scholarly journals Net demand short-term forecasting in a distribution substation with PV power generation

2020 ◽  
Vol 152 ◽  
pp. 01001 ◽  
Author(s):  
Eduardo Garcia-Garrido ◽  
Montserrat Mendoza-Villena ◽  
Pedro M. Lara-Santillan ◽  
Enrique Zorzano-Alba ◽  
Alberto Falces
Keyword(s):  
Power Generation ◽  
Solar Energy ◽  
Power Distribution ◽  
Distribution Systems ◽  
Electric Energy ◽  
Optimal Operation ◽  
Electric Energy Consumption ◽  
Short Term Forecasting ◽  
Artificial Neural Network Ann ◽  
Pv Power Generation

The integration of renewable energies, specifically solar energy, in electric distribution systems is increasingly common. For an optimal operation, it is very important to forecast the final net demand of the power distribution network, considering the variability of solar energy combined with the variability of the electric energy consumption habits of population. This paper presents the methodology followed to forecast the net demand in a power distribution substation. Two approaches are considered, the net demand direct prediction, and the indirect prediction with the forecasts of PV power generation and load demand. Artificial Neural Network (ANN) based models and autoregressive models with exogenous variables (ARX) are used to predict the net demand, directly and indirectly, for the 24 hours of the day-ahead. The methodology is applied to a medium voltage distribution substation and the direct and indirect forecasts are compared.

scholarly journals Ultra-Short-Term Forecasting of Photo-Voltaic Power via RBF Neural Network

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1717
Author(s):  
Wanxing Ma ◽  
Zhimin Chen ◽  
Qing Zhu
Keyword(s):  
Neural Network ◽  
Power Generation ◽  
Smart Grids ◽  
Percentage Error ◽  
Solar Pv ◽  
Short Term ◽  
Forecasting Method ◽  
Photo Voltaic ◽  
Short Term Forecasting ◽  
Pv Power Generation

With the fast expansion of renewable energy systems during recent years, the stability and quality of smart grids using solar energy have been challenged because of the intermittency and fluctuations. Hence, forecasting photo-voltaic (PV) power generation is essential in facilitating planning and managing electricity generation and distribution. In this paper, the ultra-short-term forecasting method for solar PV power generation is investigated. Subsequently, we proposed a radial basis function (RBF)-based neural network. Additionally, to improve the network generalization ability and reduce the training time, the numbers of hidden layer neurons are limited. The input of neural network is selected as the one with higher Spearman correlation among the predicted power features. The data are normalized and the expansion parameter of RBF neurons are adjusted continuously in order to reduce the calculation errors and improve the forecasting accuracy. Numerous simulations are carried out to evaluate the performance of the proposed forecasting method. The mean absolute percentage error (MAPE) of the testing set is within 10%, which show that the power values of the following 15 min. can be predicted accurately. The simulation results verify that our method shows better performance than other existing works.

scholarly journals Photovoltaic Power Forecasting Based on EEMD and a Variable-Weight Combination Forecasting Model

2018 ◽  
Vol 10 (8) ◽  
pp. 2627 ◽  
Author(s):  
Hui Wang ◽  
Jianbo Sun ◽  
Weijun Wang
Keyword(s):  
Power Generation ◽  
Solar Energy ◽  
Low Frequency ◽  
Intermediate Frequency ◽  
Developed Countries ◽  
Forecasting Model ◽  
Combination Forecasting ◽  
Variable Weight ◽  
Combination Forecasting Model ◽  
Pv Power Generation

It is widely considered that solar energy will be one of the most competitive energy sources in the future, and solar energy currently accounts for high percentages of power generation in developed countries. However, its power generation capacity is significantly affected by several factors; therefore, accurate prediction of solar power generation is necessary. This paper proposes a photovoltaic (PV) power generation forecasting method based on ensemble empirical mode decomposition (EEMD) and variable-weight combination forecasting. First, EEMD is applied to decompose PV power data into components that are then combined into three groups: low-frequency, intermediate-frequency, and high-frequency. These three groups of sequences are individually predicted by the variable-weight combination forecasting model and added to obtain the final forecasting result. In addition, the design of the weights for combination forecasting was studied during the forecasting process. The comparison in the case study indicates that in PV power generation forecasting, the prediction results obtained by the individual forecasting and summing of the sequences after the EEMD are better than those from direct prediction. In addition, when the single prediction model is converted to a variable-weight combination forecasting model, the prediction accuracy is further improved by using the optimal weights.

Benefit-Cost Analysis for Private PV System Investment with DSTATCOM Compensation

2014 ◽  
Vol 1030-1032 ◽  
pp. 2527-2531
Author(s):  
Shih Chieh Hsieh ◽  
Chao Shun Chen ◽  
Chia Hung Lin ◽  
Wei Lin Hsieh
Keyword(s):  
Power Generation ◽  
Cost Analysis ◽  
Distribution Systems ◽  
Voltage Control ◽  
Solar Irradiation ◽  
Pv System ◽  
Benefit Cost Analysis ◽  
Control Scheme ◽  
Benefit Cost ◽  
Pv Power Generation

This paper presents a benefit-cost analysis for private photovoltaic (PV) system investment with distribution static compensator (DSTATCOM) compensation to enhance the PV penetration in distribution systems. A hybrid voltage control scheme with reactive power compensation from DSTATCOMs and active power curtailment is applied to avoid the violation of voltage variation caused by large PV power injection. The PV power generation is estimated based on local solar irradiation and temperature data. The annual curve of PV power generation and annual energy delivered to the distribution system with the hybrid voltage control scheme are also determined. The annual revenue of PV power sales, the initial capital investment cost of a PV system with or without a DSTATCOM, and the operating and maintenance cost are then considered to evaluate the benefit and cost of the PV investment over its life cycle.

scholarly journals Review of Computational Intelligence Methods for Local Energy Markets at the Power Distribution Level to Facilitate the Integration of Distributed Energy Resources: State-of-the-art and Future Research

Energies ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 186 ◽  
Author(s):  
Pavlos S. Georgilakis
Keyword(s):  
Power Distribution ◽  
Distribution Systems ◽  
Energy Markets ◽  
Optimal Operation ◽  
Energy Resources ◽  
Distributed Energy Resources ◽  
Future Research ◽  
Local Energy ◽  
Distributed Energy ◽  
Computational Intelligence Methods

The massive integration of distributed energy resources in power distribution systems in combination with the active network management that is implemented thanks to innovative information and communication technologies has created the smart distribution systems of the new era. This new environment introduces challenges for the optimal operation of the smart distribution network. Local energy markets at power distribution level are highly investigated in recent years. The aim of local energy markets is to optimize the objectives of market participants, e.g., to minimize the network operation cost for the distribution network operator, to maximize the profit of the private distributed energy resources, and to minimize the electricity cost for the consumers. Several models and methods have been suggested for the design and optimal operation of local energy markets. This paper introduces an overview of the state-of-the-art computational intelligence methods applied to the optimal operation of local energy markets, classifying and analyzing current and future research directions in this area.

scholarly journals Statistical Approach in Analyzing of Advanced Metering Data in Power Distribution Grid

2019 ◽  
Vol 15 (2) ◽  
Author(s):  
Ivan Ramljak ◽  
Drago Bago
Keyword(s):  
Energy Consumption ◽  
Power Distribution ◽  
Distribution System ◽  
Statistical Approach ◽  
Electric Energy ◽  
Smart Metering ◽  
Distribution Grid ◽  
Smart Meters ◽  
Electric Energy Consumption ◽  
Advanced Metering

In last period many distribution system operators (DSO) invest significant amount of money in smart metering system. Those investments are in part due to regulatory obligations and in part due to needs of DSO (utilities) for knowledge about electric energy consumption. Term electric energy consumption refers not only on real consumption of electric energy but also on data about peak power, unbalance, voltage profiles, power losses etc. Data which DSO can have depends on type of smart metering system. Further, smart meters as source of data can be implemented in transformer stations (TS) MV/LV and in LV grid at consumer level. Generally, smart meters can be placed in any node of distribution grid. As amount of smart meters is greater, the possibility of data analysis is greater. In this paper a smart metering system of J.P Elektroprivreda HZ HB d.d, Mostar, Bosnia and Herzegovina will be presented. One statistical approach for analyzing of advanced metering data of TS MV/LV will be presented. Statistical approach presented here is powerful tool for analyzing great amount of data from distribution grid in simple way. Main contribution of this paper is in using results obtained from statistical analysis of smart meter data in distribution grid analyzing and in maintenance/investment planning.

USING A HEAT PUMP AS AN ALTERNATIVE TO SUPPORT SOLAR COLLECTOR FOR WATER HEATING IN BRAZIL

2012 ◽  
Vol 20 (03) ◽  
pp. 1250013 ◽  
Author(s):  
ROBERTS VINICIUS DE MELO REIS ◽  
RAPHAEL NUNES OLIVEIRA ◽  
LUIZ MACHADO ◽  
RICARDO NICOLAU NASSAR KOURY
Keyword(s):  
Energy Consumption ◽  
Solar Energy ◽  
Heat Pump ◽  
Electrical Resistance ◽  
Return On Investment ◽  
Electric Energy ◽  
Energy System ◽  
Solar Irradiation ◽  
Energy Deficit ◽  
Electric Energy Consumption

With related greenhouse effect environmental issues linked to the constant problems of the fluctuations in oil prices, the use of solar energy is an important renewable energy source. Brazil is a country which is privileged considering the high rates of solar irradiation present throughout almost the entire national territory. Nevertheless, during certain times of the year, there is a solar energy deficit, which leads solar systems to require electrical resistance support at these times. The use of electrical resistance represents 23.5% of electric energy consumption and it presents a low residential energy efficiency. The purpose of this work is an alternative technical design for reduction of electric energy consumption through the use of a solar energy system together with a generating heat pump for water heaters for households, as well as the financial feasibility study on the use of this system. One such heat pump has been designed, constructed and tested experimentally. The average performance coefficient is equal to 2.10, a low value due to the use of a hermetic reciprocating compressor. Despite this low moderate price coefficient of acquisition and installation of a heat pump, one can allow a return on investment in from 2.1 to 3.3 years, whereas the equipment has a useful life of about 20 years, this period of return on investment is interesting.

scholarly journals Energy Storage Scheduling in Distribution Systems Considering Wind and Photovoltaic Generation Uncertainties

Energies ◽  
2019 ◽  
Vol 12 (7) ◽  
pp. 1231 ◽  
Author(s):  
Iver Sperstad ◽  
Magnus Korpås
Keyword(s):  
Power Generation ◽  
Energy Storage ◽  
Distribution System ◽  
Power Flow ◽  
Distribution Systems ◽  
Optimal Power Flow ◽  
Planning Horizon ◽  
Optimal Operation ◽  
Operational Planning

Flexible distributed energy resources, such as energy storage systems (ESSs), are increasingly considered as means for mitigating challenges introduced by the integration of stochastic, variable distributed generation (DG). The optimal operation of a distribution system with ESS can be formulated as a multi-period optimal power flow (MPOPF) problem which involves scheduling of the charging/discharging of the ESS over an extended planning horizon, e.g., for day-ahead operational planning. Although such problems have been the subject of many works in recent years, these works very rarely consider uncertainties in DG, and almost never explicitly consider uncertainties beyond the current operational planning horizon. This article presents a framework of methods and models for accounting for uncertainties due to distributed wind and solar photovoltaic power generation beyond the planning horizon in an AC MPOPF model for distribution systems with ESS. The expected future value of energy stored at the end of the planning horizon is determined as a function of the stochastic DG resource variables and is explicitly included in the objective function. Results for a case study based on a real distribution system in Norway demonstrate the effectiveness of an operational strategy for ESS scheduling accounting for DG uncertainties. The case study compares the application of the framework to wind and solar power generation. Thus, this work also gives insight into how different approaches are appropriate for modeling DG uncertainty for these two forms of variable DG, due to their inherent differences in terms of variability and stochasticity.

Sign in / Sign up

Export Citation Format

Share Document