Smart Generation Control Strategy Based on State Optimal Feedback of Deep Belief Network

doi:10.12204/j.issn.1000-7229.2021.10.009

Abstract

Abstract:

According to the theory of deep belief network (DBN) and optimal control, this paper proposes a DBN state optimal feedback algorithm, which is applied to the field of automatic generation control. Firstly, a full-state optimal feedback control strategy suitable for power generation control problem is designed, and the deep-belief network is introduced to learn the characteristics of full-state optimal feedback control. The nonlinear expression ability of deep-belief network is used to make up for the deficiency of traditional linear control, thus the approximate optimal power generation control with incomplete state information feedback is realized, which effectively solves the problem of state information measurement in optimal generation control, and improves the performance of automatic generation control. The simulation results show that the the DBN state optimal feedback algorithm is able to realize the approximate optimal generation control under the combined feedback of self-area frequency deviation and transmission power deviation. The effectiveness, feasibility and strong robustness of the proposed algorithm are verified.

Key words: automatic generation control, deep-belief network, state optimal feedback, approximate optimal, state information, interconnected power systems

CLC Number:

TM761

QI Huanxing, YIN Linfei, WAN Jun, HUANG Yanglong. Smart Generation Control Strategy Based on State Optimal Feedback of Deep Belief Network[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(10): 78-88.

Figures/Tables 13

Fig.1 LFC model of two-area interconnected power system

Table 1 Parameter values of two-area interconnected power system

Fig.2 LFC system of Two-area interconnected power system applying FSOF

Fig.3 Model of deep belief network

Fig.4 DBN state optimal feedback control algorithm

Fig.5 DBN training process

Fig.6 LFC model of two-area interconnected power system under DBNSOF control

Fig.7 Automatic generation control test under step load disturbance

Table 2 AGC performance index under step load disturbance

Fig.8 AGC simulation results of nominal parameter system

Fig.9 AGC simulation results of system with uncertain parameters

Table 3 AGC simulative statistical results of nominal parameter system

Table 4 AGC simulative statistical results of system with uncertain parameters

References 27

[1]	SZNAIER M, BIANCHINI F. Mixed L^∞/H_∞ suboptimal controllers for SISO continuous-time systems[J]. IEEE Transactions on Automatic Control, 2016, 40(11): 1831-1840. doi: 10.1109/TAC.1995.7469037 URL
[2]	JOSÉ C G, GABRIEL G W. Optimal H∞ state feedback sampled-data control design of Markov jump linear systems[J]. Automatica, 2015, 54: 182-188. doi: 10.1016/j.automatica.2015.02.011 URL
[3]	HADDAD W M, L’AFFLITTO A. Finite-time stabilization and optimal feedback control[J]. IEEE Transactions on Automatic Control, 2016, 61(4): 1069-1074. doi: 10.1109/TAC.2015.2454891 URL
[4]	白莎, 潘晨玥, 熊思宇, 等. 考虑带外干扰的电力系统频率测量算法[J]. 电网技术, 2019, 43(3): 762-768.
	BAI Sha, PAN Chenyin, XIONG Siyu, et al. A frequency estimation algorithm of power system considering out-of-band interference[J]. Power System Technology, 2019, 43(3): 762-768.
[5]	QI Q Y, ZHANG H S, JI Z J. Further results on stabilization for NCSs with packet losses and transmission delay: UDP case[J]. Journal of the Franklin Institute, 2019, 356(8): 4601-4621. doi: 10.1016/j.jfranklin.2019.04.022 URL
[6]	TAHA A, BAZRAFSHAN M, NUGROHO S A, et al. Robust control for renewable-integrated power networks considering input bound constraints and worst case uncertainty measure[J]. IEEE Transactions on Control of Network Systems, 2019, 6(99): 1210-1222. doi: 10.1109/TCNS.2019.2930452 URL
[7]	SONDHI S, HOTE Y V. Fractional order PID controller for load frequency control[J]. Energy Conversion and Management, 2014, 85(9): 343-353. doi: 10.1016/j.enconman.2014.05.091 URL
[8]	IBRAHEEM N, KUMAR P, HASAN N, et al. Sub-optimal automatic generation control of interconnected power system using constrained feedback control strategy[J]. Electric Machines & Power Systems, 2012, 40(9): 977-994.
[9]	颜伟, 赵瑞锋, 赵霞, 等. 自动发电控制中控制策略的研究发展综述[J]. 电力系统保护与控制, 2013, 41(8): 154-160.
	YAN Wei, ZHAO Ruifeng, ZHAO Xia, et al. Review on control strategies in automatic generation control[J]. Power System Protection and Control, 2013, 41(8): 154-160.
[10]	VARGAS S A, TELLES ESTEVES G R, MACAIRA P M, et al. Wind power generation: A review and a research agenda[J]. Journal of Cleaner Production, 2019, 218(1): 850-870. doi: 10.1016/j.jclepro.2019.02.015 URL
[11]	丁明, 王伟胜, 王秀丽, 等. 大规模光伏发电对电力系统影响综述[J]. 中国电机工程学报, 2014, 34(1): 1-14.
	DING Ming, WANG Weisheng, WANG Xiuli, et al. A review on the effect of large-scale PV generation on power systems[J]. Proceedings of the CSEE, 2014, 34(1): 1-14.
[12]	胡泽春, 罗浩成. 大规模可再生能源接入背景下自动发电控制研究现状与展望[J]. 电力系统自动化, 2018, 42(8): 2-15.
	HU Zechun, LUO Haocheng. Research status and prospect of automatic generation control with integration of large-scale renewable energy[J]. Automation of Electric Power Systems, 2018, 42(8): 2-15.
[13]	邵汉桥, 张籍, 张维. 分布式光伏发电经济性及政策分析[J]. 电力建设, 2014, 35(7): 51-57.
	SHAO Hanjiao, ZHANG Ji, ZHANG Wei. Economy and policy analysis of distributed photovoltaic generation[J]. Electric Power Construction, 2014, 35(7): 51-57.
[14]	胡泽春, 占恺峤, 徐智威, 等. 电动汽车与电网互动的关键问题分析与展望[J]. 电力建设, 2015, 36(7): 6-13.
	HU Zechun, ZHAN Kaiqiao, XU Zhiwei, et al. Analysis and outlook on the key problems of electric vehicle and power grid interaction[J]. Electric Power Construction, 2015, 36(7): 6-13.
[15]	李扬, 韦钢, 马钰, 等. 含电动汽车和分布式电源的主动配电网动态重构[J]. 电力系统自动化, 2018, 42(5): 102-110.
	LI Yang, WEI Gang, MA Yu, et al. Dynamic reconfiguration of active distribution network considering electric vehicles and distributed generations[J]. Automation of Electric Power Systems, 2018, 42(5): 102-110.
[16]	CHEN G G, LI Z J, Zhang Z Z, et al. An improved ACO algorithm optimized fuzzy pid controller for load frequency control in multi area interconnected power systems[J]. IEEE Access, 2020, 8: 6429-6447. doi: 10.1109/ACCESS.2019.2960380 URL
[17]	殷林飞, 余涛. 基于深度Q学习的强鲁棒性智能发电控制器设计[J]. 电力自动化设备, 2018, 38(5): 12-19.
	YIN Linfei, YU Tao. Design of strong robust smart generation controller based on deep Q learning[J]. Electric Power Automation Equipment, 2018, 38(5): 12-19.
[18]	Yin L F, Zhang B, Yu T, et al. Adaptive distributed consensus protocol for automatic generation control of large-scale interconnected power systems[J]. IEEE Access, 2019, 7: 48167-48174. doi: 10.1109/ACCESS.2019.2910567 URL
[19]	李彬, 张洁, 田世明, 等. 智能电网用户域标准化最新进展及发展趋势[J]. 电力建设, 2018, 39 (3): 12-22.
	LI Bin, ZHANG Jie, TIAN Shiming, et al. Recent progress and trend analysis of standardization of smart grid user domain[j]. electric power construction, 2018, 39 (3): 12-22.
[20]	翁毅选, 邓长虹, 黄文涛, 等. 基于最优动态闭环控制的水火电互联大电网自动发电控制策略[J]. 电力自动化设备, 2013, 33(3): 66-71.
	WENG Yixuan, DENG Changhong, HUANG Wentao, et al. AGC based on optimal dynamic closed-loop control for interconnected power grid[J]. Electric Power Automation Equipment, 2013, 33(3): 66-71.
[21]	KHAMPARIA A, SINGH K M. A systematic review on deep learning architectures and applications[J]. Expert Systems, 2019, 36(3): 1-22.
[22]	熊伟丽, 孙文心, 史旭东. 基于曲率信息的改进BP算法及其在FNN中的应用[J]. 系统仿真学报, 2020, 32(1): 1-8. doi: 10.16182/j.issn1004731x.joss.17-0461
	XIONG Weili, SUN Wenxin, SHI Xudong. Curvature-based BP algorithm optimization and its application in FNN[J]. Journal of System Simulation, 2020, 32(1): 1-8.
[23]	MERINO E R, CASTRILLEJO F M, PIN J D, et al. Weighted contrastive divergence[J]. Neural Networks, 2018, 106: 147-156.
[24]	HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554. doi: 10.1162/neco.2006.18.7.1527 URL
[25]	杨永强, 巴宇, 吴玉琼, 等. 联络线功率控制性能评价标准的实施方式[J]. 电力系统自动化, 2015, 39(10): 100-106.
	YANG Yongqiang, BA Yu, WU Yuqiong, et al. Implementation mode of tie-line power control performance assessment standard[J]. Automation of Electric Power Systems, 2015, 39(10): 100-106.
[26]	JALEELI N, VANSLYCK L S. NERC’s new control performance standards[J]. Power systems IEEE trans on power systems, 1999, 14(3): 1092-1099.
[27]	WANG J, ZHANG B, SUN Z, et al. A novel conjugate gradient method with generalized Armijo search for efficient training of feedforward neural networks[J]. Neurocomputing, 2017, 275(31): 308-316. doi: 10.1016/j.neucom.2017.08.037 URL