scholarly journals Training and Testing of a Single-Layer LSTM Network for Near-Future Solar Forecasting

2020 ◽  
Vol 10 (17) ◽  
pp. 5873
Author(s):  
Naylani Halpern-Wight ◽  
Maria Konstantinou ◽  
Alexandros G. Charalambides ◽  
Angèle Reinders
Keyword(s):  
Power Plants ◽  
Short Term Memory ◽  
Mean Squared Error ◽  
Renewable Energy Sources ◽  
Single Layer ◽  
Pv System ◽  
Lstm Network ◽  
Grid Operators ◽  
Single Layer Network ◽  
Power Forecasting

Increasing integration of renewable energy sources, like solar photovoltaic (PV), necessitates the development of power forecasting tools to predict power fluctuations caused by weather. With trustworthy and accurate solar power forecasting models, grid operators could easily determine when other dispatchable sources of backup power may be needed to account for fluctuations in PV power plants. Additionally, PV customers and designers would feel secure knowing how much energy to expect from their PV systems on an hourly, daily, monthly, or yearly basis. The PROGNOSIS project, based at the Cyprus University of Technology, is developing a tool for intra-hour solar irradiance forecasting. This article presents the design, training, and testing of a single-layer long-short-term-memory (LSTM) artificial neural network for intra-hour power forecasting of a single PV system in Cyprus. Four years of PV data were used for training and testing the model (80% for training and 20% for testing). With a normalized root mean squared error (nRMSE) of 10.7%, the single-layer network performed similarly to a more complex 5-layer LSTM network trained and tested using the same data. Overall, these results suggest that simple LSTM networks can be just as effective as more complicated ones.

scholarly journals CL-Net: ConvLSTM-Based Hybrid Architecture for Batteries’ State of Health and Power Consumption Forecasting

Mathematics ◽  
2021 ◽  
Vol 9 (24) ◽  
pp. 3326
Author(s):  
Noman Khan ◽  
Ijaz Ul Haq ◽  
Fath U Min Ullah ◽  
Samee Ullah Khan ◽  
Mi Young Lee
Keyword(s):  
Power Consumption ◽  
Short Term Memory ◽  
Mean Squared Error ◽  
Renewable Energy Sources ◽  
The State ◽  
Hybrid Architecture ◽  
State Of Health ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Traditional power generating technologies rely on fossil fuels, which contribute to worldwide environmental issues such as global warming and climate change. As a result, renewable energy sources (RESs) are used for power generation where battery energy storage systems (BESSs) are widely used to store electrical energy for backup, match power consumption and generation during peak hours, and promote energy efficiency in a pollution-free environment. Accurate battery state of health (SOH) prediction is critical because it plays a key role in ensuring battery safety, lowering maintenance costs, and reducing BESS inconsistencies. The precise power consumption forecasting is critical for preventing power shortage and oversupply, and the complicated physicochemical features of batteries dilapidation cannot be directly acquired. Therefore, in this paper, a novel hybrid architecture called ‘CL-Net’ based on convolutional long short-term memory (ConvLSTM) and long short-term memory (LSTM) is proposed for multi-step SOH and power consumption forecasting. First, battery SOH and power consumption-related raw data are collected and passed through a preprocessing step for data cleansing. Second, the processed data are fed into ConvLSTM layers, which extract spatiotemporal features and form their encoded maps. Third, LSTM layers are used to decode the encoded features and pass them to fully connected layers for final multi-step forecasting. Finally, a comprehensive ablation study is conducted on several combinations of sequential learning models using three different time series datasets, i.e., national aeronautics and space administration (NASA) battery, individual household electric power consumption (IHEPC), and domestic energy management system (DEMS). The proposed CL-Net architecture reduces root mean squared error (RMSE) up to 0.13 and 0.0052 on the NASA battery and IHEPC datasets, respectively, compared to the state-of-the-arts. These experimental results show that the proposed architecture can provide robust and accurate SOH and power consumption forecasting compared to the state-of-the-art.

scholarly journals AB-Net: A Novel Deep Learning Assisted Framework for Renewable Energy Generation Forecasting

Mathematics ◽  
2021 ◽  
Vol 9 (19) ◽  
pp. 2456
Author(s):  
Noman Khan ◽  
Fath U Min Ullah ◽  
Ijaz Ul Haq ◽  
Samee Ullah Khan ◽  
Mi Young Lee ◽  
...  
Keyword(s):  
Power Generation ◽  
Renewable Energy ◽  
Power Plants ◽  
Short Term Memory ◽  
Renewable Energy Sources ◽  
Critical Issue ◽  
Daily Basis ◽  
Short Term ◽  
Benchmark Datasets ◽  
Renewable Energy Generation

Renewable energy (RE) power plants are deployed globally because the renewable energy sources (RESs) are sustainable, clean, and environmentally friendly. However, the demand for power increases on a daily basis due to population growth, technology, marketing, and the number of installed industries. This challenge has raised a critical issue of how to intelligently match the power generation with the consumption for efficient energy management. To handle this issue, we propose a novel architecture called ‘AB-Net’: a one-step forecast of RE generation for short-term horizons by incorporating an autoencoder (AE) with bidirectional long short-term memory (BiLSTM). Firstly, the data acquisition step is applied, where the data are acquired from various RESs such as wind and solar. The second step performs deep preprocessing of the acquired data via several de-noising and cleansing filters to clean the data and normalize them prior to actual processing. Thirdly, an AE is employed to extract the discriminative features from the cleaned data sequence through its encoder part. BiLSTM is used to learn these features to provide a final forecast of power generation. The proposed AB-Net was evaluated using two publicly available benchmark datasets where the proposed method obtains state-of-the-art results in terms of the error metrics.

scholarly journals FRT and Transient Stability Augmentation of Grid-Connected PV Station Using Virtual Synchronous Generator

2021 ◽  
Vol 20 (4) ◽  
pp. 118-126
Author(s):  
Md. Kamrul Islam ◽  
Mohammad Abdul Mannan ◽  
Md. Rifat Hazari
Keyword(s):  
Control System ◽  
Power System ◽  
Power Plants ◽  
Renewable Energy Sources ◽  
Synchronous Generator ◽  
Frequency Stability ◽  
Pv System ◽  
Damping Characteristics ◽  
Grid Codes ◽  
Virtual Synchronous Generator

Due to the extensive integration of renewable energy sources (RESs), i.e., photovoltaic (PV) system, the future power system is developing into an inverter-based system from a dominated alternator-based power system. This massive penetration of inverter-based PV system reduced the system inertia and damping characteristics of the power grid, impacting the fault ride-through (FRT) capability and causes frequency instability. Modern grid codes require that PV systems should work in the same way as conventional power plants and assist the system during transient state. However, most of the conventional inverter control mechanisms failed to fulfill the requirements of grid codes, especially when the penetration ratio of the PV system is close to the conventional unit. Therefore, this paper proposes a virtual synchronous generator (VSG) control mechanism of PV system inverter to augment FRT competency and frequency stability. The proposed VSG control system mimics the behavior of conventional power plants. To observe and evaluate the proposed controller behavior, simulation analyses were executed in the PSCAD/EMTDC software for both proposed and conventional controllers. The simulation results clearly indicate that the proposed VSG control system has sufficient damping characteristics to ensure FRT capability and frequency stability.       

scholarly journals Intra-Day Solar Power Forecasting Strategy for Managing Virtual Power Plants

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5648
Author(s):  
Guillermo Moreno ◽  
Carlos Santos ◽  
Pedro Martín ◽  
Francisco Javier Rodríguez ◽  
Rafael Peña ◽  
...  
Keyword(s):  
Power Plants ◽  
Solar Power ◽  
Short Term Memory ◽  
Renewable Resource ◽  
Absolute Error ◽  
Virtual Power ◽  
Additional Information ◽  
Virtual Power Plants ◽  
Solar Power Forecasting ◽  
Power Forecasting

Solar energy penetration has been on the rise worldwide during the past decade, attracting a growing interest in solar power forecasting over short time horizons. The increasing integration of these resources without accurate power forecasts hinders the grid operation and discourages the use of this renewable resource. To overcome this problem, Virtual Power Plants (VPPs) provide a solution to centralize the management of several installations to minimize the forecasting error. This paper introduces a method to efficiently produce intra-day accurate Photovoltaic (PV) power forecasts at different locations, by using free and available information. Prediction intervals, which are based on the Mean Absolute Error (MAE), account for the forecast uncertainty which provides additional information about the VPP node power generation. The performance of the forecasting strategy has been verified against the power generated by a real PV installation, and a set of ground-based meteorological stations in geographical proximity have been used to emulate a VPP. The forecasting approach is based on a Long Short-Term Memory (LSTM) network and shows similar errors to those obtained with other deep learning methods published in the literature, offering a MAE performance of 44.19 W/m2 under different lead times and launch times. By applying this technique to 8 VPP nodes, the global error is reduced by 12.37% in terms of the MAE, showing huge potential in this environment.

scholarly journals Local market mechanisms survey for peer-to-peer electricity trading on blockchain platform

2020 ◽  
Vol XXIII (1) ◽  
pp. 186-191
Author(s):  
Simona-Vasilica Oprea
Keyword(s):  
Electricity Market ◽  
Power Plants ◽  
Renewable Energy Sources ◽  
Peer To Peer ◽  
Local Market ◽  
Market Mechanisms ◽  
Large Power ◽  
Electricity Trading ◽  
Auction Mechanisms ◽  
Grid Operators

Blockchain is a promising technology for local trading of the electricity. It has specific components, such as smart contracts, data ledger, consensus, and provides many benefits for both buyers and sellers because they are obtaining/generating electricity at better prices compared with the electricity from the public grid. This practice leads to a better integration of renewable energy sources, increasing the appetite for new local generation sources and storage facilities, transparency and trading opportunities for all market players. Grid operators also benefit from blockchain since the grid loading will be reduced as the grid does not have to transmit or distribute electricity from large power plants located far away from consumption place. In the end, the market players will benefit from reducing the grid loading and alleviating the congestions as onerous investment in grid infrastructure is avoided. In this paper, we will analyse the advantages of different electricity market mechanisms for trading and settlement. Several auction mechanisms such as pay-as-bid, uniform price, generalised second price or Vickrey-Clarke-Groves are taken into account as feasible options for local markets and peer-to-peer trading.

scholarly journals Inertia Theory Frequency Dynamic Analysis and Control of Power System with High Proportion of Renewable Source

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Badar ul Islam ◽  
Zuhairi Baharudin ◽  
Parameshwari Kattel
Keyword(s):  
Renewable Energy ◽  
Power System ◽  
Power Plants ◽  
Renewable Energy Sources ◽  
Frequency Stability ◽  
Test System ◽  
Energy Sources ◽  
Power Imbalance ◽  
Pv System ◽  
System Inertia

Power plant emissions are a major cause of pollution in the environment. This necessitates the progressive replacement of conventional power plants with renewable energy sources. Changes in the quotas for conventional generating and renewable energy sources present new issues for modern power networks for example photovoltaic and wind turbines are replacing conventional power plants, which do not add to system inertia and due to the earth’s diurnal cycle and weather conditions. Solar radiations are not consistent all through the day, and photovoltaic (PV) generation is sometimes insufficient to meet the power requirement of the shifting local load. The amount of inertia in the power system, as well as the action of adjustable frequency reserves and the amount of power imbalance, all have an impact on frequency stability. As a result, estimating power system inertia and assessing frequency response are required so that necessary actions can be taken to assure frequency stability. In this way, the system frequency, power, and voltage stability are the major issues when high proportion of renewables are added. In this paper, we explained estimating power system inertia-related frequency problems. The approach account for the frequency and voltage fluctuations that occur after a disturbance and estimate the system’s total inertia constant as well as its overall power imbalance. The anticipated technique based on computational intelligence is used to analyze frequency responses from simulations of a test system under various circumstances on SIMULINK and focuses on the standalone PV system is critical for controlling it. As a result, the modelling of a PV system, battery, and generator using analogous circuits is discussed. As a matter of fact, maximum power should be harvested from a PV array to increase its efficiency that is depicted from the result outcomes of this research.

A Review on Utilization of Fly- Ash and Pond-Ash as a Partial Replacement of Cement in Concrete Mix Design

2018 ◽  
pp. 413-418
Author(s):  
Harshkumar Patel ◽  
Yogesh Patel
Keyword(s):  
Fly Ash ◽  
Electricity Generation ◽  
Power Plants ◽  
Renewable Energy Sources ◽  
Thermal Power ◽  
Strength Test ◽  
Partial Replacement ◽  
Pond Ash ◽  
Research Activities ◽  
Ash Disposal

Now-a-days energy planners are aiming to increase the use of renewable energy sources and nuclear to meet the electricity generation. But till now coal-based power plants are the major source of electricity generation. Disadvantages of coal-based thermal power plants is disposal problem of fly ash and pond ash. It was earlier considered as a total waste and environmental hazard thus its use was limited, but now its useful properties have been known as raw material for various application in construction field. Fly ash from the thermal plants is available in large quantities in fine and coarse form. Fine fly ash is used in construction industry in some amount and coarse fly ash is subsequently disposed over land in slurry forms. In India around 180 MT fly is produced and only around 45% of that is being utilized in different sectors. Balance fly ash is being disposed over land. It needs one acre of land for ash disposal to produce 1MW electricity from coal. Fly ash and pond ash utilization helps to reduce the consumption of natural resources. The fly ash became available in coal based thermal power station in the year 1930 in USA. For its gainful utilization, scientist started research activities and in the year 1937, R.E. Davis and his associates at university of California published research details on use of fly ash in cement concrete. This research had laid foundation for its specification, testing & usages. This study reports the potential use of pond-ash and fly-ash as cement in concrete mixes. In this present study of concrete produced using fly ash, pond ash and OPC 53 grade will be carried. An attempt will be made to investigate characteristics of OPC concrete with combined fly ash and pond ash mixed concrete for Compressive Strength test, Split Tensile Strength test, Flexural Strength test and Durability tests. This paper deals with the review of literature for fly-ash and pond-ash as partial replacement of cement in concrete.

PROSPECTS OF OBTAINING ALTERNATIVE FUEL FROM VARIOUS BIOMASS AND WASTE SPECIES IN AZERBAIJAN

2019 ◽  
pp. 25-41
Author(s):  
O. M. Salamov ◽  
F. F. Aliyev
Keyword(s):  
Power Plants ◽  
Energy Intensity ◽  
Oil And Gas ◽  
Renewable Energy Sources ◽  
Calorific Value ◽  
High Energy ◽  
Energy Sector ◽  
Energy Sources ◽  
Mineral Fertilizers ◽  
Gaseous Fuels

The paper discusses the possibility of obtaining liquid and gaseous fuels from different types of biomass (BM) and combustible solid waste (CSW) of various origins. The available world reserves of traditional types of fuel are analyzed and a number of environmental shortcomings that created during their use are indicated. The tables present the data on the conditional calorific value (CCV) of the main traditional and alternative types of solid, liquid and gaseous fuels which compared with CCV of various types of BM and CSW. Possible methods for utilization of BM and CSW are analyzed, as well as the methods for converting them into alternative types of fuel, especially into combustible gases.Reliable information is given on the available oil and gas reserves in Azerbaijan. As a result of the research, it was revealed that the currently available oil reserves of Azerbaijan can completely dry out after 33.5 years, and gas reserves–after 117 years, without taking into account the growth rates of the exported part of these fuels to European countries. In order to fix this situation, first of all it is necessary to use as much as possible alternative and renewable energy sources, especially wind power plants (WPP) and solar photovoltaic energy sources (SFES) in the energy sector of the republic. Azerbaijan has large reserves of solar and wind energy. In addition, all regions of the country have large reserves of BM, and in the big cities, especially in industrial ones, there are CSW from which through pyrolysis and gasification is possible to obtain a high-quality combustible gas mixture, comprising: H2 + CO + CH4, with the least amount of harmful waste. The remains of the reaction of thermochemical decomposition of BM and CSW to combustible gases can also be used as mineral fertilizers in agriculture. The available and projected resources of Azerbaijan for the BM and the CSW are given, as well as their assumed energy intensity in the energy sector of the republic.Given the high energy intensity of the pyrolysis and gasification of the BM and CSW, at the present time for carrying out these reactions, the high-temperature solar installations with limited power are used as energy sources, and further preference is given to the use of WPP and SFES on industrial scale.

WIND-DIESEL INSTALLATIONS FOR ISOLATED FAR NORTH AREAS

2020 ◽  
Author(s):  
Александр Григорьевич Комков ◽  
Александр Константинович Сокольский
Keyword(s):  
Energy Supply ◽  
Alternative Energy ◽  
Power Plants ◽  
Renewable Energy Sources ◽  
Energy Sources ◽  
Economic Potential ◽  
Far North ◽  
Alternative Energy Sources ◽  
Current State ◽  
Solar Power Plants

В статье рассмотрено современное состояние энергоснабжения и перспективы развития альтернативных источников энергии на территории Крайнего Севера. Отмечено, что несмотря на острую потребность во внедрении возобновляемых источников энергии, установленные мощности всех ветряных и солнечных электростанций в регионе не превышают 7-8 МВт. Также в работе рассчитаны технический и экономический потенциал ветровой энергии региона, на основании которых подобрана наиболее эффективная установка. The article discusses the current state of energy supply and the prospects for the development of alternative energy sources in the Far North. It is noted that despite the urgent need for the introduction of renewable energy sources, the installed capacities of all wind and solar power plants in the region do not exceed 7-8 MW. Also, the technical and economic potential of the region’s wind energy was calculated based on which the most efficient installation was selected.

scholarly journals Analyzing Trade in Continuous Intra-Day Electricity Market: An Agent-Based Modeling Approach

Energies ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 3860
Author(s):  
Priyanka Shinde ◽  
Ioannis Boukas ◽  
David Radu ◽  
Miguel Manuel de Manuel de Villena ◽  
Mikael Amelin
Keyword(s):  
Renewable Energy ◽  
Electricity Market ◽  
Power Plants ◽  
Renewable Energy Sources ◽  
Thermal Power ◽  
Agent Based Modeling ◽  
Market Liquidity ◽  
Energy Sources ◽  
Modeling Framework ◽  
Agent Based

In recent years, the vast penetration of renewable energy sources has introduced a large degree of uncertainty into the power system, thus leading to increased trading activity in the continuous intra-day electricity market. In this paper, we propose an agent-based modeling framework to analyze the behavior and the interactions between renewable energy sources, consumers and thermal power plants in the European Continuous Intra-day (CID) market. Additionally, we propose a novel adaptive trading strategy that can be used by the agents that participate in CID market. The agents learn how to adapt their behavior according to the arrival of new information and how to react to changing market conditions by updating their willingness to trade. A comparative analysis was performed to study the behavior of agents when they adopt the proposed strategy as opposed to other benchmark strategies. The effects of unexpected outages and information asymmetry on the market evolution and the market liquidity were also investigated.

Sign in / Sign up

Export Citation Format

Share Document