Optimization of Dynamic Dispatch for Multiarea Integrated Energy System Based on Hierarchical Learning Method

Li, Yijin; Tang, Hao; Lv, Kai; Wang, Ke; Wang, Gang

doi:10.1109/access.2020.2988085

Cited by 12 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The core of multi-time granulation based on external information is how to cluster the external information granules. It is to realize the period granulation of the low-carbon economic dispatching model of the electricity-gas integrated energy system [10]. Based on the idea of k-means clustering, this paper designs a granularity partition algorithm based on improved k-means clustering.…”

Section: Clustering Granularity Partitioning Algorithmmentioning

confidence: 99%

Dynamic state estimation method of urban electricity-gas-heat coupled energy network based on multiple time scales

Pan

Sun

Fang

et al. 2023

Third International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)

View full text Add to dashboard Cite

Under the background of the modern energy systems, the degree of interconnection and coupling between the power system and natural gas systems is gradually increasing. The economic dispatch model is becoming more and more complex. However, the economic dispatch of an integrated energy system is a high-dimensional, multi-period optimization problem, especially the multi-period joint optimization will greatly reduce the convergence speed of the model. Moreover, the electric power system and the natural gas system belong to two independent systems, which have a limited understanding of each other's information changes. In this paper, the cost of comprehensive operation is considered, and then the objective function is modeled. Based on the idea of k-means clustering, a granularity partition algorithm, which is based on the improved k-means clustering, is designed. To improve this algorithm, this paper adopts the shortest distance method to cluster the original data. Then, it adopts the rough clustering results to calculate the clustering center, and then applies the k-means clustering. From the source side heating coupling optimization and the load side load curve, the introduction of an air source heat pump at the source side and the consideration of waste heat recovery of electricity to the gas device can improve the flexibility of energy supply mode and optimize the heat supply coupling at the source site. Besides, it can equivalently decouple the problem of wind curtailment caused by the constraint of "determining power by heat" in co-generation, realize electric energy substitution and reduce the carbon emission of co-generation. Based on the principle of calorific value equivalence, the load side analyzes the energy conversion value of electric and thermal users, and forms a comprehensive demand response mechanism with energy substitution under the guidance of various energy price signals to assist wind power integration and consumption. Through the coordination and optimization of source and load, the phenomenon of wind power curtailment is significantly reduced while ensuring the economic operation of the system.

show abstract

Section: Clustering Granularity Partitioning Algorithmmentioning

confidence: 99%

Dynamic state estimation method of urban electricity-gas-heat coupled energy network based on multiple time scales

Pan

Sun

Fang

et al. 2023

Third International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)

View full text Add to dashboard Cite

show abstract

“…The uncertainties in both generation as well as load is incorporated into the MAED problem by utilizing an analytical method called Unscented Transformation. The authors in 80 proposed a hierarchical learning method for the dynamic energy dispatch problem of multi‐area integrated systems incorporated with renewables. The data‐driven based approach is adopted to avoid accurate modeling and the curse of dimensionality.…”

Section: Multi‐area Edmentioning

confidence: 99%

A comprehensive review of soft computing algorithms for optimal generation scheduling

et al. 2020

View full text Add to dashboard Cite

Summary Strategic planning for optimal operation of modern power systems has always been a significant task to satisfy the techno‐social aspects in the sustainable energy scenario. In the light of restructured power systems and decentralized generation, the economic dispatch (ED) problem has remained the utmost important economic assignment for the network operators. The conventional techniques have failed to address the nonlinear characteristics of generators for solving the practical ED problem. The complications identified in the literature are valve point loading, prohibited operating zones, multiple fuels, ramp rate limits, and spinning reserve. Therefore, a diverse range of traditional and modern optimization techniques have been adopted to tackle those complexities and nonlinearities. With the recent advancements in centralized optimization techniques, several research works were reported in the past decade to accomplish better results. This review paper endeavors to cover the pioneering research on centralized approaches as well as present‐day research trends on decentralized and distributed approaches by focusing on the economic aspects. First, a detailed survey of several deterministic, stochastic, nature‐inspired, and meta‐heuristic based centralized approaches for solving the ED problem is reviewed. A brief analysis based on the performance evaluation of centralized algorithms on six standard test systems is presented. Then, the recent literature on decentralized and distributed optimization approach and the consensus protocols with respect to various network topologies is briefly reviewed. The prime objective of this review is to summarize the centralized, decentralized, and distributed approaches to solve the classic dispatch, dynamic dispatch, economic emission dispatch, and multi‐area ED problems.

show abstract

“…A model‐free hierarchical learning method for multi‐region IMS dynamic energy scheduling optimisation was investigated in Ref. [8]. To enhance the flexible interactions among multiple energy carriers, a two‐stage optimisation scheme for a hybrid Alternating Current and Direct Current multi‐energy microgrid was presented in Ref.…”

Section: Introductionmentioning

confidence: 99%

An online dispatch approach for distributed integrated multi‐energy system considering non‐ideal communication conditions

Wang

et al. 2022

IET Energy Syst Integration

View full text Add to dashboard Cite

The distributed integrated multi-energy system (DIMS) has many advantages in terms of the utilisation of renewable energy sources and clean energy. Operation strategies for the DIMS based on a real-time profile have been extensively studied. In a DIMS online optimisation problem, besides fluctuations in the renewable energy output and load, inconsistent time scales of the transport dynamics of different energy flows and non-ideal communication (involving communication uncertainty and latency) result in suboptimal operation in dispatch scheduling. An online multi-time-scale optimal operation strategy is proposed for the DIMS to respond to the above challenges, using a hybrid algorithm comprising a model predictive control method and distributed collaborative consensus algorithm (CCA). The approach is based on a hierarchy, comprising rolling optimisation and adjustment. A rolling optimisation is established to schedule operations according to the latest forecast and status information. The rolling dispatch is then adjusted according to the ultrashort-term adjustment using the CCA. Meanwhile, the effect of the information transmission environment on real-time scheduling is considered, and the robust CCA is improved for the implementation of strategies under non-ideal communication conditions. Case studies and results are presented and discussed to show the effectiveness of the proposed approach with the better matching between demand and supply. K E Y W O R D S distributed integrated multi-energy system, model predictive control, multi-time-scale, non-ideal communication, robust collaborative consensus algorithm This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Optimization of Dynamic Dispatch for Multiarea Integrated Energy System Based on Hierarchical Learning Method

Cited by 12 publications

References 40 publications

Dynamic state estimation method of urban electricity-gas-heat coupled energy network based on multiple time scales

Dynamic state estimation method of urban electricity-gas-heat coupled energy network based on multiple time scales

A comprehensive review of soft computing algorithms for optimal generation scheduling

An online dispatch approach for distributed integrated multi‐energy system considering non‐ideal communication conditions

Contact Info

Product

Resources

About