1 January 2018 in IEEE Transactions on Sustainable Energy
This paper evaluates the scheduling problem for energy hub system consisting of wind turbine, combined heat and power units (CHP), auxiliary boilers and energy storage devices via hybrid stochastic/information gap decision theory (IGDT) approach. Considering that energy hub plays an undeniable role as the coupling among various energy infrastructures, still it is essential to be investigated in both modeling and scheduling aspects. On the other hand, penetration of wind power generation is significantly increased in energy infrastructures in recent years. In response, this paper aims to focus on the hybrid stochastic/IGDT optimization method for the optimal scheduling of wind integrated energy hub considering the uncertainties of wind power generation, energy prices and energy demands explicitly in a way that not only global optimal solution can be reached, but also volume of computations can be lighten. In addition, by the proposed hybrid model, the energy hub operator can pursue two different strategies to face with price uncertainty, i.e., risk-seeker strategy and risk-averse strategy. This method optimizes energy hub scheduling problem in uncertain environment by mixed-integer non-linear programming (MINLP). This formulation is proposed to minimize the expected operation cost of energy hub where different energy demands of energy hub would be efficiently met. The forecast errors of uncertainties related to wind power generation and energy demands are modeled as a scenario, while an IGDT optimization approach is proposed to model electricity price uncertainty.
3 February 2017 in IEEE Transactions on Industrial Informatics
This study presents a stochastic approach to design a wind integrated energy hub with multiple energy systems. Energy hub system offers significant advantages to energy services by providing the flexibility to cope with the challenging effects of intermittent renewable energy sources penetration. To this end, the wind integrated energy hub design problem would optimally determine appropriate number and size of system components that satisfy electricity and thermal demand and system constraints. To secure operation, the reliability indices such as the loss-of-load expectation and the expected energy not supplied are considered. The wind power generation and load forecasting uncertainties as well as the random outages of components are modeled as a scenario using proper scenario generation methods. The scenario reduction technique is also introduced to reduce the computational burden of the scenario-based design model. Finally, the proposed model is applied to a test case to illustrate effectiveness of the proposed approach.
1 August 2017 in Applied Thermal Engineering
12 March 2019 in IET Renewable Power Generation
BMBehnam Mohammadi‐Ivatloo
Multi‐carrier energy systems create new challenges as well as opportunities in future energy systems. One of these challenges is the interaction among different energy hubs’ facilities and various operational parameters on the scheduling of the energy hub systems. This paper deals with the problem of optimal scheduling of smart residential energy hub (SREH) considering the different uncertain parameters. The effect of the market prices, demands and solar radiation uncertainties on the SREH scheduling problem is characterised through a risk‐constrained two‐stage stochastic programming model. The objective of the proposed scheduling problem is to determine the least‐cost 24 h operation of the facilities that would cover the cooling, thermal and electrical demands. The Monte Carlo simulation method is applied to model the inaccuracies of solar radiation, energy demands, and electricity market prices. Additionally, a proper scenario‐reduction algorithm is employed to reduce the number of scenarios and simulation burden. The proposed approach evaluates the impacts of different values of risk aversion parameter and the utility of the demand response program on the optimal solution of the proposed PV integrated SREH scheduling. Finally, an illustrative example is provided to confirm the efficiency and the applicability of the proposed approach.
10 October 2022 in IEEE Transactions on Power Systems
This paper utilizes a fully model-free and data-driven deep reinforcement learning (DRL) framework to develop an intelligent controller that can exploit information to optimally schedule the energy hub with the aim of minimizing energy costs and emissions. By posing the energy hub scheduling problem as a multi-dimensional continuous state and action space, the proposed deep deterministic policy gradient (DDPG) method enables more cost-effective control strategies. The method can lead to a more efficient operation by considering nonlinear physical characteristics of the energy hub components like nonconvex feasible operating regions of combined heat and power (CHP) units, valve-point effects of power-only units, and fuel cell dynamic efficiency. Moreover, to provide great potential for the DDPG agent to learn an optimal policy in an efficient way, a hybrid forecasting model based on convolutional neural networks (CNNs) and bidirectional long short-term memories (BLSTMs) is developed to overcome the risk associated with PV power generation that can be highly intermittent, particularly on cloudy days. The effectiveness and applicability of the proposed scheduling framework in reducing energy costs and emissions while coping with uncertainties are demonstrated by comparing it against conventional robust optimization and stochastic programming approaches as well as state-of-the-art DRL methods in different case studies.
19 July 2021 in IEEE Transactions on Industrial Informatics
Optimizing wind turbine performance is still a challenge due to the dynamic interactions between the spatially temporally stochastic wind fields and the wind turbine as a complex mechanical system. Recent cost reduction of remote sensing wind measurement technologies, such as light detection and ranging (LiDAR), has opened a new research area on the use of deep learning models for predicting wind turbine's responses. In this article, a LiDAR-aided deep learning model is presented to learn the powerful spatial-temporal characteristics from the input wind fields. In the proposed method, the combination of 2-D convolutional neural networks (CNNs) and bidirectional long short-term memory (BLSTM) units is used to capture high levels of abstractions in wind fields concurrently, and thus, forecasting wind output power and fatigue load as two representatives of wind turbine responses. The LiDAR wind preview information is used as the 2-D-images of wind fields for the CNN. Moreover, the BLSTM is incorporated with the proposed CNN to improve the forecasting accuracy further and learn deep temporal features. The aero-elastic 5-MW reference wind turbine of National Renewable Energy Laboratory (NREL) is used to evaluate the performance of proposed model compared to the state-of-the-art deep-learning-based architectures in the recent literature.