Dynamic Economic Scheduling with Self-Adaptive Uncertainty in Distribution Network Based on Deep Reinforcement Learning

Traditional optimal scheduling methods are limited to accurate physical models and parameter settings, which aredifficult to adapt to the uncertainty of source and load, and there are problems such as the inability to make dynamicdecisions continuously. This paper proposed a dynamic economic scheduling method for distribution networksbased on deep reinforcement learning. Firstly, the economic scheduling model of the new energy distributionnetwork is established considering the action characteristics of micro-gas turbines, and the dynamic schedulingmodel based on deep reinforcement learning is constructed for the new energy distribution network system with ahigh proportion of new energy, and the Markov decision process of the model is defined. Secondly, Second, for thechanging characteristics of source-load uncertainty, agents are trained interactively with the distributed networkin a data-driven manner. Then, through the proximal policy optimization algorithm, agents adaptively learn thescheduling strategy and realize the dynamic scheduling decision of the new energy distribution network system.Finally, the feasibility and superiority of the proposed method are verified by an improved IEEE 33-node simulationsystem.

Optimized scheduling of integrated energy systems for low carbon economy considering carbon transaction costs

With the introduction of the“dual carbon”goal and the continuous promotion of low-carbon development,the integrated energy system(IES)has gradually become an effective way to save energy and reduce emissions.This study proposes a low-carbon economic optimization scheduling model for an IES that considers carbon trading costs.With the goal of minimizing the total operating cost of the IES and considering the transferable and curtailable characteristics of the electric and thermal flexible loads,an optimal scheduling model of the IES that considers the cost of carbon trading and flexible loads on the user side was established.The role of flexible loads in improving the economy of an energy system was investigated using examples,and the rationality and effectiveness of the study were verified through a comparative analysis of different scenarios.The results showed that the total cost of the system in different scenarios was reduced by 18.04%,9.1%,3.35%,and 7.03%,respectively,whereas the total carbon emissions of the system were reduced by 65.28%,20.63%,3.85%,and 18.03%,respectively,when the carbon trading cost and demand-side flexible electric and thermal load responses were considered simultaneously.Flexible electrical and thermal loads did not have the same impact on the system performance.In the analyzed case,the total cost and carbon emissions of the system when only the flexible electrical load response was considered were lower than those when only the flexible thermal load response was taken into account.Photovoltaics have an excess of carbon trading credits and can profit from selling them,whereas other devices have an excess of carbon trading and need to buy carbon credits.

Intelligent Scheduling for High Bulilding Multi-type Cooling System

In modern giant buildings,in order to improve energy utilization efficiency, cooling systems have developed from conventional chillers alone to smart energy net which includes chillers,ice storage,ground-source heat pump,combined cooling heating and power( CCHP) and so on. The reasonable distribution of load is the key to guarantee such system in economical operation.Based on typical multi-type cooling system,economic models of different devices are presented and real-time intelligent economic scheduling with the approach of mixed integer programming is carried out. This algorithm has been applied in a certain building of Shanghai and results of simulation show that it is able to provide guidance on intelligent economic scheduling for multi-type cooling system.

Effect of thermal storage performance of concrete radiant cooling room on indoor temperature

A building model with radiant cooling system was established and the cooling load, indoor temperature, surface temperature of the wails and other parameters in non-cooling and radiant cooling room were calculated by TRNSYS. The comparative analysis of the characteristics of attenuation and delay proves that the operation of radiant cooling system increases the degree of temperature attenuation of the room and reduces the inner surface temperature of the wall significantly, but has little effect on the attenuation coefficient and delay time of wall heat transfer. The simulation results also show that the inner surface temperature of the walls in the radiant cooling room is much lower than that in non-cooling room in the day with the maximum cooling load, which reduces the indoor operation temperature largely, and improves the thermal comfort. Finally, according to the analysis of indoor temperature of the rooms with different operation schedules of cooling system, it can be derived that the indoor mean temperature changes with the working time of radiant cooling system, and the operation schedule can be adjusted in practice according to the actual indoor temperature to achieve the integration of energy efficiency and thermal comfort.

Development of the laminar flow cooling control system of the No.3 hot strip rolling line at Baosteel

The coiling temperature of the hot strip rolling process plays an important role in strip quality control. The newly-built laminar flow cooling control system was independently developed by Baosteel. L2 conducts totally dynamic control （L1 only executes the result from L2, and does not conduct any dynamic control ）. The system has many advantages, such as quick real-time control, accurate model calculation, quick response after self-adaptation, etc. Compared with the 2050 mm hot strip rolling line,the new system can satisfy the strict cooling requirements of high strength steel, silicon steel and heavy plates because of its newly-developed technologies of cooling rate control, strip cooling by sections and proportion-integral-differential coefficient （PID） feedback fuzzy control.

Mixed Self-adapting GA Optimal Scheduling Algorithm for a Multiple Resource Job-shop

With an aim at the job-shop scheduling problem of multiple resource constraints, this paper presents mixed self-adapting Genetic Algorithm （ GA ） , and establishes a job-shop optimal scheduling model of multiple resource constraints based on the effect of priority scheduling rules in the heuristic algorithm upon the scheduling target. New coding regulations or rules are designed. The sinusoidal function is adopted as the self-adapting factor, thus making cross probability and variable probability automatically change with group adaptability in such a way as to overcome the shortcoming in the heuristic algorithm and common GA, so that the operation efficiency is improved. The results from real example simulation and comparison with other algorithms indicate that the mixed self-adapting GA algorithm can well solve the job-shop optimal scheduling problem under the constraints of various kinds of production resources such as machine-tools and cutting tools.

果蔬采后分级和预冷车辆协同调度模型与算法

新兴的移动式分级、预冷技术应用于果蔬田间采后处理,有助于降低采后损耗,也催生了采后“最先一公里”冷链物流环节协同运作优化问题。以采后分级、预冷环节为例,综合考虑果蔬最佳预冷时间、先分级后预冷的服务顺序等特有协同情景,构建了移动式分级预冷资源协同调度优化模型。与现有模型不同,本研究考虑延迟预冷对果蔬新鲜度的特殊影响,设计了延迟预冷成本函数,在保障产品质量的同时最小化服务运作成本。设计混合遗传算法对模型进行求解,该算法融合了遗传算法与邻域搜索算法,增强混合算法的局部和全局搜索能力。其中,结合问题的双需求特点及关键协同约束,设计了基于双序列的解的表达方式、基于最佳插入策略的交叉算子以及基于三阶段邻域搜索的变异操作,以提高算法的收敛速度与求解质量。通过与标准遗传算法和变邻域搜索算法对比,验证了本文算法在求解大规模算例时可以更快收敛到更高质量的解。基于陕西省洛川县水蜜桃产业的分级预冷数据证明了模型的合理性。本研究有助于把协同运作优化思想引入果蔬采后“最先一公里”冷链物流环节,为降低我国果蔬采后损耗提供创新性解决思路。

气膜孔电加工智能产线控制系统研究

针对航空发动机叶片气膜孔电加工领域生产线自动化程度不高、生产效率较低的问题,对电加工智能产线控制系统展开研究。基于叶片电加工的工艺特点,设计智能生产线的工艺流程及产线布局;根据所需功能要求设计产线控制系统总体结构,并对控制原理及具体实现进行研究,包括控制系统具体的产线控制流程及内部控制机制,用以保证产线的稳定运行。在模拟环境下对系统进行验证,研究结果表明:系统运行正常,能够实现叶片的自动化加工。

Design and Simulation Test of Advanced Secondary Cooling Control System of Continuous Casting Based on Fuzzy Self-Adaptive PID

To improve billet quality and the trackability and stability of secondary cooling water during continuous casting, the superheat is introduced into the water distribution for secondary cooling to design the relevant control system, based on the water distribution model, superheat and fuzzy self-adaptive PID （process identity） . A spray cooling system is set up for simulation test in laboratory to test the step signal from the conventional, integral sepa rated and fuzzy self-adaptive PID controllers and the simulation casting. And the on-site test is done in some steel plant. The test results show that the fuzzy self-adaptive PID controller＇s performance is better than that of the other two controllers, which provides a basis for further study and application.

Microstructure and mechanical properties of X80 pipeline steels in different cooling schedules

The microstructures and mechanical properties of three X80 pipeline steel plates were investigated in this study.The plates were hot rolled by two stages, and cooled by three different cooling schedules to obtain different microstructures and mechanical properties.Transmission electron microscope（TEM） was used to observe the microstructure.The results indicated that the amount of polygonal ferrite（PF） and quasi-polygonal ferrite（QPF） decreased with decreasing of the finish cooling temperature（FCT）, while the amount and size of M-A islands were larger.Relaxation promoted the Charpy V-notch（CVN） impact toughness at-20℃, but not the drop weight tear testing（DWTT） property at-15℃, and decreased the strength of the steel.

Optimal Scheduling of Air Conditioners for Energy Efficiency

Energy saving is one of the most important research hotspots, by which operational expenditure and CO2 emission can be reduced. Optimal cooling capacity scheduling in addition to temperature control can improve energy efficiency. The main contribution of this work is modeling the telecommunication building for the fabric cooling load to schedule the operation of air conditioners. The time series data of the fabric cooling load of the building envelope is taken by simulation by using Energy Plus, Building Control Virtual Test Bed （BCVTB）, and Matlab. This pre-computed data and other internal thermal loads are used for scheduling in air conditioners. Energy savings obtained for the whole year are about 4% to 6% by simulation and the field study, respectively.

热控制制度强化再生A356铝合金性能研究

文章考察了废铝制品制备再生A356铝合金过程中精炼除杂脱气、冷却制度及热处理条件对再生铝合金组织结构及力学性能的影响,研选了提升再生A356铝合金力学性能的关键工艺参数,结果表明:通过投加自制Ti-C_(2)Cl_(6)精炼剂,再生铝合金浇注后立即室温水淬骤冷,以及固溶+时效的热处理等步骤,可实现脱气除杂、晶粒细化和抑制β-Fe相生成目的,所得铸态再生A356铝合金抗拉强度由201 MPa大幅度提升至277 MPa,将有助于推动汽车用再生铝技术的高质量发展。

基于云计算的船舶冷却泵变频智能控制技术

研究基于云计算的船舶冷却泵变频智能控制技术,解决船舶航行过程中冷却泵产能过剩的问题。选取PLC控制芯片控制数据采集模块,利用温度传感器,采集冷却泵进水口与出水口的水温,将所采集温度结果通过串口通信协议,传送至云计算平台;云计算平台的云端服务器接收用户上传的冷却泵温度数据后,依据资源分配的任务调度算法,为用户分配最佳的云计算资源,变频控制模块依据冷却泵温度采集结果,通过PID控制器实现船舶冷却泵的变频智能控制。实验结果表明,该技术可以实现冷却泵的变频智能控制,不同工况下冷却泵的热负荷降低幅度较大,节能效果明显。

冷却调度参数对模拟退火算法性能的影响分析

通过模拟仿真实验,研究了不同冷却调度参数对模拟退火算法性能的影响。结果表明:在5种不同的冷却调度下,不同的降温参数对算法的收敛效果存在差异。其中,线性冷却的降温速率呈等速率直线下降,并不能很好地控制收敛速率;指数冷却的冷却速率对降温参数的变化敏感,参数越小,冷却速率越快;逆冷却降温参数过大或过小均不利于算法的收敛效果;对数冷却和逆线性冷却在最初的迭代过程中,冷却速率较快,随后冷却速率变得极为缓慢,算法的收敛性较差。

基于热湿负荷与自适应预测时域微网优化调度

为了提升建筑冷热电联供(CCHP)微网灵活性并减少负荷波动,开展建筑湿负荷参与日前需求响应的效果和日内预测时域的自适应调节方法研究.在日前阶段,构建包含建筑湿负荷的冷负荷需求响应模型;在日内阶段,提出基于预测负荷方差的自适应预测时域模型预测控制(MPC)方法.在日前阶段,分析分时电价下包含湿负荷的冷负荷需求响应对总经济成本和蓄能水罐蓄冷量的影响;在日内阶段,分析采用自适应预测时域MPC方法对计算时间、成本和各类设备工作状态的影响.结果表明,考虑湿负荷的冷负荷需求响应降低了日前阶段成本7.75%;在日内阶段,自适应预测时域MPC方法不仅能够平衡计算时间和成本,还能够增加蓄能量和平滑燃气内燃机出力.

建筑用不锈钢减振复合板冷却工艺制度研究及C弯板形优化

使用酒钢自产的0.26 mm 304不锈钢和0.9 mm镀锌板,利用引进新型复合材料生产线开发1.2 mm不锈钢减振复合板,研究了10种冷却方式对C弯板形的影响规律。研究结果表明:在镀锌板加热温度为260℃、不锈钢板加热温度为125℃,产线速度6 m/min的条件下,最佳的冷却工艺为全开1、2、3区上层水且关闭1、2、3区下层水;通过降低基板的冷却强度和提高复板的冷却强度可有效改善C弯;上层冷却强度越大,下层的冷却强度越小,形成的C弯越小;上层1区水开关对不锈钢减振复合板板形C弯的影响最大。

融合需求侧虚拟储能系统的冷热电联供楼宇微网优化调度方法

提出一种融合需求侧虚拟储能系统的冷热电联供楼宇微网优化调度方法。首先基于楼宇蓄热特性,构建了一种虚拟储能系统模型。进而,将虚拟储能系统集成到楼宇微网优化调度模型中,通过在温度舒适度范围内对楼宇室温进行优化调节,实现对楼宇虚拟储能系统的充放电管理。最后以夏季制冷场景为例,对两种典型楼宇微网算例进行经济优化调度分析。结果表明,所提融合需求侧虚拟储能系统的冷热电联供楼宇微网优化调度方法可以在保证温度舒适度的前提下充分发掘楼宇参与微网经济优化运行的虚拟储能潜力,可在一定程度上降低微网运行成本。

热槽法模拟退火分析及其改进

本文在Rothman[1]提出的热槽法的基础上，对剩余静校正的估计进行了大量模型试验。通过分析研究得出了对热槽法冷却进度表构造的一些指导性原则，并引进了回火退火的思想来改过热槽法的收敛性及抗噪声能力。试验表明这种回火退火算法其效果是令人鼓舞的，对目前低信噪比的地震资料剩余静校正的估计是很有实际价值的。

南钢板坯三角区裂纹的成因及分析

针对南钢连铸板坯出现三角区裂纹的现状,通过低倍和硫印结果得出三角区裂纹的具体位置和类型,根据南钢当前的二冷配水情况,分析三角区裂纹产生的原因并提出二冷制度的改进方案。改进后三角区裂纹产生的比率下降至2.33%。

邻域退火粒子群算法在配电网重构中的应用

为求解多目标非线性整数组合优化的配电网络重构问题,建立了以电压均衡指数和网损为目标的配电网重构数学模型。为了克服粒子群算法容易局部收敛的不足,提出了一种基于正态分布的局优邻域闭锁方法的退火技术的粒子群算法(LA-PSO),改进了扰动机制,设计了自适应退火策略,对邻域内的粒子执行并行化退火操作,从而弥补粒子群算法爬山能力的不足,提高了算法的全局寻优能力。用3个不同规模的算例测试提出的算法并与基本算法的性能进行了比较。结果表明,该算法有效改进了粒子群优化算法的局部收敛问题,与单一算法相比,在收敛特性、全局寻优能力和稳定性等方面都有所提高。