Optimal scheduling of regional integrated energy system considering multiple uncertainties and integrated demand response

Electric Power Systems Research, Journal Year: 2023, Volume and Issue: 217, P. 109169 - 109169

Published: Feb. 1, 2023

Language: Английский

---

Data-Driven hierarchical energy management in multi-integrated energy systems considering integrated demand response programs and energy storage system participation based on MADRL approach

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 103, P. 105264 - 105264

Published: Feb. 8, 2024

In this study, an intelligent and data-driven hierarchical energy management approach considering the optimal participation of renewable resources (RER), storage systems (ESSs) integrated demand response (IDR) programs execution based on wholesale retail market signals in multi-integrated system (MIES) structure is presented. The proposed objective function presented four levels, which include minimizing operating costs, environmental pollution risk reducing destructive effects cyberattacks such as false data injection (FDI). implemented central controller local multi-agent deep reinforcement learning method (MADRL). MADRL model formulated Markov decision process equations solved by soft actor-critic Q-learning algorithms two levels offline training online operation. different scenario results show operation cost reduction equivalent to 19.51%, 19.69%, cyber security 24%, 20.24%. has provided important step responding smart cities challenges requirements advantage fast response, high accuracy also computational time burden.

Language: Английский

---

Optimal operation of integrated energy systems considering energy trading and integrated demand response

Energy Reports, Journal Year: 2024, Volume and Issue: 11, P. 3307 - 3316

Published: March 11, 2024

Currently, a large number of integrated energy systems operate independently, which is not conducive to the efficient utilization clean energy. To fully utilize resources multiple systems, realize local consumption and utilization, further improve flexibility on demand side, this paper constructs an optimal scheduling framework for considering multi-energy sharing response. A cooperative operation model established minimize overall cost based Nash bargaining theory. The energy-sharing problem solved distributively via alternating direction multiplier method stakeholders' privacy security protected well. validity proposed verified by arithmetic analysis. Compared with situation independent no comprehensive response, strategy in article has better results. Implementing multi response can save 21.45% costs. whole system been reduced from initial 18033.26RMB 14164.39RMB. In addition, context fluctuating renewable scenarios, still effectively reduce Therefore, promote high practical value.

Language: Английский

---

Optimal dispatch of community integrated energy system based on Stackelberg game and integrated demand response under carbon trading mechanism

Applied Thermal Engineering, Journal Year: 2022, Volume and Issue: 219, P. 119508 - 119508

Published: Nov. 10, 2022

Language: Английский

---

Distributionally robust optimization model considering deep peak shaving and uncertainty of renewable energy

Energy, Journal Year: 2023, Volume and Issue: 288, P. 129935 - 129935

Published: Dec. 9, 2023

Language: Английский

---

A robust optimization model for green supplier selection and order allocation in a closed-loop supply chain considering cap-and-trade mechanism

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 228, P. 120423 - 120423

Published: May 12, 2023

Language: Английский

---

Multi-dimension day-ahead scheduling optimization of a community-scale solar-driven CCHP system with demand-side management

Renewable and Sustainable Energy Reviews, Journal Year: 2023, Volume and Issue: 185, P. 113654 - 113654

Published: Aug. 21, 2023

Language: Английский

---

Optimal energy system scheduling using a constraint-aware reinforcement learning algorithm

International Journal of Electrical Power & Energy Systems, Journal Year: 2023, Volume and Issue: 152, P. 109230 - 109230

Published: May 31, 2023

The massive integration of renewable-based distributed energy resources (DERs) inherently increases the system's complexity, especially when it comes to defining its operational schedule. Deep reinforcement learning (DRL) algorithms arise as a promising solution due their data-driven and model-free features. However, current DRL fail enforce rigorous constraints (e.g., power balance, ramping up or down constraints) limiting implementation in real systems. To overcome this, this paper, algorithm (namely MIP-DQN) is proposed, capable strictly enforcing all action space, ensuring feasibility defined schedule real-time operation. This done by leveraging recent optimization advances for deep neural networks (DNNs) that allow representation MIP formulation, enabling further consideration any space constraints. Comprehensive numerical simulations show proposed outperforms existing state-of-the-art algorithms, obtaining lower error compared with optimal global (upper boundary) obtained after solving mathematical programming formulation perfect forecast information; while (even unseen test days).

Language: Английский

---

Low carbon economic dispatch of integrated energy systems considering life cycle assessment and risk cost

International Journal of Electrical Power & Energy Systems, Journal Year: 2023, Volume and Issue: 153, P. 109287 - 109287

Published: June 15, 2023

Integrated energy systems (IES) strengthen the interaction among electricity, gas and heat systems, concept of low-carbon development can further reduce carbon emissions IES. However, uncertainty IES reduces supply flexibility complexity different chains accuracy trading volume. Therefore, this study proposes a low economic scheduling considering life cycle assessment (LCA) risk cost. First, generated from chain conversion processes in are analyzed by method. Subsequently, calculated emission coefficients introduced into ladder-type mechanism to constrain Specifically, system is controlled using conditional value-at-risk (CVaR) theory obtain day-ahead dispatch strategy. Finally, effectiveness proposed method verified based on modified IEEE 39-node electric network, 20-node network 6-node models.

Language: Английский

---

A random optimization strategy of microgrid dispatching based on stochastic response surface method considering uncertainty of renewable energy supplies and load demands

International Journal of Electrical Power & Energy Systems, Journal Year: 2023, Volume and Issue: 154, P. 109408 - 109408

Published: Aug. 17, 2023

The stochastic response of microgrid regulation under the influence uncertainty should be considered in day-ahead optimal dispatching. This paper focuses on Stochastic Response Surface Method (SRSM) modelling and Second-Order Cone Programming (SOCP) solution for optimization strategy dispatching considering random fluctuations renewable energy supplies load demands. Based SRSM theory, distributions are converted into independent standard normal by Nataf transformation, then means a small amount standardized samples fluctuations, Hermite Chaotic Polynomials can formulated to describe process adjustment. And Matrix establishes linear constraint functions probability distribution characteristics adjustment uncertainty. On this basis, based (SO) model with multi-objective constructed economic operation, control cost fluctuation lower carbon emissions. In addition, reduce operation risk, constraints extreme power shortage introduced model. To ensure convexity model, Relaxation is applied all quadratic terms Thus, proposed SO transformed an SOCP problem. Yalmip-Gurobi solver adopted which has efficient speed stability. effectiveness scheme demonstrated case studies using Monte Carlo sampling simulation.

Language: Английский

---