional Autoencoder

The electric scooter (e-scooter) sharing service has attracted significant attention because of its extensive usage and eco-friendliness. Since e-scooters are mostly accessed by foot, the presence of e-scooters within walking distance has a crucial effect on the service quality. Therefore, to maintain appropriate service quality, relocation strategies are often used to properly distribute e-scooters within service areas. There are extensive literatures on demand forecasting for an efficient relocation. However, the study of the relocation of small-scale spatial units within walking distance level is still inadequate because of the sparsity of demand data. This research aims to establish an effective methodology for predicting the demand for e-scooters in high spatial resolution. A new grid-based spatial setting was created with the usage data. The model in the methodology predicts not only the identified demand but also the unmet demand to increase practicality. A convolutional autoencoder is used to obtain the latent feature that can reduce the problem of representing sparse data. An encoder–recurrent neural network–decoder (ERD) framework with a convolutional autoencoder resulted in a huge improvement in predicting spatiotemporal events. This new ERD framework shows enhanced prediction performance, reducing the mean squared error loss to 0.00036 from 0.00679 compared with the baseline long short-term memory model. This methodological strategy has its significance in that it can solve any prediction issue with spatiotemporal data, even those with sparse data problems.

Sign in / Sign up

Export Citation Format

Share Document