CN113313301A - Photovoltaic power generation power ultra-short term prediction result combination optimization method and system - Google Patents

Photovoltaic power generation power ultra-short term prediction result combination optimization method and system Download PDF

Info

Publication number
CN113313301A
CN113313301A CN202110572661.1A CN202110572661A CN113313301A CN 113313301 A CN113313301 A CN 113313301A CN 202110572661 A CN202110572661 A CN 202110572661A CN 113313301 A CN113313301 A CN 113313301A
Authority
CN
China
Prior art keywords
moment
ultra
power
generated power
prediction
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
CN202110572661.1A
Other languages
Chinese (zh)
Inventor
王铮
王勃
王伟胜
冯双磊
刘纯
赵艳青
姜文玲
裴岩
车建峰
张菲
汪步惟
王钊
靳双龙
胡菊
宋宗朋
王姝
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.)
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
State Grid Shanghai Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
State Grid Shanghai Electric Power 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 State Grid Corp of China SGCC, China Electric Power Research Institute Co Ltd CEPRI, State Grid Shanghai Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202110572661.1A priority Critical patent/CN113313301A/en
Publication of CN113313301A publication Critical patent/CN113313301A/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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

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

Abstract

本发明提供了一种光伏发电功率超短期预测结果组合优化方法和系统，包括：采集光伏电站当前时刻的发电功率、预测时刻的发电功率超短期预测结果和上一预设周期的同一预测时刻的实际发电功率；基于所述采集光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率，利用预先建立组合优化模型对预测时刻的发电功率超短期预测结果进行优化；本发明能够有效提高光伏超短期预测结果的精度，支撑发电计划日内实时调整，从而在保障系统安全的前提下，提高新能源消纳能力。

Figure 202110572661

The invention provides a combined optimization method and system for ultra-short-term prediction results of photovoltaic power generation, including: collecting the generated power of the photovoltaic power station at the current moment, the ultra-short-term prediction result of the generated power at the predicted moment, and the ultra-short-term prediction results of the same prediction moment in the previous preset cycle. Actual power generation; based on the collected photovoltaic power station's current power at the current moment and the actual power generation at the same forecast moment in the previous preset period, use a pre-established combined optimization model to optimize the ultra-short-term forecast result of the power generation at the forecast moment; this The invention can effectively improve the accuracy of photovoltaic ultra-short-term forecast results, support the real-time adjustment of the power generation plan within the day, thereby improving the new energy consumption capacity under the premise of ensuring system security.

Figure 202110572661

Description

一种光伏发电功率超短期预测结果组合优化方法和系统A combined optimization method and system for ultra-short-term prediction results of photovoltaic power generation power

技术领域technical field

本发明属于新能源并网运行技术领域，尤其是涉及一种光伏发电功率超短期预测结果组合优化方法和系统。The invention belongs to the technical field of new energy grid-connected operation, and in particular relates to a combined optimization method and system of photovoltaic power generation power ultra-short-term prediction results.

背景技术Background technique

光伏超短期功率预测是光伏调控运行的基础之一，对日内发电计划实时调整具有重要的支撑作用。随着电力市场化改革进程的推进，光伏超短期功率高精度预测的作用将进一步凸显。由于辐照强度的周期性变化以及云层的随机干扰，无惯量光伏发电系统的输出功率波动剧烈，引入实时云观测数据是提高光伏输出功率超短期预测精度的有效手段之一，但受云层移动轨迹的评估偏差以及云层的生消、变形等影响，仅依赖物理模型的光伏超短期预测结果仍存在误差较大的问题，不能支撑电网调控运行最大限度的挖掘新能源消纳空间。Photovoltaic ultra-short-term power prediction is one of the foundations of photovoltaic regulation and operation, and plays an important supporting role in real-time adjustment of intraday power generation plans. With the advancement of the reform process of electricity marketization, the role of photovoltaic ultra-short-term power high-precision prediction will be further highlighted. Due to the periodic changes of radiation intensity and the random interference of clouds, the output power of inertia-free photovoltaic power generation systems fluctuates violently. Introducing real-time cloud observation data is one of the effective means to improve the ultra-short-term prediction accuracy of photovoltaic output power. There is still a problem of large error in the ultra-short-term prediction results of photovoltaics that only rely on physical models, and cannot support grid regulation and operation to maximize new energy consumption space.

发明内容SUMMARY OF THE INVENTION

为克服上述现有技术的不足，本发明提出一种光伏发电功率超短期预测结果组合优化方法，包括：In order to overcome the above-mentioned deficiencies of the prior art, the present invention proposes a combined optimization method for ultra-short-term prediction results of photovoltaic power generation, including:

采集光伏电站当前时刻的发电功率、预测时刻的发电功率超短期预测结果和上一预设周期的同一预测时刻的实际发电功率；Collect the generated power of the photovoltaic power station at the current moment, the ultra-short-term forecast result of the generated power at the forecast moment, and the actual generated power at the same forecast moment of the previous preset period;

基于所述采集光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率，利用预先建立组合优化模型对预测时刻的发电功率超短期预测结果进行优化；Based on the collection of the generated power at the current moment of the photovoltaic power station and the actual generated power at the same predicted moment in the previous preset period, using a pre-established combined optimization model to optimize the ultra-short-term prediction result of the generated power at the predicted moment;

其中，所述组合优化模型包括分别以光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率对发电功率超短期预测结果分别进行优化，然后组合两次优化结果。Wherein, the combined optimization model includes separately optimizing the ultra-short-term prediction results of the generated power with the generated power of the photovoltaic power station at the current moment and the actual generated power at the same forecast moment in the previous preset period, and then combining the two optimization results.

优选的，所述组合优化模型，包括：持续算法模型、周期优化模型以及对所述持续算法模型、周期优化模型的结果进行组合；Preferably, the combined optimization model includes: a continuous algorithm model, a cycle optimization model, and a combination of the results of the continuous algorithm model and the cycle optimization model;

其中，所述持续算法模型包括以持续计算得到的当前预测时间尺度下的持续系数为权重，对所述光伏电站当前时刻的发电功率和预测时刻的发电功率超短期预测结果进行拟合得到持续算法功率超短期预测结果；Wherein, the continuous algorithm model includes using the continuous calculation of the continuous coefficient under the current prediction time scale as the weight, and fitting the generated power of the photovoltaic power station at the current moment and the ultra-short-term prediction result of the generated power at the predicted moment to obtain the continuous algorithm Power ultra-short-term prediction results;

所述周期优化模型包括以持续计算得到的当前预测时间尺度下的融合系数为权重，对所述光伏电站上一预设周期的同一预测时刻的实际发电功率和预测时刻的发电功率超短期预测结果进行拟合得到周期优化功率超短期预测结果。The cycle optimization model includes using the fusion coefficient under the current prediction time scale obtained by continuous calculation as the weight, and the ultra-short-term prediction results of the actual power generation at the same prediction time and the power generation power at the prediction time in the previous preset cycle of the photovoltaic power station. Fitting is performed to obtain the ultra-short-term prediction results of cycle-optimized power.

优选的，所述持续算法模型包括如下计算式：Preferably, the continuous algorithm model includes the following calculation formula:

Figure BDA0003083294240000021
Figure BDA0003083294240000021

式中，k为预测时刻的时间尺度；t表示当前时刻；

Figure BDA0003083294240000022
为第t+k时刻的持续算法功率超短期预测结果；pSCADA,t为t时刻的实时发电功率；
Figure BDA0003083294240000023
为第t+k时刻的发电功率超短期预测结果；αk为第k预测时间尺度下的持续系数。In the formula, k is the time scale of the predicted moment; t is the current moment;
Figure BDA0003083294240000022
is the ultra-short-term prediction result of continuous algorithm power at time t+k; p SCADA,t is the real-time power generation at time t;
Figure BDA0003083294240000023
is the ultra-short-term prediction result of power generation at time t+k; α k is the persistence coefficient at the kth prediction time scale.

优选的，所述第k预测时间尺度下的持续系数αk的计算式如下：Preferably, the calculation formula of the persistence coefficient α k under the kth prediction time scale is as follows:

Figure BDA0003083294240000024
Figure BDA0003083294240000024

式中，ε为调整系数。In the formula, ε is the adjustment coefficient.

优选的，所述周期优化模型包括如下计算式：Preferably, the cycle optimization model includes the following calculation formula:

Figure BDA0003083294240000025
Figure BDA0003083294240000025

式中，k为预测时刻的时间尺度；t表示当前时刻；

Figure BDA0003083294240000026
为第t+k时刻的周期优化功率超短期预测结果；β为融合系数；pday-ahead,t+k为上一预设周期的第t+k时刻的实际发电功率；
Figure BDA0003083294240000027
为第t+k时刻的发电功率超短期预测结果。In the formula, k is the time scale of the predicted moment; t is the current moment;
Figure BDA0003083294240000026
is the ultra-short-term prediction result of the cycle optimized power at time t+k; β is the fusion coefficient; p day-ahead,t+k is the actual power generation at time t+k in the previous preset cycle;
Figure BDA0003083294240000027
is the ultra-short-term prediction result of power generation at time t+k.

优选的，所述融合系数是以历史预测时刻的历史发电功率的实际值与预测时刻的周期优化功率超短期预测结果间误差最小为目标进行寻优得到的。Preferably, the fusion coefficient is obtained by performing optimization with the goal of minimizing the error between the actual value of the historical generated power at the historical prediction time and the ultra-short-term prediction result of the periodic optimized power at the prediction time.

优选的，对所述持续算法模型、周期优化模型的结果按下式进行组合：Preferably, the results of the continuous algorithm model and the periodic optimization model are combined as follows:

Figure BDA0003083294240000028
Figure BDA0003083294240000028

其中，k为预测时刻的时间尺度；t表示当前时刻；

Figure BDA0003083294240000029
为第t+k时刻组合优化结果；pSCADA,t为第t时刻实际功率；
Figure BDA00030832942400000210
为第t+k时刻的持续算法功率超短期预测结果；
Figure BDA00030832942400000211
为第t+k时刻的周期优化功率超短期预测结果；
Figure BDA00030832942400000212
为上一次组合优化结果预测的当前时刻的发电功率；γ为组合系数。Among them, k is the time scale of the predicted moment; t is the current moment;
Figure BDA0003083294240000029
is the combined optimization result at time t+k; p SCADA,t is the actual power at time t;
Figure BDA00030832942400000210
is the ultra-short-term prediction result of continuous algorithm power at time t+k;
Figure BDA00030832942400000211
Optimize ultra-short-term prediction results of power for the period at time t+k;
Figure BDA00030832942400000212
The generated power at the current moment predicted for the last combined optimization result; γ is the combination coefficient.

优选的，所述组合系数是以历史预测时刻的历史发电功率的实际值与预测时刻组合优化结果间误差最小为目标进行寻优得到的。Preferably, the combination coefficient is obtained by performing optimization with the goal of minimizing the error between the actual value of the historical power generation power at the historical prediction time and the combined optimization result at the prediction time.

优选的，所述持续算法模型包括以持续计算得到的当前预测时间尺度下的持续系数为权重，对所述光伏电站当前时刻的发电功率和预测时刻的发电功率超短期预测结果进行拟合得到持续算法功率超短期预测结果之后，且在所述周期优化模型包括以持续计算得到的当前预测时间尺度下的融合系数为权重，对所述光伏电站上一预设周期的同一预测时刻的实际发电功率和预测时刻的发电功率超短期预测结果进行拟合得到周期优化功率超短期预测结果之前，还包括：Preferably, the continuation algorithm model includes using the continuation coefficient under the current prediction time scale obtained by continuous calculation as the weight, and fitting the ultra-short-term prediction result of the generated power of the photovoltaic power station at the current moment and the generated power at the predicted moment to obtain the continuation coefficient. After the ultra-short-term prediction result of the algorithm power, and the cycle optimization model includes taking the fusion coefficient under the current prediction time scale obtained by continuous calculation as the weight, the actual generated power of the photovoltaic power station at the same prediction moment in the previous preset cycle is calculated. Before fitting the ultra-short-term forecast results of power generation at the forecast moment to obtain the ultra-short-term forecast results of cycle-optimized power, it also includes:

在日出和日落的预设时段采用净空模型计算净空辐照强度；Use the headroom model to calculate the headroom irradiance at preset time periods of sunrise and sunset;

将所述净空辐照强度转化为光伏电站的输出功率，并将所述输出功率作为当预测时刻在日出和日落的预设时段时，预测时刻的持续算法功率超短期预测结果。The headroom irradiance intensity is converted into the output power of the photovoltaic power station, and the output power is used as the ultra-short-term prediction result of the continuous algorithm power at the predicted time when the predicted time is within the preset time period of sunrise and sunset.

基于同一发明构思，本发明还提供了一种光伏发电功率超短期预测结果组合优化系统，包括：采集模块和优化模块；Based on the same inventive concept, the present invention also provides a photovoltaic power generation power ultra-short-term forecast result combined optimization system, including: a collection module and an optimization module;

所述采集模块，用于采集光伏电站当前时刻的发电功率、预测时刻的发电功率超短期预测结果和上一预设周期的同一预测时刻的实际发电功率；The collection module is used to collect the generated power of the photovoltaic power station at the current moment, the ultra-short-term prediction result of the generated power at the predicted moment, and the actual generated power at the same predicted moment of the previous preset period;

所述优化模块，用于基于所述采集光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率，利用预先建立组合优化模型对预测时刻的发电功率超短期预测结果进行优化；The optimization module is configured to use a pre-established combined optimization model to perform an ultra-short-term prediction result of the generated power at the predicted time based on the collected photovoltaic power generation power at the current moment and the actual generated power at the same predicted time in the previous preset period. optimization;

其中，所述组合优化模型包括分别以光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率对发电功率超短期预测结果分别进行优化，然后组合两次优化结果。Wherein, the combined optimization model includes separately optimizing the ultra-short-term prediction results of the generated power with the generated power of the photovoltaic power station at the current moment and the actual generated power at the same forecast moment in the previous preset period, and then combining the two optimization results.

与最接近的现有技术相比，本发明具有的有益效果如下：Compared with the closest prior art, the present invention has the following beneficial effects:

本发明实现了一种光伏发电功率超短期预测结果组合优化方法和系统，包括：采集光伏电站当前时刻的发电功率、预测时刻的发电功率超短期预测结果和上一预设周期的同一预测时刻的实际发电功率；基于所述采集光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率，利用预先建立组合优化模型对预测时刻的发电功率超短期预测结果进行优化；其中，所述组合优化模型包括分别以光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率对发电功率超短期预测结果分别进行优化，然后组合两次优化结果；本发明能够有效提高光伏超短期预测结果的精度，支撑发电计划日内实时调整，从而在保障系统安全的前提下，提高新能源消纳能力。The invention realizes a combined optimization method and system for ultra-short-term prediction results of photovoltaic power generation, including: collecting the generated power of the photovoltaic power station at the current moment, the ultra-short-term prediction result of the generated power at the predicted moment, and the ultra-short-term prediction results of the same prediction moment in the previous preset cycle. Actual generated power; based on the collected photovoltaic power station's generated power at the current moment and the actual generated power at the same predicted moment of the previous preset period, using a pre-established combined optimization model to optimize the ultra-short-term forecast result of the generated power at the predicted moment; wherein , the combined optimization model includes separately optimizing the ultra-short-term prediction results of the generated power with the generated power of the photovoltaic power station at the current moment and the actual generated power at the same predicted moment in the previous preset period, and then combining the two optimization results; the present invention It can effectively improve the accuracy of photovoltaic ultra-short-term forecast results, support real-time adjustment of power generation plans within a day, and improve new energy consumption capacity on the premise of ensuring system security.

附图说明Description of drawings

图1为本发明提供的一种光伏发电功率超短期预测结果组合优化方法流程示意图；1 is a schematic flowchart of a combined optimization method for ultra-short-term prediction results of photovoltaic power generation provided by the present invention;

图2为本发明提供的一种光伏发电功率超短期预测结果组合优化系统结构示意图。FIG. 2 is a schematic structural diagram of a combined optimization system for ultra-short-term prediction results of photovoltaic power generation provided by the present invention.

具体实施方式Detailed ways

为了使本发明的目的、技术方案及优点更加清楚明白，以下结合实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

实施例1：Example 1:

下面结合附图及具体实施例对本发明的应用原理作进一步描述。The application principle of the present invention will be further described below with reference to the accompanying drawings and specific embodiments.

如图1所示，本发明实施例的一种光伏发电功率超短期预测结果组合优化方法，如图1所示，包括：As shown in FIG. 1 , a method for combining optimization of ultra-short-term forecast results of photovoltaic power generation according to an embodiment of the present invention, as shown in FIG. 1 , includes:

步骤1：采集光伏电站当前时刻的发电功率、预测时刻的发电功率超短期预测结果和上一预设周期的同一预测时刻的实际发电功率；Step 1: collect the generated power of the photovoltaic power station at the current moment, the ultra-short-term prediction result of the generated power at the predicted moment, and the actual generated power at the same predicted moment of the previous preset period;

步骤2：基于所述采集光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率，利用预先建立组合优化模型对预测时刻的发电功率超短期预测结果进行优化；Step 2: Based on the collected generated power of the photovoltaic power station at the current moment and the actual generated power at the same predicted moment of the previous preset period, using a pre-established combined optimization model to optimize the ultra-short-term prediction result of the generated power at the predicted moment;

其中，所述组合优化模型包括分别以光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率对发电功率超短期预测结果分别进行优化，然后组合两次优化结果。Wherein, the combined optimization model includes separately optimizing the ultra-short-term prediction results of the generated power with the generated power of the photovoltaic power station at the current moment and the actual generated power at the same forecast moment in the previous preset period, and then combining the two optimization results.

其中，步骤2具体包括：Wherein, step 2 specifically includes:

(1)组合优化模型(1) Combination optimization model

以持续算法模型和周期优化模型的输出结果作为输入，通过实时调整系数对持续算法模型和周期优化模型的组合结果进行修正，具体方法如下：Taking the output results of the continuous algorithm model and the periodic optimization model as the input, the combined results of the continuous algorithm model and the periodic optimization model are corrected through the real-time adjustment coefficient. The specific methods are as follows:

Figure BDA0003083294240000041
Figure BDA0003083294240000041

式中，

Figure BDA0003083294240000042
为第t+k时刻组合优化结果；pSCADA,t为第t时刻实际功率；
Figure BDA0003083294240000043
为第t+k时刻的持续算法功率超短期预测结果；
Figure BDA0003083294240000044
为第t+k时刻的周期优化功率超短期预测结果；
Figure BDA0003083294240000045
为上一次组合优化结果的第一个值；γ为组合系数，以组合优化结果的误差最优为目标，通过寻优获得(即通过历史预测时刻的历史实际值与修正后的预测结果间误差最小获得)。In the formula,
Figure BDA0003083294240000042
is the combined optimization result at time t+k; p SCADA,t is the actual power at time t;
Figure BDA0003083294240000043
is the ultra-short-term prediction result of continuous algorithm power at time t+k;
Figure BDA0003083294240000044
Optimize ultra-short-term prediction results of power for the period at time t+k;
Figure BDA0003083294240000045
is the first value of the last combined optimization result; γ is the combination coefficient, aiming at the optimal error of the combined optimization result, obtained through optimization (that is, the error between the historical actual value at the historical forecast time and the revised forecast result) minimum gain).

持续算法模型的输出结果的计算方法如下：The output of the continuous algorithm model is calculated as follows:

(2)持续算法模型(2) Continuous algorithm model

(2-1)以光伏电站的实时发电功率作为输入，采用持续算法，对光伏电站超短期功率预测结果进行优化，方法如下：(2-1) Using the real-time power generation power of the photovoltaic power station as the input, the continuous algorithm is used to optimize the ultra-short-term power prediction results of the photovoltaic power station. The method is as follows:

Figure BDA0003083294240000046
Figure BDA0003083294240000046

其中，in,

Figure BDA0003083294240000051
Figure BDA0003083294240000051

式中，

Figure BDA0003083294240000052
为第t+k时刻修正后的超短期预测结果(第t+k时刻的持续算法功率超短期预测结果)；pSCADA,t为t时刻的实际发电功率；
Figure BDA0003083294240000053
为第t+k时刻优化前的超短期预测结果(第t+k时刻的发电功率超短期预测结果)；t表示当前时刻；αk为第k预测时间尺度下的持续系数；ε为调整系数，取值范围基本在0.1至3之间，最优取值可通过随机最优化方法获得；k为预测时刻的时间尺度，取整数，根据相关行业标准，我国当前的超短期预测时间尺度为4小时，数据分辨率为15分钟，因此k的取值在1到16之间。In the formula,
Figure BDA0003083294240000052
is the revised ultra-short-term prediction result at time t+k (the ultra-short-term prediction result of continuous algorithm power at time t+k); p SCADA,t is the actual power generated at time t;
Figure BDA0003083294240000053
is the ultra-short-term prediction result before optimization at time t+k (the ultra-short-term prediction result of power generation at time t+k); t represents the current time; α k is the persistence coefficient under the k-th prediction time scale; ε is the adjustment coefficient , the value range is basically between 0.1 and 3, and the optimal value can be obtained by the stochastic optimization method; k is the time scale of the forecast moment, which is an integer. According to relevant industry standards, the current ultra-short-term forecast time scale in China is 4 hours, the data resolution is 15 minutes, so the value of k is between 1 and 16.

(2-2)上述模型中，日出和日落时段会引入误差，因此采用净空模型进行修正，净空条件下，辐照强度为：(2-2) In the above model, errors will be introduced during sunrise and sunset, so the headroom model is used for correction. Under the headroom condition, the irradiance intensity is:

Figure BDA0003083294240000054
Figure BDA0003083294240000054

其中，in,

Figure BDA0003083294240000055
Figure BDA0003083294240000055

Figure BDA0003083294240000056
Figure BDA0003083294240000056

式中，Iclear为净空辐照强度，w/m2；ISC为太阳常数，ISC＝1367W/m2；q为空间质量系数，一般取0.7；Γ为第N日的日角；αs为太阳高度角，具有固定的计算方法，此处不再累述。In the formula, I clear is the clearance radiation intensity, w/m 2 ; I SC is the solar constant, I SC =1367W/m 2 ; q is the space quality coefficient, generally taken as 0.7; Γ is the solar angle on the Nth day; α s is the altitude angle of the sun, which has a fixed calculation method, and will not be repeated here.

采用光伏发电系统物理模型，将净空辐照强度转化为输出功率pclear：Using the physical model of the photovoltaic power generation system, the headroom radiation intensity is converted into the output power p clear :

pclear＝f(Iclear) (6)p clear =f(I clear ) (6)

利用日出后4小时以内的净空出力和日落前4小时以内的净空出力对异常的优化结果进行修正。Use the headroom output within 4 hours after sunrise and the headroom output within 4 hours before sunset to correct the abnormal optimization results.

周期优化模型的输出结果的计算方法如下：The output of the cycle optimization model is calculated as follows:

(3)周期优化模型(3) Cycle optimization model

以前一日对应时刻的实际发电功率作为输入，采用持续算法(滚动形式的计算)对光伏电站超短期功率预测结果进行修正，方法如下：The actual generated power at the corresponding moment of the previous day is used as the input, and the continuous algorithm (calculation in the form of rolling) is used to correct the ultra-short-term power prediction result of the photovoltaic power station. The method is as follows:

Figure BDA0003083294240000057
Figure BDA0003083294240000057

式中，

Figure BDA0003083294240000061
为第t+k时刻修正后的超短期预测结果(第t+k时刻的周期优化功率超短期预测结果)；k为预测时刻的时间尺度；t表示当前时刻；β为融合系数，可以修正后的误差最小为目标，通过寻优获得(即通过历史预测时刻的历史实际值与修正后的预测结果间误差最小获得)；pday-ahead,t+k为前一日(上一预设周期)第t+k时刻的实际发电功率；
Figure BDA0003083294240000062
为第t+k时刻优化前的超短期预测结果。这里需要说明上一预设周期可能取前一日、前一星期和前一月等周期长度，本实施例采用前一日代表上一预设周期。In the formula,
Figure BDA0003083294240000061
is the corrected ultra-short-term prediction result at the t+kth time (the ultra-short-term prediction result of the cycle optimization power at the t+kth time); k is the time scale of the prediction time; t is the current time; β is the fusion coefficient, which can be corrected after The minimum error is the goal, which is obtained through optimization (that is, obtained through the minimum error between the historical actual value at the historical forecast moment and the revised forecast result); p day-ahead, t+k is the previous day (the previous preset period ) the actual generated power at time t+k;
Figure BDA0003083294240000062
It is the ultra-short-term prediction result before optimization at time t+k. It should be noted here that the previous preset period may be the previous day, the previous week, and the previous month, etc., and in this embodiment, the previous day is used to represent the previous preset period.

该方法可将不同类型的光伏电站发电功率超短期预测结果精度提升1-2个百分点。This method can improve the accuracy of ultra-short-term prediction results of power generation of different types of photovoltaic power plants by 1-2 percentage points.

实施例2：Example 2:

基于同一发明构思，本发明还提供了一种光伏发电功率超短期预测结果组合优化系统，由于这些系统解决技术问题的原理与一种光伏发电功率超短期预测结果组合优化方法相似，重复之处不再赘述。Based on the same inventive concept, the present invention also provides a combined optimization system for ultra-short-term forecast results of photovoltaic power generation. Since the principles of these systems for solving technical problems are similar to a method for combined optimization of ultra-short-term forecast results of photovoltaic power generation, the repetitions are not repeated. Repeat.

该系统，如图2所示，包括：采集模块和优化模块；The system, as shown in Figure 2, includes: an acquisition module and an optimization module;

所述采集模块，用于采集光伏电站当前时刻的发电功率、预测时刻的发电功率超短期预测结果和上一预设周期的同一预测时刻的实际发电功率；The collection module is used to collect the generated power of the photovoltaic power station at the current moment, the ultra-short-term prediction result of the generated power at the predicted moment, and the actual generated power at the same predicted moment of the previous preset period;

所述优化模块，用于基于所述采集光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率，利用预先建立组合优化模型对预测时刻的发电功率超短期预测结果进行优化；The optimization module is configured to use a pre-established combined optimization model to perform an ultra-short-term prediction result of the generated power at the predicted time based on the collected photovoltaic power generation power at the current moment and the actual generated power at the same predicted time in the previous preset period. optimization;

其中，所述组合优化模型包括分别以光伏电站当前时刻的发电功率和上一预设周期的同一预测时刻的实际发电功率对发电功率超短期预测结果分别进行优化，然后组合两次优化结果。Wherein, the combined optimization model includes separately optimizing the ultra-short-term prediction results of the generated power with the generated power of the photovoltaic power station at the current moment and the actual generated power at the same forecast moment in the previous preset period, and then combining the two optimization results.

本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

最后应当说明的是：以上实施例仅用于说明本发明的技术方案而非对其保护范围的限制，尽管参照上述实施例对本发明进行了详细的说明，所属领域的普通技术人员应当理解：本领域技术人员阅读本发明后依然可对发明的具体实施方式进行种种变更、修改或者等同替换，但这些变更、修改或者等同替换，均在发明待批的权利要求保护范围之内。Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit its protection scope. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: Those skilled in the art can still make various changes, modifications or equivalent replacements to the specific embodiments of the invention after reading the present invention, but these changes, modifications or equivalent replacements are all within the protection scope of the pending claims of the invention.

Claims (10)

1. A combined optimization method for a photovoltaic power generation power ultra-short term prediction result is characterized by comprising the following steps:
collecting the generated power of the photovoltaic power station at the current moment, the generated power ultra-short term prediction result at the prediction moment and the actual generated power at the same prediction moment in the previous preset period;
optimizing the generated power ultra-short-term prediction result at the prediction moment by utilizing a pre-established combined optimization model based on the acquired generated power of the photovoltaic power station at the current moment and the actual generated power at the same prediction moment in the previous preset period;
the combined optimization model comprises the steps of respectively optimizing the generated power ultra-short term prediction results according to the generated power of the photovoltaic power station at the current moment and the actual generated power of the photovoltaic power station at the same prediction moment in the previous preset period, and then combining the two optimization results.
2. The method of claim 1, wherein the combinatorial optimization model comprises: the method comprises the following steps of combining results of a continuous algorithm model and a periodic optimization model;
the continuous algorithm model comprises a continuous coefficient under the current prediction time scale obtained through continuous calculation as a weight, and the generated power of the photovoltaic power station at the current moment and the generated power ultra-short term prediction result at the prediction moment are fitted to obtain a continuous algorithm power ultra-short term prediction result;
the period optimization model comprises the step of fitting the actual generated power at the same prediction moment of a preset period of the photovoltaic power station and the generated power ultra-short term prediction result at the prediction moment by taking the fusion coefficient under the current prediction time scale obtained through continuous calculation as a weight to obtain a period optimization power ultra-short term prediction result.
3. The method of claim 2, wherein the continuous algorithm model comprises the following equation:
Figure FDA0003083294230000011
in the formula, k is the time scale of the prediction moment; t represents the current time;
Figure FDA0003083294230000012
the power ultra-short term prediction result of the continuous algorithm at the t + k moment is obtained; p is a radical ofSCADA,tThe real-time generated power at the moment t;
Figure FDA0003083294230000013
the generated power ultra-short term prediction result at the t + k moment is obtained; alpha is alphakThe persistence coefficient at the time scale is predicted for the kth.
4. The method according to claim 3, wherein the persistence coefficient α at the kth prediction time scalekIs calculated as follows:
Figure FDA0003083294230000014
wherein ε represents an adjustment coefficient.
5. The method of claim 2, wherein the period optimization model comprises the following calculation:
Figure FDA0003083294230000015
in the formula, k is the time scale of the prediction moment; t represents the current time;
Figure FDA0003083294230000021
optimizing a power ultra-short term prediction result for the period at the t + k moment; beta is a fusion coefficient; p is a radical ofday-ahead,t+kThe actual generated power at the t + k moment of the last preset period is obtained;
Figure FDA0003083294230000022
and the prediction result is the generated power ultra-short term prediction result at the t + k moment.
6. The method according to claim 2 or 5, wherein the fusion coefficient is obtained by optimizing with the aim of minimizing the error between the actual value of the historical generated power at the historical prediction time and the cycle optimization power ultra-short term prediction result at the prediction time.
7. The method of claim 2, wherein the results of the continuous algorithm model, the periodic optimization model are combined as follows:
Figure FDA0003083294230000023
wherein k is the time scale of the prediction moment; t represents the current time;
Figure FDA0003083294230000024
combining and optimizing results at the t + k th moment; p is a radical ofSCADA,tActual power at the t moment;
Figure FDA0003083294230000025
the power ultra-short term prediction result of the continuous algorithm at the t + k moment is obtained;
Figure FDA0003083294230000026
optimizing a power ultra-short term prediction result for the period at the t + k moment;
Figure FDA0003083294230000027
generating power at the current moment predicted by the last combined optimization result; and gamma is a combination coefficient.
8. The method according to claim 7, wherein the combination coefficient is optimized with a view to minimizing an error between an actual value of the historical generated power at the historical prediction time and a result of the combined optimization at the prediction time.
9. The method of claim 2, wherein the continuous algorithm model comprises a continuous coefficient under a current prediction time scale obtained by continuous calculation as a weight, after fitting the generated power at the current time of the photovoltaic power station and the generated power ultra-short term prediction result at the prediction time to obtain a continuous algorithm power ultra-short term prediction result, and the cycle optimization model comprises a fusion coefficient under the current prediction time scale obtained by continuous calculation as a weight, before fitting the actual generated power at the same prediction time of a preset cycle on the photovoltaic power station and the generated power ultra-short term prediction result at the prediction time to obtain a cycle optimization power ultra-short term prediction result, further comprising:
calculating clearance irradiation intensity by adopting a clearance model in preset time periods of sunrise and sunset;
and converting the clearance irradiation intensity into the output power of the photovoltaic power station, and taking the output power as a power ultra-short term prediction result of a continuous algorithm at the prediction moment when the prediction moment is in the preset time periods of sunrise and sunset.
10. A photovoltaic power generation power ultra-short term prediction result combination optimization system is characterized by comprising: the system comprises an acquisition module and an optimization module;
the acquisition module is used for acquiring the generated power of the photovoltaic power station at the current moment, the generated power ultra-short term prediction result at the prediction moment and the actual generated power at the same prediction moment in the previous preset period;
the optimization module is used for optimizing the ultra-short-term prediction result of the generated power at the prediction moment by utilizing a pre-established combined optimization model based on the collected generated power of the photovoltaic power station at the current moment and the actual generated power at the same prediction moment in the previous preset period;
the combined optimization model comprises the steps of respectively optimizing the generated power ultra-short term prediction results according to the generated power of the photovoltaic power station at the current moment and the actual generated power of the photovoltaic power station at the same prediction moment in the previous preset period, and then combining the two optimization results.
CN202110572661.1A 2021-05-25 2021-05-25 Photovoltaic power generation power ultra-short term prediction result combination optimization method and system Pending CN113313301A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110572661.1A CN113313301A (en) 2021-05-25 2021-05-25 Photovoltaic power generation power ultra-short term prediction result combination optimization method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110572661.1A CN113313301A (en) 2021-05-25 2021-05-25 Photovoltaic power generation power ultra-short term prediction result combination optimization method and system

Publications (1)

Publication Number Publication Date
CN113313301A true CN113313301A (en) 2021-08-27

Family

ID=77374709

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110572661.1A Pending CN113313301A (en) 2021-05-25 2021-05-25 Photovoltaic power generation power ultra-short term prediction result combination optimization method and system

Country Status (1)

Country Link
CN (1) CN113313301A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113922734A (en) * 2021-09-18 2022-01-11 南京南瑞继保电气有限公司 Light storage controller and light storage control method for reshaping external characteristics of photovoltaic power station
CN114256843A (en) * 2022-03-01 2022-03-29 中国电力科学研究院有限公司 Distributed photovoltaic radiation data correction method and device

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113922734A (en) * 2021-09-18 2022-01-11 南京南瑞继保电气有限公司 Light storage controller and light storage control method for reshaping external characteristics of photovoltaic power station
CN113922734B (en) * 2021-09-18 2023-12-29 南京南瑞继保电气有限公司 Light storage controller for remolding external characteristics of photovoltaic power station and light storage control method
CN114256843A (en) * 2022-03-01 2022-03-29 中国电力科学研究院有限公司 Distributed photovoltaic radiation data correction method and device
CN114256843B (en) * 2022-03-01 2022-07-08 中国电力科学研究院有限公司 Distributed photovoltaic radiation data correction method and device

Similar Documents

Publication Publication Date Title
CN107846040B (en) Coordinated planning method and system for distributed photovoltaics and energy storage based on second-order cone relaxation
CN103593577B (en) A kind of photovoltaic power generation system output power modeling and evaluation method
EP3026774B1 (en) Method for the control of power ramp-rates minimizing energy storage requirements in intermittent power generation plants
CN113313301A (en) Photovoltaic power generation power ultra-short term prediction result combination optimization method and system
TWI782049B (en) Method for controlling power ramps with prediction in intermittent power generation plants
CN109543323B (en) Method for detecting generating capacity of photovoltaic system based on time-by-time meteorological data
CN104268659A (en) Photovoltaic power station generated power super-short-term prediction method
CN104601104B (en) Ultra-short term photovoltaic prediction method with ARMA correction based on LSSVM
CN104318314A (en) Power generation capacity prediction method based on photovoltaic power generation efficiency
CN104111691A (en) Photovoltaic inverter MPPT control method based on three-point comparison method
CN109345046A (en) The prediction technique and device of photovoltaic power
CN105184399A (en) Power prediction method for photovoltaic power plant
CN108268963B (en) Self-correction-inspection photovoltaic power short-term prediction method
CN102281016A (en) Clear-sky photovoltaic super-short-term power forecast method based on real-time radiation acquisition technology
CN105389744A (en) Method for evaluating photovoltaic capacity credit based on load day and night peak difference constraint
CN108493999B (en) Method and system for evaluating complementarity of wind and light resources in region
CN110571862A (en) A method and system for time sequence matching degree analysis between photovoltaic power station and power load
CN104239979B (en) A kind of wind power plant generated output ultra-short term prediction method
CN114492084A (en) Photovoltaic power station generation hour number estimation model based on capacity-proportion comparison and selection
CN110098623A (en) A kind of Prosumer unit control method based on intelligent load
CN105610199A (en) Method and device for determining wind-solar ratio considering grid constraints
Recioui et al. Hybrid renewable energy system optimization using iHOGA
El-Azab et al. Optimal solar plant site selection
CN112561234A (en) Quantification method and system for on-site limited electric quantity and off-site limited electric quantity
CN110555220B (en) Calibration method and system of photoelectric conversion model

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