CN112381397A - Real-time energy control method for building by comprehensive energy - Google Patents

Real-time energy control method for building by comprehensive energy Download PDF

Info

Publication number
CN112381397A
CN112381397A CN202011270642.5A CN202011270642A CN112381397A CN 112381397 A CN112381397 A CN 112381397A CN 202011270642 A CN202011270642 A CN 202011270642A CN 112381397 A CN112381397 A CN 112381397A
Authority
CN
China
Prior art keywords
time
energy
building
power
value function
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011270642.5A
Other languages
Chinese (zh)
Inventor
程维杰
程韧俐
史军
刘金生
陈择栖
余涛
李捷
何晓峰
周招鹤
黄双
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Power Supply Bureau Co Ltd
Original Assignee
Shenzhen Power Supply Bureau Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Power Supply Bureau Co Ltd filed Critical Shenzhen Power Supply Bureau Co Ltd
Priority to CN202011270642.5A priority Critical patent/CN112381397A/en
Publication of CN112381397A publication Critical patent/CN112381397A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06313—Resource planning in a project environment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/16—Real estate
    • G06Q50/163—Real estate management

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

本发明公开一种综合能源楼宇实时能量控制方法，包括：步骤S1，建立综合能源楼宇的经济调度模型，构建考虑不确定性因素的总成本期望最小的目标函数；步骤S2，根据贝尔曼最优性原理将多时段决策问题转化为递推问题，并构造值函数的近似形式；步骤S3，基于逐次投影近似法对构造的值函数进行训练，得到收敛的近似值函数；步骤S4，将收敛的近似值函数投入在线运行，逐时段求解综合能源楼宇的实时能量控制问题。本发明一方面实现综合能源楼宇内部多种能源的实时协调互补，提升调度收益；另一方面能有效应对多种不确定性因素对系统调度的影响，实现随机协同调度。

Figure 202011270642

The invention discloses a real-time energy control method for an integrated energy building, comprising: step S1, establishing an economic dispatch model for an integrated energy building, and constructing an objective function with the minimum expected total cost considering uncertain factors; step S2, according to the Bellman optimality The multi-period decision-making problem is transformed into a recursive problem according to the principle of stability, and the approximate form of the value function is constructed; step S3, the constructed value function is trained based on the successive projection approximation method, and the convergent approximate value function is obtained; step S4, the converged approximate value The function is put into online operation to solve the real-time energy control problem of the integrated energy building time by time. On the one hand, the invention realizes the real-time coordination and complementation of multiple energy sources in the integrated energy building, and improves the dispatching income;

Figure 202011270642

Description

一种综合能源楼宇实时能量控制方法A real-time energy control method for integrated energy buildings

技术领域technical field

本发明涉及电网运行与控制技术领域，尤其涉及一种综合能源楼宇实时能量控制方法。The invention relates to the technical field of power grid operation and control, in particular to a real-time energy control method for buildings with integrated energy.

背景技术Background technique

综合能源楼宇是综合能源系统的重要应用形式，以冷热电联供CCHP(CombinedCooling，Heating and Power)为关键技术，并结合先进的控制、通信和管理等手段，建成楼宇能量管理系统。大型商业楼宇的负荷已超过城市总负荷的30％，挖掘以综合能源楼宇为代表的电力负荷能量管理潜力，对于改进用电方式，实现科学用电具有重要的意义。The integrated energy building is an important application form of the integrated energy system. It takes CCHP (Combined Cooling, Heating and Power) as the key technology and combines advanced control, communication and management methods to build a building energy management system. The load of large commercial buildings has exceeded 30% of the total urban load. It is of great significance to tap the energy management potential of electric load represented by buildings with integrated energy to improve the way of electricity consumption and realize scientific electricity consumption.

发明内容SUMMARY OF THE INVENTION

本发明所要解决的技术问题在于，提出一种综合能源楼宇实时能量控制方法，以实现综合能源楼宇内部多种能源的实时协调互补，应对多种不确定性因素对系统调度的影响。The technical problem to be solved by the present invention is to propose a real-time energy control method for an integrated energy building, so as to realize the real-time coordination and complementation of multiple energy sources in the integrated energy building, and to cope with the influence of various uncertain factors on system scheduling.

为了解决上述技术问题，本发明提供一种综合能源楼宇实时能量控制方法，包括：In order to solve the above-mentioned technical problems, the present invention provides a real-time energy control method for buildings with integrated energy, comprising:

步骤S1，建立综合能源楼宇的经济调度模型，构建考虑不确定性因素的总成本期望最小的目标函数；Step S1, establishing an economic dispatch model of an integrated energy building, and constructing an objective function with a minimum expected total cost considering uncertain factors;

步骤S2，根据贝尔曼最优性原理将多时段决策问题转化为递推问题，并构造值函数的近似形式；Step S2, according to the Bellman optimality principle, the multi-period decision-making problem is transformed into a recursive problem, and an approximate form of the value function is constructed;

步骤S3，基于逐次投影近似法对构造的值函数进行训练，得到收敛的近似值函数；In step S3, the constructed value function is trained based on the successive projection approximation method to obtain a converged approximate value function;

步骤S4，将收敛的近似值函数投入在线运行，逐时段求解综合能源楼宇的实时能量控制问题。In step S4, the converged approximate value function is put into online operation, and the real-time energy control problem of the building with integrated energy is solved time by time.

进一步地，所述步骤S1建立的综合能源楼宇的经济调度模型的功率平衡约束如下：Further, the power balance constraints of the economic dispatch model of the comprehensive energy building established in the step S1 are as follows:

Figure BDA0002777592880000011
Figure BDA0002777592880000011

其中，

Figure BDA0002777592880000021
为t时刻配网向楼宇传输的有功功率，
Figure BDA0002777592880000022
为t时刻冷热电联供输出的电功率，
Figure BDA0002777592880000023
为t时刻储能系统的有功出力，放电为正，充电为负，
Figure BDA0002777592880000024
为t时刻楼宇的负荷，NESS为储能系统数量；in,
Figure BDA0002777592880000021
is the active power transmitted by the distribution network to the building at time t,
Figure BDA0002777592880000022
is the electrical power output by the combined cooling, heating and power supply at time t,
Figure BDA0002777592880000023
is the active power output of the energy storage system at time t, the discharge is positive and the charge is negative,
Figure BDA0002777592880000024
is the load of the building at time t, and N ESS is the number of energy storage systems;

储能系统约束如下：The energy storage system constraints are as follows:

Figure BDA0002777592880000025
Figure BDA0002777592880000025

Pi,t,min≤Pi,t≤Pi,t,max P i,t,min ≤P i,t ≤P i,t,max

Ei,t,min≤Ei,t≤Ei,t,max E i,t,min ≤E i,t ≤E i,t,max

其中，Ei,t为t时刻第i个储能系统的能量，Pi,t为t时刻第i个储能系统的功率，其大于0表示放电，小于0表示充电；Pi,t,max、Pi,t,min分别为功率的上限约束和下限约束，Ei,t,max、Ei,t,min分别为能量的上限约束和下限约束。Among them, E i,t is the energy of the i-th energy storage system at time t, and P i,t is the power of the i-th energy storage system at time t, which is greater than 0 means discharging, and less than 0 means charging; P i,t, max and P i,t,min are the upper and lower constraints of power, respectively, and E i,t,max and E i,t,min are the upper and lower constraints of energy, respectively.

进一步地，所述步骤S1建立的综合能源楼宇的经济调度模型包括热水负荷模型、室温调节负荷模型和冷热电联供模型。Further, the economic dispatch model of the integrated energy building established in the step S1 includes a hot water load model, a room temperature regulation load model and a combined cooling, heating and power supply model.

进一步地，热水负荷模型如下所示：Further, the hot water load model is as follows:

Figure BDA0002777592880000026
Figure BDA0002777592880000026

其中，V为水箱体积，Cw为水比热容，

Figure BDA0002777592880000027
为t时刻水箱的温度，
Figure BDA0002777592880000028
分别为t时刻注入的冷水的体积和温度，Δt表示时间间隔，
Figure BDA0002777592880000029
为t时刻的热功率，
Figure BDA00027775928800000210
分别为用户可接受的热水温度上下限；Among them, V is the volume of the water tank, C w is the specific heat capacity of water,
Figure BDA0002777592880000027
is the temperature of the water tank at time t,
Figure BDA0002777592880000028
are the volume and temperature of the cold water injected at time t, respectively, Δt represents the time interval,
Figure BDA0002777592880000029
is the thermal power at time t,
Figure BDA00027775928800000210
are the upper and lower limits of the hot water temperature acceptable to the user, respectively;

进一步地，室温调节负荷模型在楼宇制冷时采用下式表示：Further, the room temperature regulation load model is expressed by the following formula when the building is cooled:

Figure BDA00027775928800000211
Figure BDA00027775928800000211

在供暖时采用下式表示：The following formula is used for heating:

Figure BDA00027775928800000212
Figure BDA00027775928800000212

其中，Cair为空气比热容，

Figure BDA0002777592880000031
为t时刻室内的温度，
Figure BDA0002777592880000032
为t时刻室外的温度，R为房屋热阻，Δt表示时间间隔，
Figure BDA0002777592880000033
分别为制冷功率、制热功率；where C air is the specific heat capacity of air,
Figure BDA0002777592880000031
is the indoor temperature at time t,
Figure BDA0002777592880000032
is the outdoor temperature at time t, R is the thermal resistance of the house, Δt is the time interval,
Figure BDA0002777592880000033
are cooling power and heating power, respectively;

进一步地，冷热电联供模型的运行约束如下所示：Further, the operating constraints of the CCHP model are as follows:

Figure BDA0002777592880000034
Figure BDA0002777592880000034

其中，

Figure BDA0002777592880000035
分别为t时刻冷热电联供输出的热功率、电功率和天然气消耗量，ηe、ηh分别为冷热电联供系统产电和产热的效率，Qgas为天然气热值。in,
Figure BDA0002777592880000035
are the thermal power, electric power and natural gas consumption output by CCHP at time t, respectively, η e and η h are the electricity and heat generation efficiencies of the CCHP system, respectively, and Q gas is the calorific value of natural gas.

进一步地，所述目标函数为调度周期内的总成本期望值最小，如下式所示：Further, the objective function is that the expected value of the total cost in the scheduling period is the smallest, as shown in the following formula:

Figure BDA0002777592880000036
Figure BDA0002777592880000036

Figure BDA0002777592880000037
Figure BDA0002777592880000037

其中，Ct为t时刻的总成本，St为储能系统所处的状态，包括负荷功率

Figure BDA0002777592880000038
电价信息pDN；xt为决策变量，包括储能系统的充放电功率
Figure BDA0002777592880000039
冷热电联供输出的热功率
Figure BDA00027775928800000310
购电功率
Figure BDA00027775928800000311
wt为随机信息，包括室外温度的变化信息
Figure BDA00027775928800000312
电价的变化信息
Figure BDA00027775928800000313
T是调度总时段，
Figure BDA00027775928800000314
是t时刻的天然气成本，
Figure BDA00027775928800000315
是t时刻的网购电价格，
Figure BDA00027775928800000316
是t时刻温控负荷的不舒适成本，
Figure BDA00027775928800000317
是i个储能系统在t时刻的成本。Among them, C t is the total cost at time t, and S t is the state of the energy storage system, including the load power
Figure BDA0002777592880000038
Electricity price information p DN ; x t is a decision variable, including the charging and discharging power of the energy storage system
Figure BDA0002777592880000039
Thermal power output by CCHP
Figure BDA00027775928800000310
Purchased power
Figure BDA00027775928800000311
w t is random information, including the change of outdoor temperature
Figure BDA00027775928800000312
Electricity price change information
Figure BDA00027775928800000313
T is the total scheduling period,
Figure BDA00027775928800000314
is the natural gas cost at time t,
Figure BDA00027775928800000315
is the online purchase price of electricity at time t,
Figure BDA00027775928800000316
is the discomfort cost of the temperature control load at time t,
Figure BDA00027775928800000317
is the cost of i energy storage systems at time t.

进一步地，所述步骤S2具体包括：Further, the step S2 specifically includes:

将所述目标函数转化为下式：The objective function is transformed into the following formula:

Vt(St)＝min(Ct(St,xt,wt)+ξE(Vt+1(St+1|St)))V t (S t )=min(C t (S t ,x t ,w t )+ξE(V t+1 (S t+1 |S t )))

其中，Vt(St)为储能系统在St状态的值函数，Vt+1(St+1|St)为储能系统在St状态的前提下，t+1时刻的值函数，ξ为折算因子；Among them, V t (S t ) is the value function of the energy storage system in the state of S t , and V t+1 (S t+1 | S t ) is the value function of the energy storage system at the time of t+1 under the premise that the energy storage system is in the state of S t value function, ξ is the conversion factor;

用分段线性法构造近似值函数如下：The approximate value function is constructed using the piecewise linear method as follows:

Figure BDA0002777592880000041
Figure BDA0002777592880000041

同时须满足下式：At the same time, the following formula must be satisfied:

Figure BDA0002777592880000042
Figure BDA0002777592880000042

其中，n代表迭代次数，β代表总段数，r表示第r段，ρ为每段的长度，ytr为每段的资源量。Among them, n represents the number of iterations, β represents the total number of segments, r represents the rth segment, ρ is the length of each segment, and y tr is the resource amount of each segment.

进一步地，所述步骤S3采用SPAR法求取近似值函数，包括：Further, the step S3 adopts the SPAR method to obtain the approximate value function, including:

步骤S31，初始化

Figure BDA0002777592880000043
利用蒙特卡罗法生成N个训练样本，每个训练样本中包含综合能源楼宇中一天内各种随机量的变化情况，令迭代次数n＝1，t＝1；Step S31, initialize
Figure BDA0002777592880000043
Use Monte Carlo method to generate N training samples, each training sample contains the changes of various random quantities in the integrated energy building in one day, let the number of iterations n=1, t=1;

步骤S32，根据最新的随机变量更新系统状态，并利用上一次迭代后的各分段斜率

Figure BDA0002777592880000044
求解步骤S2构造的近似值函数，求得各决策变量
Figure BDA0002777592880000045
决策后的系统状态
Figure BDA0002777592880000046
决策后的可调容量
Figure BDA0002777592880000047
Step S32, update the system state according to the latest random variable, and use the slope of each segment after the last iteration
Figure BDA0002777592880000044
Solve the approximate value function constructed in step S2 to obtain each decision variable
Figure BDA0002777592880000045
System state after decision
Figure BDA0002777592880000046
Adjustable capacity after decision
Figure BDA0002777592880000047

步骤S33，由更新样本计算斜率的临时值：In step S33, the temporary value of the slope is calculated from the updated sample:

Figure BDA0002777592880000048
Figure BDA0002777592880000048

其中，g为临时向量，a为步长，

Figure BDA0002777592880000049
为边际收益，
Figure BDA00027775928800000410
为近似斜率；Among them, g is the temporary vector, a is the step size,
Figure BDA0002777592880000049
is the marginal revenue,
Figure BDA00027775928800000410
is the approximate slope;

步骤S34，对临时向量做投影运算，得到第n次迭代的近似斜率分量：Step S34, perform a projection operation on the temporary vector to obtain the approximate slope component of the nth iteration:

Figure BDA0002777592880000051
Figure BDA0002777592880000051

步骤S35，t＝t+1，返回步骤S32，当t>T时转到步骤S36；Step S35, t=t+1, return to step S32, and go to step S36 when t>T;

步骤S36，令n＝n+1，并令t＝1，返回步骤S32，当n>N时循环终止。Step S36, let n=n+1, and let t=1, return to step S32, when n>N, the loop is terminated.

进一步地，所述步骤S4具体包括：Further, the step S4 specifically includes:

步骤S41，令t＝1；Step S41, let t=1;

步骤S42，更新当前时段的随机信息，包括电价的误差、室外温度的误差；Step S42, update the random information of the current period, including the error of the electricity price and the error of the outdoor temperature;

步骤S43，利用训练好的近似值函数，根据步骤S2构造的近似值函数计算出t时段最优决策；Step S43, using the trained approximation value function, according to the approximation value function constructed in step S2 to calculate the optimal decision in the t period;

步骤S44，令t＝t+1，若t≤T，返回步骤S42，若t>T，循环终止。Step S44, set t=t+1, if t≤T, return to step S42, and if t>T, the loop is terminated.

本发明实施例的有益效果在于：一方面实现综合能源楼宇内部多种能源的实时协调互补，提升调度收益；另一方面能有效应对多种不确定性因素对系统调度的影响，实现随机协同调度。The beneficial effects of the embodiments of the present invention are: on the one hand, the real-time coordination and complementation of multiple energy sources in the integrated energy building can be realized, and the dispatching benefit can be improved; .

附图说明Description of drawings

为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative efforts.

图1为本发明实施例一种综合能源楼宇实时能量控制方法的流程示意图。FIG. 1 is a schematic flowchart of a real-time energy control method for an integrated energy building according to an embodiment of the present invention.

具体实施方式Detailed ways

以下各实施例的说明是参考附图，用以示例本发明可以用以实施的特定实施例。The following descriptions of the various embodiments refer to the accompanying drawings to illustrate specific embodiments in which the invention may be practiced.

请参照图1所示，本发明实施例提供一种综合能源楼宇实时能量控制方法，包括：Referring to FIG. 1, an embodiment of the present invention provides a real-time energy control method for a building with integrated energy, including:

步骤S1，建立综合能源楼宇的经济调度模型，构建考虑不确定性因素的总成本期望最小的目标函数；Step S1, establishing an economic dispatch model of an integrated energy building, and constructing an objective function with a minimum expected total cost considering uncertain factors;

步骤S2，根据贝尔曼最优性原理将多时段决策问题转化为递推问题，并构造值函数的近似形式；Step S2, according to the Bellman optimality principle, the multi-period decision-making problem is transformed into a recursive problem, and an approximate form of the value function is constructed;

步骤S3，基于逐次投影近似法对构造的值函数进行训练，得到收敛的近似值函数；In step S3, the constructed value function is trained based on the successive projection approximation method to obtain a converged approximate value function;

步骤S4，将收敛的近似值函数投入在线运行，逐时段求解综合能源楼宇的实时能量控制问题。In step S4, the converged approximate value function is put into online operation, and the real-time energy control problem of the building with integrated energy is solved time by time.

进一步地，所述步骤S1包括以下步骤：Further, the step S1 includes the following steps:

建立综合能源楼宇的经济调度模型，其中，功率平衡约束如下：Establish an economic dispatch model for integrated energy buildings, where the power balance constraints are as follows:

Figure BDA0002777592880000061
Figure BDA0002777592880000061

其中，

Figure BDA0002777592880000062
为t时刻配网向楼宇传输的有功功率，
Figure BDA0002777592880000063
为t时刻冷热电联供输出的电功率，
Figure BDA0002777592880000064
为t时刻储能系统的有功出力，放电为正，充电为负，
Figure BDA0002777592880000065
为t时刻楼宇的负荷，NESS为储能系统数量。in,
Figure BDA0002777592880000062
is the active power transmitted by the distribution network to the building at time t,
Figure BDA0002777592880000063
is the electrical power output by the combined cooling, heating and power supply at time t,
Figure BDA0002777592880000064
is the active power output of the energy storage system at time t, the discharge is positive and the charge is negative,
Figure BDA0002777592880000065
is the load of the building at time t, and N ESS is the number of energy storage systems.

储能系统约束如下：The energy storage system constraints are as follows:

Figure BDA0002777592880000066
Figure BDA0002777592880000066

Pi,t,min≤Pi,t≤Pi,t,max (3)P i,t,min ≤P i,t ≤P i,t,max (3)

Ei,t,min≤Ei,t≤Ei,t,max (4)E i,t,min ≤E i,t ≤E i,t,max (4)

其中，Ei,t为t时刻第i个储能系统的能量，Pi,t为t时刻第i个储能系统的功率，大于0表示放电，小于0表示充电；公式(3)和公式(4)分别为能量和功率的上下限约束。Among them, E i,t is the energy of the i-th energy storage system at time t, P i,t is the power of the i-th energy storage system at time t, greater than 0 means discharge, and less than 0 means charging; formula (3) and formula (4) are the upper and lower limits of energy and power, respectively.

热水负荷模型：假设水箱一直处于满水状态，忽略水流的动态过程，则水箱的数学模型可用公式(5)表示：Hot water load model: Assuming that the water tank is always full of water, ignoring the dynamic process of water flow, the mathematical model of the water tank can be expressed by formula (5):

Figure BDA0002777592880000067
Figure BDA0002777592880000067

其中，V为水箱体积，Cw为水比热容，

Figure BDA0002777592880000071
为t时刻水箱的温度，
Figure BDA0002777592880000072
分别为t时刻注入的冷水的体积和温度，Δt表示时间间隔，
Figure BDA0002777592880000073
为t时刻的热功率，
Figure BDA0002777592880000074
分别为用户可接受的热水温度上下限。Among them, V is the volume of the water tank, C w is the specific heat capacity of water,
Figure BDA0002777592880000071
is the temperature of the water tank at time t,
Figure BDA0002777592880000072
are the volume and temperature of the cold water injected at time t, respectively, Δt represents the time interval,
Figure BDA0002777592880000073
is the thermal power at time t,
Figure BDA0002777592880000074
They are the upper and lower limits of the hot water temperature acceptable to the user, respectively.

室温调节负荷模型：楼宇在制冷时可用公式(6)的离散化数学模型表示，在供暖时可用公式(7)的数学模型表示，Room temperature regulation load model: the building can be represented by the discrete mathematical model of formula (6) during cooling, and can be represented by the mathematical model of formula (7) during heating.

Figure BDA0002777592880000075
Figure BDA0002777592880000075

Figure BDA0002777592880000076
Figure BDA0002777592880000076

其中，Cair为空气比热容，

Figure BDA0002777592880000077
为t时刻室内的温度，
Figure BDA0002777592880000078
为t时刻室外的温度，R为房屋热阻，Δt表示时间间隔，
Figure BDA0002777592880000079
分别为制冷功率、制热功率。where C air is the specific heat capacity of air,
Figure BDA0002777592880000077
is the indoor temperature at time t,
Figure BDA0002777592880000078
is the outdoor temperature at time t, R is the thermal resistance of the house, Δt is the time interval,
Figure BDA0002777592880000079
are cooling power and heating power, respectively.

冷热电联供模型：冷热电联供系统包括发电装置、余热回收装置、制冷系统，其运行约束如下：Combined cooling, heating and power model: The combined cooling, heating and power system includes a power generation device, a waste heat recovery device, and a refrigeration system. The operating constraints are as follows:

Figure BDA00027775928800000710
Figure BDA00027775928800000710

其中，

Figure BDA00027775928800000711
分别为t时刻冷热电联供输出的热功率、电功率和天然气消耗量，ηe、ηh分别为冷热电联供系统产电和产热的效率，Qgas为天然气热值。in,
Figure BDA00027775928800000711
are the thermal power, electric power and natural gas consumption output by CCHP at time t, respectively, η e and η h are the electricity and heat generation efficiencies of the CCHP system, respectively, and Q gas is the calorific value of natural gas.

综合能源楼宇运营商以能量管理的总成本最低为目标，包括燃料成本即购气成本和购电成本，温控负荷的不舒适成本，储能系统的运行成本，如下式所示：Integrated energy building operators aim to minimize the total cost of energy management, including fuel costs, namely gas and electricity purchase costs, discomfort costs of temperature-controlled loads, and operating costs of energy storage systems, as shown in the following formula:

Figure BDA00027775928800000712
Figure BDA00027775928800000712

Figure BDA0002777592880000081
Figure BDA0002777592880000081

其中，T是调度总时段；

Figure BDA0002777592880000082
是t时刻的天然气成本；pgas是天然气价格；
Figure BDA0002777592880000083
是t时刻的网购电价格；
Figure BDA0002777592880000084
是配网向楼宇传输的有功功率，pDN是t时刻的电价；
Figure BDA0002777592880000085
是t时刻温控负荷的不舒适成本；pindoor和pwt分别是室内温度和热水温度的敏感系数；Tindoorset和Twtset分别为用户设定的室内温度和热水温度的值；
Figure BDA0002777592880000086
是第i个储能系统在t时刻的成本；pESS是储能系统运行成本系数。Among them, T is the total scheduling period;
Figure BDA0002777592880000082
is the cost of natural gas at time t; p gas is the price of natural gas;
Figure BDA0002777592880000083
is the online purchase price at time t;
Figure BDA0002777592880000084
is the active power transmitted by the distribution network to the building, and p DN is the electricity price at time t;
Figure BDA0002777592880000085
is the discomfort cost of the temperature control load at time t; p indoor and p wt are the sensitivity coefficients of indoor temperature and hot water temperature, respectively; T indoorset and T wtset are the values of indoor temperature and hot water temperature set by the user;
Figure BDA0002777592880000086
is the cost of the ith energy storage system at time t; p ESS is the operating cost coefficient of the energy storage system.

考虑到实时能量管理中，电价、室外温度等的不确定性，目标函数应为调度周期内(本发明实施例设为一天)的总成本期望值最小，如下式所示：Considering the uncertainty of electricity price, outdoor temperature, etc. in real-time energy management, the objective function should be the minimum expected value of total cost in the scheduling period (set as one day in the embodiment of the present invention), as shown in the following formula:

Figure BDA0002777592880000087
Figure BDA0002777592880000087

Figure BDA0002777592880000088
Figure BDA0002777592880000088

其中，Ct为t时刻的总成本，St为储能系统所处的状态，包括负荷功率

Figure BDA0002777592880000089
电价信息pDN；xt为决策变量，包括储能系统的充放电功率
Figure BDA00027775928800000810
冷热电联供输出的热功率
Figure BDA00027775928800000811
购电功率
Figure BDA00027775928800000812
wt为随机信息，包括室外温度的变化信息
Figure BDA00027775928800000813
电价的变化信息
Figure BDA00027775928800000814
Among them, C t is the total cost at time t, and S t is the state of the energy storage system, including the load power
Figure BDA0002777592880000089
Electricity price information p DN ; x t is a decision variable, including the charging and discharging power of the energy storage system
Figure BDA00027775928800000810
Thermal power output by CCHP
Figure BDA00027775928800000811
Purchased power
Figure BDA00027775928800000812
w t is random information, including the change of outdoor temperature
Figure BDA00027775928800000813
Electricity price change information
Figure BDA00027775928800000814

进一步地，所述步骤S2包括以下步骤：Further, the step S2 includes the following steps:

根据贝尔曼最优性原理将多时段决策问题转化为递推问题，并构造值函数的近似形式，即将公式(11)转化成公式(13)：According to the Bellman optimality principle, the multi-period decision-making problem is transformed into a recursive problem, and an approximate form of the value function is constructed, that is, formula (11) is transformed into formula (13):

Vt(St)＝min(Ct(St,xt,wt)+ξE(Vt+1(St+1|St))) (13)V t (S t )=min(C t (S t ,x t ,w t )+ξE(V t+1 (S t+1 |S t ))) (13)

其中，Vt(St)为系统在St状态的值函数，Vt+1(St+1|St)为系统在St状态的前提下，t+1时刻的值函数，意义为当前决策对后续时段成本的影响，取期望值运算是随机变量Wt的存在，ξ为折算因子，一般取值在0～1内。Among them, V t (S t ) is the value function of the system in the state of S t , and V t+1 (S t+1 | S t ) is the value function of the system at the time of t+1 under the premise of the state of S t , meaning For the impact of the current decision on the cost of the subsequent period, the operation of taking the expected value is the existence of the random variable W t , and ξ is the conversion factor, which is generally within 0 to 1.

用分段线性法构造近似值函数，即有：The approximate value function is constructed by the piecewise linear method, that is:

Figure BDA0002777592880000091
Figure BDA0002777592880000091

同时须满足：At the same time, it must meet:

Figure BDA0002777592880000092
Figure BDA0002777592880000092

其中，n代表迭代次数，β代表总段数，r表示第r段，ρ为每段的长度，ytr为每段的资源量。Among them, n represents the number of iterations, β represents the total number of segments, r represents the rth segment, ρ is the length of each segment, and y tr is the resource amount of each segment.

进一步地，所述步骤S3包括以下步骤：Further, the step S3 includes the following steps:

采用SPAR法求取近似值函数的步骤如下：The steps to obtain the approximate value function using the SPAR method are as follows:

步骤S31，初始化

Figure BDA0002777592880000093
利用蒙特卡罗法生成N个训练样本，每个训练样本中包含综合能源楼宇中一天内各种随机量的变化情况。令迭代次数n＝1，t＝1；Step S31, initialize
Figure BDA0002777592880000093
The Monte Carlo method is used to generate N training samples, and each training sample contains the variation of various random quantities in a day in the integrated energy building. Let the number of iterations n=1, t=1;

步骤S32，根据最新的随机变量更新系统状态，并利用上一次迭代后的各分段斜率

Figure BDA0002777592880000094
求解公式(14)，求得各决策变量
Figure BDA0002777592880000095
决策后的系统状态
Figure BDA0002777592880000096
决策后的可调容量
Figure BDA0002777592880000097
等。Step S32, update the system state according to the latest random variable, and use the slope of each segment after the last iteration
Figure BDA0002777592880000094
Solve Equation (14) to obtain each decision variable
Figure BDA0002777592880000095
System state after decision
Figure BDA0002777592880000096
Adjustable capacity after decision
Figure BDA0002777592880000097
Wait.

步骤S33，由更新样本计算斜率的临时值：In step S33, the temporary value of the slope is calculated from the updated sample:

Figure BDA0002777592880000101
Figure BDA0002777592880000101

其中，g为临时向量，a为步长，

Figure BDA0002777592880000102
为边际收益，
Figure BDA0002777592880000103
为近似斜率。Among them, g is the temporary vector, a is the step size,
Figure BDA0002777592880000102
is the marginal revenue,
Figure BDA0002777592880000103
is the approximate slope.

步骤S34，对临时向量做投影运算，得到第n次迭代的近似斜率分量：Step S34, perform a projection operation on the temporary vector to obtain the approximate slope component of the nth iteration:

Figure BDA0002777592880000104
Figure BDA0002777592880000104

步骤S35，t＝t+1，返回步骤S32，当t>T时转到步骤S36；Step S35, t=t+1, return to step S32, and go to step S36 when t>T;

步骤S36，令n＝n+1，并令t＝1，返回步骤S32，当n>N时循环终止。Step S36, let n=n+1, and let t=1, return to step S32, when n>N, the loop is terminated.

进一步地，所述步骤S4包括以下步骤：Further, the step S4 includes the following steps:

步骤S41，令t＝1；Step S41, let t=1;

步骤S42，更新当前时段的随机信息，包括电价的误差、室外温度的误差等；Step S42, update the random information of the current period, including the error of the electricity price, the error of the outdoor temperature, etc.;

步骤S43，利用前述训练好的近似值函数，根据公式(14)计算出t时段最优决策；Step S43, using the aforementioned trained approximation function, according to formula (14) to calculate the optimal decision in the t period;

步骤S44，令t＝t+1，若t≤T，返回步骤S42，若t>T，循环终止。Step S44, set t=t+1, if t≤T, return to step S42, and if t>T, the loop is terminated.

通过上述说明可知，本发明实施例的有益效果在于：一方面实现综合能源楼宇内部多种能源的实时协调互补，提升调度收益；另一方面能有效应对多种不确定性因素对系统调度的影响，实现随机协同调度。It can be seen from the above description that the beneficial effects of the embodiments of the present invention are: on the one hand, the real-time coordination and complementation of multiple energy sources in the integrated energy building can be realized, and the dispatching benefit can be improved; , to achieve random cooperative scheduling.

以上所揭露的仅为本发明较佳实施例而已，当然不能以此来限定本发明之权利范围，因此依本发明权利要求所作的等同变化，仍属本发明所涵盖的范围。The above disclosures are only preferred embodiments of the present invention, and of course, the scope of the rights of the present invention cannot be limited by this. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims (10)

1.一种综合能源楼宇实时能量控制方法，其特征在于，包括：1. a comprehensive energy building real-time energy control method, is characterized in that, comprises: 步骤S1，建立综合能源楼宇的经济调度模型，构建考虑不确定性因素的总成本期望最小的目标函数；Step S1, establishing an economic dispatch model of an integrated energy building, and constructing an objective function with a minimum expected total cost considering uncertain factors; 步骤S2，根据贝尔曼最优性原理将多时段决策问题转化为递推问题，并构造值函数的近似形式；Step S2, according to the Bellman optimality principle, the multi-period decision-making problem is transformed into a recursive problem, and an approximate form of the value function is constructed; 步骤S3，基于逐次投影近似法对构造的值函数进行训练，得到收敛的近似值函数；In step S3, the constructed value function is trained based on the successive projection approximation method to obtain a converged approximate value function; 步骤S4，将收敛的近似值函数投入在线运行，逐时段求解综合能源楼宇的实时能量控制问题。In step S4, the converged approximate value function is put into online operation, and the real-time energy control problem of the building with integrated energy is solved time by time. 2.根据权利要求1所述的综合能源楼宇实时能量控制方法，其特征在于，所述步骤S1建立的综合能源楼宇的经济调度模型的功率平衡约束如下：2. comprehensive energy building real-time energy control method according to claim 1 is characterized in that, the power balance constraint of the economic dispatch model of the comprehensive energy building established by described step S1 is as follows:
Figure FDA0002777592870000011
Figure FDA0002777592870000011
 其中，
Figure FDA0002777592870000012
为t时刻配网向楼宇传输的有功功率，
Figure FDA0002777592870000013
为t时刻冷热电联供输出的电功率，
Figure FDA0002777592870000014
为t时刻储能系统的有功出力，放电为正，充电为负，
Figure FDA0002777592870000015
为t时刻楼宇的负荷，NESS为储能系统数量；in,
Figure FDA0002777592870000012
is the active power transmitted by the distribution network to the building at time t,
Figure FDA0002777592870000013
is the electrical power output by the combined cooling, heating and power supply at time t,
Figure FDA0002777592870000014
is the active power output of the energy storage system at time t, the discharge is positive and the charge is negative,
Figure FDA0002777592870000015
is the load of the building at time t, and N ESS is the number of energy storage systems; 储能系统约束如下：The energy storage system constraints are as follows:
Figure FDA0002777592870000016
Figure FDA0002777592870000016
 Pi,t,min≤Pi,t≤Pi,t,max P i,t,min ≤P i,t ≤P i,t,max Ei,t,min≤Ei,t≤Ei,t,max E i,t,min ≤E i,t ≤E i,t,max 其中，Ei,t为t时刻第i个储能系统的能量，Pi,t为t时刻第i个储能系统的功率，其大于0表示放电，小于0表示充电；Pi,t,max、Pi,t,min分别为功率的上限约束和下限约束，Ei,t,max、Ei,t,min分别为能量的上限约束和下限约束。Among them, E i,t is the energy of the i-th energy storage system at time t, and P i,t is the power of the i-th energy storage system at time t, which is greater than 0 means discharging, and less than 0 means charging; P i,t, max and P i,t,min are the upper and lower constraints of power, respectively, and E i,t,max and E i,t,min are the upper and lower constraints of energy, respectively. 3.根据权利要求2所述的综合能源楼宇实时能量控制方法，其特征在于，所述步骤S1建立的综合能源楼宇的经济调度模型包括热水负荷模型、室温调节负荷模型和冷热电联供模型。3. comprehensive energy building real-time energy control method according to claim 2 is characterized in that, the economic dispatch model of the comprehensive energy building established in described step S1 comprises hot water load model, room temperature regulation load model and combined cooling, heating and power supply Model. 4.根据权利要求3所述的综合能源楼宇实时能量控制方法，其特征在于，热水负荷模型如下所示：4. comprehensive energy building real-time energy control method according to claim 3, is characterized in that, hot water load model is as follows:
Figure FDA0002777592870000021
Figure FDA0002777592870000021
 其中，V为水箱体积，Cw为水比热容，
Figure FDA0002777592870000022
为t时刻水箱的温度，
Figure FDA0002777592870000023
分别为t时刻注入的冷水的体积和温度，Δt表示时间间隔，
Figure FDA0002777592870000024
为t时刻的热功率，
Figure FDA0002777592870000025
分别为用户可接受的热水温度上下限。Among them, V is the volume of the water tank, C w is the specific heat capacity of water,
Figure FDA0002777592870000022
is the temperature of the water tank at time t,
Figure FDA0002777592870000023
are the volume and temperature of the cold water injected at time t, respectively, Δt represents the time interval,
Figure FDA0002777592870000024
is the thermal power at time t,
Figure FDA0002777592870000025
They are the upper and lower limits of the hot water temperature acceptable to the user, respectively. 5.根据权利要求4所述的综合能源楼宇实时能量控制方法，其特征在于，室温调节负荷模型在楼宇制冷时采用下式表示：5. comprehensive energy building real-time energy control method according to claim 4, is characterized in that, room temperature regulation load model adopts following formula to express when building is refrigerated:
Figure FDA0002777592870000026
Figure FDA0002777592870000026
 在供暖时采用下式表示：The following formula is used for heating:
Figure FDA0002777592870000027
Figure FDA0002777592870000027
 其中，Cair为空气比热容，
Figure FDA0002777592870000028
为t时刻室内的温度，
Figure FDA0002777592870000029
为t时刻室外的温度，R为房屋热阻，Δt表示时间间隔，
Figure FDA00027775928700000210
分别为制冷功率、制热功率。where C air is the specific heat capacity of air,
Figure FDA0002777592870000028
is the indoor temperature at time t,
Figure FDA0002777592870000029
is the outdoor temperature at time t, R is the thermal resistance of the house, Δt is the time interval,
Figure FDA00027775928700000210
are cooling power and heating power, respectively. 6.根据权利要求5所述的综合能源楼宇实时能量控制方法，其特征在于，冷热电联供模型的运行约束如下所示：6. comprehensive energy building real-time energy control method according to claim 5, is characterized in that, the operation constraint of CCHP model is as follows:
Figure FDA00027775928700000211
Figure FDA00027775928700000211
 其中，
Figure FDA00027775928700000212
分别为t时刻冷热电联供输出的热功率、电功率和天然气消耗量，ηe、ηh分别为冷热电联供系统产电和产热的效率，Qgas为天然气热值。in,
Figure FDA00027775928700000212
are the thermal power, electric power and natural gas consumption output by CCHP at time t, respectively, η e and η h are the electricity and heat generation efficiencies of the CCHP system, respectively, and Q gas is the calorific value of natural gas. 7.根据权利要求1所述的综合能源楼宇实时能量控制方法，其特征在于，所述目标函数为调度周期内的总成本期望值最小，如下式所示：7. The comprehensive energy building real-time energy control method according to claim 1, wherein the objective function is that the expected value of the total cost in the scheduling period is minimum, as shown in the following formula:
Figure FDA0002777592870000031
Figure FDA0002777592870000031
Figure FDA0002777592870000032
Figure FDA0002777592870000032
 其中，Ct为t时刻的总成本，St为储能系统所处的状态，包括负荷功率
Figure FDA0002777592870000033
电价信息pDN；xt为决策变量，包括储能系统的充放电功率
Figure FDA0002777592870000034
冷热电联供输出的热功率
Figure FDA0002777592870000035
购电功率
Figure FDA0002777592870000036
wt为随机信息，包括室外温度的变化信息
Figure FDA0002777592870000037
电价的变化信息
Figure FDA0002777592870000038
T是调度总时段，
Figure FDA0002777592870000039
是t时刻的天然气成本，
Figure FDA00027775928700000310
是t时刻的网购电价格，
Figure FDA00027775928700000311
是t时刻温控负荷的不舒适成本，
Figure FDA00027775928700000312
是i个储能系统在t时刻的成本。Among them, C t is the total cost at time t, and S t is the state of the energy storage system, including the load power
Figure FDA0002777592870000033
Electricity price information p DN ; x t is a decision variable, including the charging and discharging power of the energy storage system
Figure FDA0002777592870000034
Thermal power output by CCHP
Figure FDA0002777592870000035
Purchased power
Figure FDA0002777592870000036
w t is random information, including the change of outdoor temperature
Figure FDA0002777592870000037
Electricity price change information
Figure FDA0002777592870000038
T is the total scheduling period,
Figure FDA0002777592870000039
is the natural gas cost at time t,
Figure FDA00027775928700000310
is the online purchase price of electricity at time t,
Figure FDA00027775928700000311
is the discomfort cost of the temperature control load at time t,
Figure FDA00027775928700000312
is the cost of i energy storage systems at time t. 8.根据权利要求7所述的综合能源楼宇实时能量控制方法，其特征在于，所述步骤S2具体包括：8. The real-time energy control method for buildings with integrated energy according to claim 7, wherein the step S2 specifically comprises: 将所述目标函数转化为下式：The objective function is transformed into the following formula: Vt(St)＝min(Ct(St,xt,wt)+ξE(Vt+1(St+1|St)))V t (S t )=min(C t (S t ,x t ,w t )+ξE(V t+1 (S t+1 |S t ))) 其中，Vt(St)为储能系统在St状态的值函数，Vt+1(St+1|St)为储能系统在St状态的前提下，t+1时刻的值函数，ξ为折算因子；Among them, V t (S t ) is the value function of the energy storage system in the state of S t , and V t+1 (S t+1 | S t ) is the value function of the energy storage system at the time of t+1 under the premise that the energy storage system is in the state of S t value function, ξ is the conversion factor; 用分段线性法构造近似值函数如下：The approximate value function is constructed using the piecewise linear method as follows:
Figure FDA00027775928700000313
Figure FDA00027775928700000313
 同时须满足下式：At the same time, the following formula must be satisfied:
Figure FDA0002777592870000041
Figure FDA0002777592870000041
 其中，n代表迭代次数，β代表总段数，r表示第r段，ρ为每段的长度，ytr为每段的资源量。Among them, n represents the number of iterations, β represents the total number of segments, r represents the rth segment, ρ is the length of each segment, and y tr is the resource amount of each segment. 9.根据权利要求8所述的综合能源楼宇实时能量控制方法，其特征在于，所述步骤S3采用SPAR法求取近似值函数，包括：9. comprehensive energy building real-time energy control method according to claim 8, is characterized in that, described step S3 adopts SPAR method to obtain approximate value function, comprises: 步骤S31，初始化
Figure FDA0002777592870000042
利用蒙特卡罗法生成N个训练样本，每个训练样本中包含综合能源楼宇中一天内各种随机量的变化情况，令迭代次数n＝1，t＝1；Step S31, initialize
Figure FDA0002777592870000042
Use Monte Carlo method to generate N training samples, each training sample contains the changes of various random quantities in the integrated energy building in one day, let the number of iterations n=1, t=1; 步骤S32，根据最新的随机变量更新系统状态，并利用上一次迭代后的各分段斜率
Figure FDA0002777592870000043
求解步骤S2构造的近似值函数，求得各决策变量
Figure FDA0002777592870000044
决策后的系统状态
Figure FDA0002777592870000045
决策后的可调容量
Figure FDA0002777592870000046
Step S32, update the system state according to the latest random variable, and use the slope of each segment after the last iteration
Figure FDA0002777592870000043
Solve the approximate value function constructed in step S2 to obtain each decision variable
Figure FDA0002777592870000044
System state after decision
Figure FDA0002777592870000045
Adjustable capacity after decision
Figure FDA0002777592870000046
 步骤S33，由更新样本计算斜率的临时值：In step S33, the temporary value of the slope is calculated from the updated sample:
Figure FDA0002777592870000047
Figure FDA0002777592870000047
 其中，g为临时向量，a为步长，
Figure FDA0002777592870000048
为边际收益，
Figure FDA0002777592870000049
为近似斜率；Among them, g is the temporary vector, a is the step size,
Figure FDA0002777592870000048
is the marginal revenue,
Figure FDA0002777592870000049
is the approximate slope; 步骤S34，对临时向量做投影运算，得到第n次迭代的近似斜率分量：Step S34, perform a projection operation on the temporary vector to obtain the approximate slope component of the nth iteration:
Figure FDA00027775928700000410
Figure FDA00027775928700000410
 步骤S35，t＝t+1，返回步骤S32，当t>T时转到步骤S36；Step S35, t=t+1, return to step S32, and go to step S36 when t>T; 步骤S36，令n＝n+1，并令t＝1，返回步骤S32，当n>N时循环终止。Step S36, let n=n+1, and let t=1, return to step S32, when n>N, the loop is terminated. 10.根据权利要求9所述的综合能源楼宇实时能量控制方法，其特征在于，所述步骤S4具体包括：10. The comprehensive energy building real-time energy control method according to claim 9, wherein the step S4 specifically comprises: 步骤S41，令t＝1；Step S41, let t=1; 步骤S42，更新当前时段的随机信息，包括电价的误差、室外温度的误差；Step S42, update the random information of the current period, including the error of the electricity price and the error of the outdoor temperature; 步骤S43，利用训练好的近似值函数，根据步骤S2构造的近似值函数计算出t时段最优决策；Step S43, using the trained approximation value function, according to the approximation value function constructed in step S2 to calculate the optimal decision in the t period; 步骤S44，令t＝t+1，若t≤T，返回步骤S42，若t>T，循环终止。Step S44, set t=t+1, if t≤T, return to step S42, and if t>T, the loop is terminated.
CN202011270642.5A 2020-11-13 2020-11-13 Real-time energy control method for building by comprehensive energy Pending CN112381397A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011270642.5A CN112381397A (en) 2020-11-13 2020-11-13 Real-time energy control method for building by comprehensive energy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011270642.5A CN112381397A (en) 2020-11-13 2020-11-13 Real-time energy control method for building by comprehensive energy

Publications (1)

Publication Number Publication Date
CN112381397A true CN112381397A (en) 2021-02-19

Family

ID=74582542

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011270642.5A Pending CN112381397A (en) 2020-11-13 2020-11-13 Real-time energy control method for building by comprehensive energy

Country Status (1)

Country Link
CN (1) CN112381397A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109712019A (en) * 2018-12-13 2019-05-03 深圳供电局有限公司 Real-time energy management optimization method for multifunctional building
CN110245878A (en) * 2019-06-27 2019-09-17 华翔翔能电气股份有限公司 The Distributed Integration energy demand of intelligent building group responds cooperative optimization method
CN110929964A (en) * 2019-12-18 2020-03-27 国网福建省电力有限公司 An optimal scheduling method for distribution network with energy storage based on approximate dynamic programming algorithm
CN111429038A (en) * 2020-04-25 2020-07-17 华南理工大学 Active power distribution network real-time random optimization scheduling method based on reinforcement learning

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109712019A (en) * 2018-12-13 2019-05-03 深圳供电局有限公司 Real-time energy management optimization method for multifunctional building
CN110245878A (en) * 2019-06-27 2019-09-17 华翔翔能电气股份有限公司 The Distributed Integration energy demand of intelligent building group responds cooperative optimization method
CN110929964A (en) * 2019-12-18 2020-03-27 国网福建省电力有限公司 An optimal scheduling method for distribution network with energy storage based on approximate dynamic programming algorithm
CN111429038A (en) * 2020-04-25 2020-07-17 华南理工大学 Active power distribution network real-time random optimization scheduling method based on reinforcement learning

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
刘翠平;林舜江;刘明波;简淦杨;陆文甜;: "应用近似动态规划算法求解安全约束随机动态经济调度问题", 电力系统自动化 *
卢艺;梁俊文;程韧俐;卢苑;林舜江;刘明波;: "考虑光伏和电动汽车不确定性的配电网鲁棒经济调度", 电工电能新技术 *
李捷;余涛;潘振宁;: "基于强化学习的增量配电网实时随机调度方法", 电网技术 *
简淦杨等: "随机动态经济调度问题的存储器建模及近似动态规划算法", 中国电机工程学报, vol. 34, no. 25, 5 September 2014 (2014-09-05), pages 4333 - 4340 *

Similar Documents

Publication Publication Date Title
CN109858759B (en) Industrial park comprehensive energy balance scheduling method
CN114611772B (en) A collaborative optimization method for multi-microgrid systems based on multi-agent reinforcement learning
JP2022550225A (en) Electric heat pump - regulation method and system for optimizing cogeneration systems
CN110689189A (en) Combined cooling heating and power supply and demand balance optimization scheduling method considering energy supply side and demand side
CN107732897B (en) Prediction and regulation method of building microgrid model integrating virtual energy storage system
CN109636056B (en) A decentralized optimization scheduling method for multi-energy microgrids based on multi-agent technology
CN115099725B (en) Energy management and distribution method and system for comprehensive energy system
CN107464008A (en) A kind of Optimization Scheduling of large buildings cooling heating and power generation system
CN106228258A (en) A kind of meter and the home energy source LAN energy optimal control method of dsm
CN110807588A (en) An optimal scheduling method for a multi-energy coupled integrated energy system
CN114330827B (en) Distributed robust self-scheduling optimization method for multi-energy flow virtual power plant and application thereof
CN116542370A (en) Park low-carbon economic operation method considering carbon capture and carbon transaction
CN111553544B (en) A Distributed Comprehensive Demand Response Method for Industrial Parks Based on Consensus Algorithm
CN116663820A (en) An Energy Management Method for Integrated Energy System under Demand Response
CN108133285A (en) A kind of energy mix system real-time scheduling method for accessing extensive regenerative resource
CN113902339B (en) A method and device for optimizing and dispatching a comprehensive energy system
CN114048908B (en) Multi-time scale reinforcement interval optimization method for unified power grid-distributed heat supply network system
CN110474370A (en) The cooperative control system and method for a kind of air-conditioning controllable burden, photovoltaic energy storage system
CN108879657A (en) Balance of electric power and ener optimization method based on wind-powered electricity generation volume metering
CN117172499A (en) A smart community energy optimization scheduling method, system and storage medium based on reinforcement learning
Liu et al. Two-stage scheduling strategy for integrated energy systems considering renewable energy consumption
CN111476394B (en) A robust operation optimization method suitable for multi-energy systems such as electric heating and gas
Liu Multiple time‐scale economic dispatching strategy for commercial building with virtual energy storage under demand response mechanism
CN115099590B (en) Active power distribution network economic optimization scheduling method and system considering light load uncertainty
CN112713590A (en) IDR (inverse discrete cosine transformation) -based combined cooling, heating and power supply micro-grid and active power distribution network joint optimization scheduling method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210219