scholarly journals Managing Distributed Flexibility under Uncertainty by Combining Deep Learning with Duality

2021 ◽  
Author(s):  
Georgios Tsaousoglou ◽  
Katerina Mitropoulou ◽  
Konstantinos Steriotis ◽  
Nikolaos Paterakis ◽  
Pierre Pinson ◽  
...  
Keyword(s):  
Deep Learning ◽  
Power Systems ◽  
Renewable Energy Sources ◽  
Economic Dispatch ◽  
Multiple Sources ◽  
Arrival Times ◽  
Energy Needs ◽  
Markov Decision ◽  
Dual Variables ◽  
Economic Dispatch Problem

<div>In modern power systems, small distributed energy resources (DERs) are considered a valuable source of flexibility towards accommodating high penetration of Renewable Energy Sources (RES). In this paper we consider an economic dispatch problem for a community of DERs, where energy management decisions are made online and under uncertainty. We model multiple sources of uncertainty such as RES, wholesale electricity prices as well as the arrival times and energy needs of a set of Electric Vehicles. The economic dispatch problem is formulated as a multi-agent Markov Decision Process. The difficulties lie in the curse of dimensionality and in guaranteeing the satisfaction of constraints under uncertainty.</div><div>A novel method, that combines duality theory and deep learning, is proposed to tackle these challenges. In particular, a Neural Network (NN) is trained to return the optimal dual variables of the economic dispatch problem. By training the NN on the dual problem instead of the primal, the number of output neurons is dramatically reduced, which enhances the performance and reliability of the NN. Finally, by treating the resulting dual variables as prices, each distributed agent can self-schedule, which guarantees the satisfaction of its constraints. As a result, our simulations show that the proposed scheme performs reliably and efficiently.</div>

scholarly journals Managing Distributed Flexibility under Uncertainty by Combining Deep Learning with Duality

2021 ◽  
Author(s):  
Georgios Tsaousoglou ◽  
Katerina Mitropoulou ◽  
Konstantinos Steriotis ◽  
Nikolaos Paterakis ◽  
Pierre Pinson ◽  
...  
Keyword(s):  
Deep Learning ◽  
Power Systems ◽  
Renewable Energy Sources ◽  
Economic Dispatch ◽  
Multiple Sources ◽  
Arrival Times ◽  
Energy Needs ◽  
Markov Decision ◽  
Dual Variables ◽  
Economic Dispatch Problem

<div>In modern power systems, small distributed energy resources (DERs) are considered a valuable source of flexibility towards accommodating high penetration of Renewable Energy Sources (RES). In this paper we consider an economic dispatch problem for a community of DERs, where energy management decisions are made online and under uncertainty. We model multiple sources of uncertainty such as RES, wholesale electricity prices as well as the arrival times and energy needs of a set of Electric Vehicles. The economic dispatch problem is formulated as a multi-agent Markov Decision Process. The difficulties lie in the curse of dimensionality and in guaranteeing the satisfaction of constraints under uncertainty.</div><div>A novel method, that combines duality theory and deep learning, is proposed to tackle these challenges. In particular, a Neural Network (NN) is trained to return the optimal dual variables of the economic dispatch problem. By training the NN on the dual problem instead of the primal, the number of output neurons is dramatically reduced, which enhances the performance and reliability of the NN. Finally, by treating the resulting dual variables as prices, each distributed agent can self-schedule, which guarantees the satisfaction of its constraints. As a result, our simulations show that the proposed scheme performs reliably and efficiently.</div>

scholarly journals Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods

2020 ◽  
Vol 34 (01) ◽  
pp. 630-637 ◽  
Author(s):  
Ferdinando Fioretto ◽  
Terrence W.K. Mak ◽  
Pascal Van Hentenryck
Keyword(s):  
Deep Learning ◽  
Power Systems ◽  
Power Flow ◽  
Optimal Power Flow ◽  
Large Scale ◽  
Renewable Energy Sources ◽  
Electrical Power ◽  
Practical Applications ◽  
Fundamental Building Block ◽  
Optimal Power

The Optimal Power Flow (OPF) problem is a fundamental building block for the optimization of electrical power systems. It is nonlinear and nonconvex and computes the generator setpoints for power and voltage, given a set of load demands. It is often solved repeatedly under various conditions, either in real-time or in large-scale studies. This need is further exacerbated by the increasing stochasticity of power systems due to renewable energy sources in front and behind the meter. To address these challenges, this paper presents a deep learning approach to the OPF. The learning model exploits the information available in the similar states of the system (which is commonly available in practical applications), as well as a dual Lagrangian method to satisfy the physical and engineering constraints present in the OPF. The proposed model is evaluated on a large collection of realistic medium-sized power systems. The experimental results show that its predictions are highly accurate with average errors as low as 0.2%. Additionally, the proposed approach is shown to improve the accuracy of the widely adopted linear DC approximation by at least two orders of magnitude.

scholarly journals Risk Analysis of the Power System Protection Delayed Triggers in Power Network Integrating Renewable Energy Sources in Fault Dynamic States

2020 ◽  
Author(s):  
Mateusz Szablicki ◽  
Piotr Rzepka ◽  
Adrian Halinka
Keyword(s):  
Power Systems ◽  
Power System ◽  
Renewable Energy Sources ◽  
Operation Time ◽  
Power Network ◽  
Renewable Generation ◽  
System Protection ◽  
Energy Needs ◽  
Digital Protection ◽  
Decision Algorithms

In the development of power systems it is indicated very often, that transformation of power systems should be carried out in accordance with the idea of energy democracy. This will develop energy communities, that are trying to meet energy needs by using local renewable generation sources. This may result with a temporary low load on the MV lines connecting the community grid and the power system. Such state may cause incorrect operation of power protection systems. This can cause an extended protection operation time, due to decision algorithms inactivity at low values of measurement currents. Therefore, the detailed MV lines overcurrent digital protection model and a dynamic model of the power network were developed. The simulation results are showing that the settings of the parameters activating the protection decision algorithms affect their operation time in dynamic conditions. The conclusion is that the development of the power protection automatics must be carried out in the same time (preferably in advance) with the change of the power system operation model. This is very important for future power systems with high penetration energy communities and renewable generation sources.

scholarly journals Recent Approaches of Forecasting and Optimal Economic Dispatch to Overcome Intermittency of Wind and Photovoltaic (PV) Systems: A Review

Energies ◽  
2019 ◽  
Vol 12 (22) ◽  
pp. 4392 ◽  
Author(s):  
Manzoor Ellahi ◽  
Ghulam Abbas ◽  
Irfan Khan ◽  
Paul Mario Koola ◽  
Mashood Nasir ◽  
...  
Keyword(s):  
Neural Networks ◽  
Particle Swarm Optimization ◽  
Power Systems ◽  
Fossil Fuels ◽  
Renewable Energy Sources ◽  
Economic Dispatch ◽  
Energy Sources ◽  
Swarm Optimization ◽  
Pv Systems ◽  
High Penetration

Renewable energy sources (RESs) are the replacement of fast depleting, environment polluting, costly, and unsustainable fossil fuels. RESs themselves have various issues such as variable supply towards the load during different periods, and mostly they are available at distant locations from load centers. This paper inspects forecasting techniques, employed to predict the RESs availability during different periods and considers the dispatch mechanisms for the supply, extracted from these resources. Firstly, we analyze the application of stochastic distributions especially the Weibull distribution (WD), for forecasting both wind and PV power potential, with and without incorporating neural networks (NN). Secondly, a review of the optimal economic dispatch (OED) of RES using particle swarm optimization (PSO) is presented. The reviewed techniques will be of great significance for system operators that require to gauge and pre-plan flexibility competence for their power systems to ensure practical and economical operation under high penetration of RESs.

scholarly journals Emulation Strategies and Economic Dispatch for Inverter-Based Renewable Generation under VSG Control Participating in Multiple Temporal Frequency Control

2020 ◽  
Vol 10 (4) ◽  
pp. 1303
Author(s):  
Weichao Zhang ◽  
Xiangwu Yan ◽  
Hanyan Huang
Keyword(s):  
Power Systems ◽  
Frequency Control ◽  
Renewable Energy Sources ◽  
Temporal Frequency ◽  
Economic Dispatch ◽  
Synchronous Generator ◽  
System Stability ◽  
Frequency Regulation ◽  
Renewable Generation ◽  
Frequency Responses

As the increasing penetration of inverter-based generation (IBG) and the consequent displacement of traditional synchronous generators (SGs), the system stability and reliability deteriorate for two reasons: first, the overall inertia decreases since the power electronic interfaces (PEIs) are almost inertia-less; second, renewable generation profiles are largely influenced by stochastic meteorological conditions. To strengthen power systems, the concept of the virtual synchronous generator (VSG) has been proposed, which controls the external characteristics of PEIs to emulate those of SGs. Currently, PEIs could perform short-term inertial and primary frequency responses through the VSG algorithm. For renewable energy sources (RES), deloading strategies enable the generation units to possess active power reserves for system frequency responses. Additionally, the deloading strategies could provide the potential for renewable generation to possess long-term frequency regulation abilities. This paper focuses on emulation strategies and economic dispatch for IBG units to perform multiple temporal frequency control. By referring to the well-established knowledge systems of generation and operation in conventional power systems, the current VSG algorithm is extended and complemented by the emulation of secondary and tertiary regulations. The reliability criteria are proposed, considering the loss of load probability (LOLP) and renewable spillage probability (RSP). The reliability criteria are presented in two scenarios, including the renewable units operated in maximum power point tracking (MPPT) and VSG modes. A LOLP-based economic dispatch (ED) approach is solved to acquire the generation and reserve schemes. The emulation strategies and the proposed approach are verified by simulation.

Sign in / Sign up

Export Citation Format

Share Document