CN115642617B - Scheduling method of photovoltaic energy storage system - Google Patents
Scheduling method of photovoltaic energy storage system Download PDFInfo
- Publication number
- CN115642617B CN115642617B CN202210938501.9A CN202210938501A CN115642617B CN 115642617 B CN115642617 B CN 115642617B CN 202210938501 A CN202210938501 A CN 202210938501A CN 115642617 B CN115642617 B CN 115642617B
- Authority
- CN
- China
- Prior art keywords
- sample
- benefit
- state information
- scheduling
- energy storage
- 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.)
- Active
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000008901 benefit Effects 0.000 claims abstract description 117
- 238000010606 normalization Methods 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000005611 electricity Effects 0.000 description 30
- 238000010248 power generation Methods 0.000 description 16
- 238000007599 discharging Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000007774 longterm Effects 0.000 description 3
- 238000011002 quantification Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of photovoltaic energy storage systems, in particular to a scheduling method of a photovoltaic energy storage system, which comprises the following steps: s1: acquiring current state information of a photovoltaic energy storage system and pre-acquired standard state information; s2: acquiring a plurality of corresponding standard state information according to the current state information, and judging the current state mode; s3: generating an optimal benefit index according to the state mode and a plurality of standard state information associated with the state mode; s4: and generating scheduling parameters for controlling the photovoltaic energy storage system according to the optimal benefit index. The invention has the beneficial effects that: the optimal benefit index which can be achieved by the photovoltaic energy storage system in the current state mode is obtained by combining the pre-acquired standard state information in the process of generating the scheduling parameters, and the scheduling parameters which accord with the current state mode are generated through the optimal benefit index and the current state information, so that the economic benefit maximization is realized, and the problem of extreme value output by the model is avoided.
Description
Technical Field
The invention relates to the technical field of photovoltaic energy storage systems, in particular to a scheduling method of a photovoltaic energy storage system.
Background
The photovoltaic energy storage system is an equipment system which is applied to a photovoltaic power generation system and can store, convert and release circulated electric energy through an electrochemical cell or an electromagnetic energy storage medium. Because the photovoltaic power generation system is greatly influenced by external factors such as weather, seasons and the like, the phenomenon of obvious power generation power fluctuation exists in the whole working period, and certain difficulty is brought to the dispatching of the power grid. Aiming at the problem, the peak regulation is carried out on the output electric energy of the photovoltaic power generation system through the energy storage system, so that the problems of electric discarding, insufficient power and the like of the photovoltaic power generation system can be effectively avoided. Especially to the industry park of some self-built photovoltaic power generation system, this kind of user is in industry park usually, through photovoltaic power generation system, photovoltaic energy storage system, external electric wire netting to and the consumer in the park, constitutes a local little electric wire netting, and it is supplied power through photovoltaic power generation system and external electric wire netting, dispatches the unnecessary electric energy that photovoltaic power generation system produced through photovoltaic energy storage system, inputs the consumer at the low valley of generating electricity.
In the prior art, there are technical schemes for scheduling for such scenes. For example, CN201811602550.5 discloses a method, an apparatus, a computer device and a storage medium for scheduling photovoltaic power, which are used for comparing photovoltaic power generation power, photovoltaic power consumption power, a first residual electric quantity, a first electricity price and a selling electricity price in sequence, so as to determine how to adjust charging power of a charging pile. For another example, CN201910619256.3 discloses a multi-energy storage battery operation model capable of realizing smooth photovoltaic output, which is constructed and solved for various parameters to be processed in the operation process of the energy storage battery, so as to obtain the charge and discharge power of the energy storage battery.
However, in the practical implementation process, the inventor finds that, because the above technical scheme simply compares a plurality of parameters collected on site through a plurality of judging conditions, and schedules according to the comparison result, the economic benefit generated by the scheduling instruction in the implementation process is relatively extensive. For example, in the above-mentioned scheme, "when the second electricity price is less than or equal to the electricity buying price, the photovoltaic charging power of the charging pile is reduced according to the photovoltaic power generation power and the photovoltaic power of the energy storage system in the current time period", which is only adjusted for the photovoltaic charging power at the current time, the maximization of the economic benefit cannot be achieved in the relatively long-term scheduling process of the photovoltaic energy storage system. For another example, the scheduling parameters are planned only through a single model, so that extreme values which do not meet the actual environmental conditions can be generated due to strong target guidance, and the photovoltaic energy storage system cannot be effectively controlled.
Disclosure of Invention
Aiming at the problems in the prior art, the scheduling method of the photovoltaic energy storage system is provided.
The specific technical scheme is as follows:
a method of scheduling a photovoltaic energy storage system, comprising:
step S1: acquiring current state information of the photovoltaic energy storage system and a plurality of different standard state information acquired in advance;
step S2: acquiring a plurality of corresponding standard state information according to the current state information, and judging the current state mode of the photovoltaic energy storage system;
step S3: generating an optimal benefit index corresponding to the state mode according to the state mode and a plurality of standard state information associated with the state mode;
step S4: and generating scheduling parameters for controlling the photovoltaic energy storage system according to the optimal benefit index.
Preferably, the current state information includes a plurality of state parameters, and the step S2 includes:
step S21: sequentially comparing a plurality of state parameters in the current state information according to a preset comparison rule, and generating corresponding prescheduling information according to a comparison result;
step S22: and determining the current state mode according to the pre-scheduling information and the standard state information.
Preferably, the step S22 includes:
step S221: generating a first sample distance of a sample point of the prescheduling information and a sample point of each of the standard state information respectively;
step S222: clustering the sample points according to the first sample distance to generate a plurality of sample classes;
step S223: respectively calculating second sample distances between every two sample classes, and clustering the sample classes according to the second sample distances;
step S224: and repeating the step S223 until the number of the clustered sample classes reaches a set class threshold, and outputting the sample class where the sample point of the prescheduling information is located as the state mode.
Preferably, the step S3 includes:
step S31: acquiring a plurality of standard state information in the state mode, and respectively calculating benefit indexes of each standard state information;
step S32: and generating the optimal benefit index in the state mode according to a plurality of the benefit indexes.
Preferably, in the step S31, the method for calculating the benefit index includes:
wherein ,Rhat As an index of the benefit to be used,
for the i-th hour of the upper grid power, < >>
For the i-th hour, internet power price, < >>
For the ith hour of lower grid power, +.>
The grid for the ith hour is powered up.
Preferably, in the step S32, the method for calculating the optimal benefit index includes:
wherein ,
r is the optimum benefit index k R is the number of all the standard state information in the state mode hat ∈top10％R k R is the standard state information with the benefit index of the first 10% in the state mode hat And the benefit index is the standard state information.
Preferably, the step S4 includes:
step S41: generating a sample to be predicted according to the pre-standard state information and the optimal benefit index, and generating a benefit sample according to the standard state information and the benefit index corresponding to the standard state information;
step S42: respectively calculating second sample distances between the sample points of the sample to be predicted and the sample points of each benefit sample;
step S43: generating a benefit sample set corresponding to the sample to be predicted according to the second sample distance;
step S44: and generating the scheduling parameters corresponding to the samples to be predicted according to the benefit sample set.
Preferably, before the step S42, normalization processing is further performed on all the state parameters in the sample to be predicted and the benefit sample, respectively;
wherein ,xnew For the normalized state parameter, X is the state parameter before normalization, max (X) is the maximum value of the state parameters in the same class, and min (X) is the minimum value of the state parameters in the same class.
Preferably, in the step S44, the method for generating the scheduling parameter according to the standard state information set includes:
wherein ,Pbat* K is the number of the benefit samples in the benefit sample set, P, for the scheduling parameter corresponding to the sample to be predicted bat S for the benefit samples in the benefit sample set g For the benefit sample set, P bat And scheduling parameters for the benefit samples.
The technical scheme has the following advantages or beneficial effects: the optimal benefit index which can be achieved by the photovoltaic energy storage system in the current state mode is obtained by combining the pre-acquired standard state information in the process of generating the scheduling parameters, and the scheduling parameters which accord with the current state mode are generated through the optimal benefit index and the current state information, so that the economic benefit maximization is realized, and the problem of extreme value output by the model is avoided.
Drawings
Embodiments of the present invention will now be described more fully with reference to the accompanying drawings. The drawings, however, are for illustration and description only and are not intended as a definition of the limits of the invention.
FIG. 1 is an overall schematic of an embodiment of the present invention;
FIG. 2 is a schematic diagram of a photovoltaic energy storage system according to an embodiment of the present invention;
FIG. 3 is a schematic diagram showing the sub-steps of step S2 in the embodiment of the invention;
FIG. 4a is a schematic diagram showing the substep of step S21 according to an embodiment of the present invention;
FIG. 4b is a schematic diagram showing the sub-steps of step S21 according to an embodiment of the present invention;
FIG. 5a is a schematic diagram showing the substep of step S21 according to another embodiment of the present invention;
FIG. 5b is a schematic diagram showing the substep of step S21 according to another embodiment of the present invention;
FIG. 6 is a schematic diagram showing the substep of step S22 in the embodiment of the invention;
FIG. 7 is a schematic diagram showing the sub-steps of step S3 in an embodiment of the present invention;
fig. 8 is a schematic diagram of the substep of step S4 in the embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
The invention is further described below with reference to the drawings and specific examples, which are not intended to be limiting.
The invention comprises the following steps:
a method for scheduling a photovoltaic energy storage system, as shown in fig. 1, includes:
step S1: acquiring current state information of a photovoltaic energy storage system and a plurality of different standard state information acquired in advance;
step S2: acquiring a plurality of corresponding standard state information according to the current state information, and judging the current state mode of the photovoltaic energy storage system;
step S3: generating an optimal benefit index corresponding to the state mode according to the state mode and a plurality of standard state information associated with the state mode;
step S4: and generating scheduling parameters for controlling the photovoltaic energy storage system according to the optimal benefit index.
Specifically, for the photovoltaic energy storage system in the prior art, when the photovoltaic energy storage system is scheduled, the corresponding scheduling instruction is simply judged according to a plurality of state parameters, and the problem that the economic benefit is difficult to maximize in the long-term operation process is solved. When the dispatching is started, the current state information at the current moment is obtained, clustering is carried out according to the current state information and the standard state information, so that the state mode of the micro-grid where the current photovoltaic energy storage system is located is obtained, the optimal benefit index under the state mode is generated, the dispatching parameter can be obtained according to the optimal benefit index regression, the photovoltaic energy storage system is controlled to carry out operations such as charging and discharging through the dispatching parameter, and the maximization of economic benefit is realized.
Further, in the embodiment, the state mode of the photovoltaic energy storage system in the current state information is judged by comparing the current state information with the standard state information before generating the optimal benefit index, so that the optimal benefit index which can be achieved by the photovoltaic energy storage system in the state mode is generated, and the problem that the scheduling parameter deviating from the actual condition is easy to output when the economic benefit maximization is simply set as the objective function in the prior art is avoided.
In the implementation process, the scheduling method is used as a software embodiment and is arranged in the photovoltaic energy storage system. As shown in fig. 2, the photovoltaic energy storage system 101 is disposed in a micro grid 102, where the micro grid 102 refers to a local micro grid including a photovoltaic power generation system 102 and a power consumption system 104, and the local micro grid is further connected to an external power grid 105, and is used for taking power from the external power grid 105 when a part of conditions, such as when the photovoltaic power generation power or the stored energy dispatching power is insufficient, is satisfied, and is used for transmitting power to the external power grid A5 when a specific condition is satisfied, so as to obtain the power charge for surfing the net. The current state information refers to state parameters collected from the photovoltaic energy storage system in real time, including the residual capacity SOC of the battery and the photovoltaic power P pv Load power P load External network electricity price C out Photovoltaic internet price C pv And the state parameters can characterize the current operation state of the photovoltaic energy storage system. The standard state information refers to historical scheduling data before the current starting scheduling, which is acquired through corresponding acquisition&The storage program is connected to the photovoltaic energy storage system and stores state parameters of different periods.
In a preferred embodiment, as shown in fig. 3, step S2 includes:
step S21: sequentially comparing a plurality of state parameters in the current state information according to a preset comparison rule, and generating corresponding prescheduling information according to a comparison result;
step S22: the current state mode is determined based on the prescheduling information and the standard state information.
Specifically, in the embodiment, after the pre-scheduling information is generated by comparing the state parameters, the pre-scheduling information is processed according to the pre-collected standard state information and the pre-scheduling information, so that the state mode of the current state information in the whole scheduling process is judged on the basis of the standard state information accumulated for a long time, and then the optimal benefit index corresponding to the current state mode can be generated according to different state modes in the subsequent judging process, so that the scheduling parameter obtained by the regression of the optimal benefit index is the scheduling parameter which can be realized in the state mode, and the problem that the model output deviates from the actual extreme value is avoided.
In the implementation process, the pre-scheduling information refers to pre-scheduling information corresponding to current state information generated by sequentially comparing the state parameter with a preset judging condition, and in this embodiment, the pre-scheduling information is only used for representing the current running state of the photovoltaic energy storage system and is not equal to a control instruction or a scheduling parameter actually used for the photovoltaic energy storage system. In general, as shown in table 1, both the standard state information and the prescheduling information have the following fields: battery remaining capacity SOC, photovoltaic power P pv Load power P load External network electricity price C out Photovoltaic internet price C pv Charging and discharging power p of energy storage battery bat Power p of upper electric network up Lower grid power p down . Wherein, the battery residual capacity SOC and the photovoltaic power P pv Load power P load External network electricity price C out Photovoltaic internet price C pv A field of the "run mode" category, which is derived from a state parameter received by the photovoltaic energy storage system at run time; charging and discharging power p of energy storage battery bat Power p of upper electric network up Lower grid power p down A field of the "control instructions" class, which is used to characterize the scheduling conditions of the photovoltaic energy storage system in a certain operating mode. Wherein, the charge and discharge power p of the energy storage battery bat Representing the charge and discharge power of the current photovoltaic energy storage system, wherein the field is a positive numberAnd when the field is negative, the photovoltaic energy storage system is in a charging state. It should be noted that the convention of signs is merely illustrative of one embodiment, and may be reversed according to actual needs.
TABLE 1
Based on the above parameters, we can collect several fixed parameters in advance, such as the maximum battery capacity soc_max, the minimum battery capacity soc_min, the maximum battery discharge power p_bat_out_max, the maximum battery charge power p_bat_in_max, and various judgment conditions, such as "whether the photovoltaic power per unit time is greater than the load power", "whether the remaining battery power per unit time is less than the maximum battery capacity"; whether the photovoltaic internet price is larger than the unit time external network electricity price or not; and (3) taking the difference value of the maximum charging power in the unit time of the battery which is larger than the photovoltaic power in the unit time and the load power as a comparison rule to perform step-by-step comparison, so as to judge the approximate running condition of the current micro-grid and generate corresponding scheduling parameters. The plurality of judgment conditions themselves do not have a strict execution order.
For example, in one embodiment, as shown in fig. 4a and 4b, in step S21, the process of generating the pre-scheduling information by the comparison rule includes:
step A21: judging whether the photovoltaic power in unit time is larger than the load power or not;
if yes, go to step A22
If not, go to step A25:
step A22: judging whether the residual electric quantity of the battery in unit time is smaller than the maximum capacity of the battery;
if yes, go to step a23:
if not, setting the scheduling parameter in the pre-scheduling information as 'selling electricity to an external power grid by the difference value of the photovoltaic power and the load power in unit time';
step A23: judging whether the photovoltaic internet price is larger than the unit time external network electricity price or not;
if yes, setting a scheduling parameter in the pre-scheduling information as 'selling electricity to an external power grid by using the difference value of the photovoltaic power and the load power in unit time';
if not, turning to step A24;
step A24: judging whether the maximum charging power in the unit time of the battery is larger than the difference value between the photovoltaic power and the load power in the unit time;
if yes, setting a scheduling parameter in the pre-scheduling information as 'charging a battery by a difference value between photovoltaic power and load power in unit time';
if not, setting the scheduling parameter in the pre-scheduling information as ' charging the battery with the maximum charging power in the unit time of the battery ', and selling electricity to an external power grid according to the residual power ';
step A25: judging whether the residual electric quantity of the battery in unit time is larger than the minimum capacity of the battery;
if yes, go to step a26;
if not, turning to step A29;
step A26: judging whether the photovoltaic internet price is larger than the unit time external network electricity price or not;
if yes, turning to step A27;
if not, turning to step A28;
step A27: judging whether the residual electric quantity of the battery in unit time is smaller than the maximum capacity of the battery;
if so, setting a scheduling parameter in the pre-scheduling information as ' charging the battery with the maximum charging power in unit time of the battery ', and simultaneously powering an external power grid according to the difference value of the load power and the photovoltaic power in unit time and the charging rate of the battery ';
if not, setting the scheduling parameters in the pre-scheduling information as 'power taking to an external power grid according to the difference value of the load power and the photovoltaic power in unit time';
step A28: judging whether the maximum discharge power of the battery in unit time is larger than the load power in unit time or not;
if yes, setting a scheduling parameter in the pre-scheduling information as 'discharging the battery with load power';
if not, setting the scheduling parameter in the pre-scheduling information as ' discharging the battery with the maximum discharging power ', and simultaneously taking electricity to an external power grid according to the difference value of the load power, the battery discharging power and the photovoltaic power generation power ';
step A29: judging whether the photovoltaic internet price is larger than the unit time external network electricity price or not;
if so, setting a scheduling parameter in the pre-scheduling information as ' charging the battery with the maximum charging power in unit time of the battery ', and simultaneously powering an external power grid according to the difference value of the load power and the photovoltaic power in unit time and the charging rate of the battery ';
if not, setting the scheduling parameter in the pre-scheduling information as 'electricity is taken to an external power grid according to the difference value of the load power and the photovoltaic power in unit time'.
Alternatively, in another embodiment, as shown in fig. 5a and 5b, in step S21, the process of generating the pre-scheduling information by the comparison rule includes:
step B20: judging whether the real-time electricity price of the external power grid is smaller than or equal to the real-time electricity price of the external power grid (the flat of peak Gu Ping);
if yes, turning to a step B21;
if not, go to step B24:
step B21: judging whether the residual electric quantity of the battery in unit time is smaller than the maximum capacity of the battery;
if yes, setting a scheduling parameter in the pre-scheduling information as 'charging the battery with the maximum charging power in the unit time of the battery';
if not, go to step B22:
step B22: judging whether the photovoltaic power in unit time is larger than the load power or not;
if yes, setting a scheduling parameter in the pre-scheduling information as 'selling electricity to an external power grid by using the difference value of the photovoltaic power and the load power in unit time';
if not, turning to the step B23;
step B23: judging whether the maximum discharge power in the unit time of the battery is smaller than the difference value between the load power and the photovoltaic power in the unit time;
if yes, setting a scheduling parameter in the pre-scheduling information as ' discharging the battery with maximum discharging power ', and simultaneously taking electricity to an external power grid according to the difference value of the load power, the battery discharging power and the photovoltaic power generation power ';
if not, setting the scheduling parameter in the pre-scheduling information as 'the battery discharges with the difference value of the load power and the photovoltaic power in unit time';
step B24: judging whether the photovoltaic power in unit time is larger than the load power or not;
if yes, turning to a step B25;
if not, turning to step B27;
step B25: judging whether the residual electric quantity of the battery in unit time is smaller than the maximum capacity of the battery;
if yes, go to step B26;
if not, setting the scheduling parameter in the pre-scheduling information as 'selling electricity to an external power grid by the difference value of the photovoltaic power and the load power in unit time';
step B26: judging whether the maximum charging power in the unit time of the battery is smaller than the difference value between the photovoltaic power and the load power in the unit time;
if yes, setting a scheduling parameter in the pre-scheduling information as ' charging a battery with the maximum charging power in unit time of the battery ', and selling electricity to an external power grid according to the residual power ';
if not, setting the scheduling parameter in the pre-scheduling information as 'charging the battery by the difference value of the photovoltaic power and the load power in unit time';
step B27: judging whether the residual electric quantity of the battery in unit time is larger than the minimum capacity of the battery;
if yes, go to step B28;
if not, setting the scheduling parameters in the pre-scheduling information as 'power taking to an external power grid according to the difference value of the load power and the photovoltaic power in unit time';
step B28: judging whether the maximum discharge power in the unit time of the battery is smaller than the difference value between the load power and the photovoltaic power in the unit time;
if yes, setting a scheduling parameter in the pre-scheduling information as 'the battery discharges with the difference value of the load power and the photovoltaic power in unit time';
if not, setting the scheduling parameter in the pre-scheduling information as ' discharging the battery with the maximum discharging power ', and simultaneously taking electricity to an external power grid according to the difference value of the load power, the battery discharging power and the photovoltaic power generation power '.
It will be appreciated that in some alternative implementations, the functions noted in the flowcharts, or blocks in the block diagrams, may occur out of the order noted in the figures. For example, two steps or blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
In a preferred embodiment, as shown in fig. 6, step S22 includes:
step S221: respectively generating a first sample distance of a sample point of the prescheduling information and a sample point of each standard state information;
step S222: clustering sample points according to the first sample distance to generate a plurality of sample classes;
step S223: respectively calculating a second sample distance between every two sample classes, and clustering the sample classes according to the second sample distance;
step S224: and repeating the step S223 until the number of clustered sample classes reaches a set class threshold, and outputting the sample class where the sample point of the prescheduling information is located as a state mode.
Specifically, in order to achieve better division of the state mode to which the current state information belongs, in this embodiment, a KNN method is introduced to classify sample points of the prescheduled information and the standard state information, and a set of a plurality of sample points is converged into a specific plurality of state modes through the processes of clustering, calculating a centroid and re-clustering. The number of the state modes is selected according to the number of the collected standard state information in the actual operation process, and the state modes represent the operation state of a micro-grid where the photovoltaic energy storage system is located, such as 'high battery residual electricity and higher online electricity price'; the load power is lower, the off-grid electricity price is low, and the like. By clustering the pre-scheduling information and the standard state information and dividing the pre-scheduling information and the standard state information into a certain operation mode, the optimal benefit index which can be achieved in a certain operation mode can be judged according to the pre-collected standard state information in the subsequent process, and further scheduling parameters which should be executed by the current state information are reversely deduced according to the optimal benefit index and the standard state information, so that the operation mode of the photovoltaic energy storage system is globally optimized. It should be noted that, while the number of state modes is selected, it is necessary to consider that too many state modes occupy too many computing resources in the subsequent regression operation, resulting in an extended processing time.
In an implementation process, the above process is embodied as an iterative process of calculating distances, clustering according to the distances, calculating centroids, and then calculating the distances again. In the first calculation, step S222, the distance calculation method commonly used in KNN method is adopted, that is, the battery remaining capacity SOC, photovoltaic power P is included according to the fields in the prescheduling information and the standard state information pv Load power P load External network electricity price C out Photovoltaic internet price C pv And the fields are used for respectively calculating the distance between each sample point according to the fields. The distance used herein is the Euclidean distance, such as:
wherein d (i, j) indicates the distance between the ith sample point and the jth sample point, i m The mth field, j, being the ith sample point m The mth field, which is the jth sample point, n is the number of fields, in this embodiment 5.
After the calculation of the first sample distance of each sample point is completed, clustering can be performed through a pre-divided distance threshold, and a certain pair of sample points with the first sample distance smaller than the distance threshold are used as a class, so that the first clustering process is completed. And then, for each clustered sample class, calculating the mass center of the class as a class center, calculating the distance between the class centers again to be used as a sample class distance, judging the calculated sample class distance by adopting a sample distance threshold value, and merging a certain pair of sample classes with the sample class distance smaller than the sample distance threshold value to form a new sample class. By repeating the clustering process of the sample classes, a plurality of sample classes can be converged to a plurality of sample classes with specific numbers, namely a plurality of state modes, so that the state mode of the prescheduled information can be judged.
The class center calculation process of the sample class is as follows:
wherein ,ci For sample class R i S is the sample class R i Coordinates of each sample point.
As an alternative embodiment, the category threshold is set to 4.
In a preferred embodiment, as shown in fig. 7, step S3 includes:
step S31: acquiring a plurality of standard state information in a state mode, and respectively calculating benefit indexes of each standard state information;
step S32: and generating the optimal benefit index in the state mode according to the plurality of benefit indexes.
In a preferred embodiment, in step S31, the method for calculating the benefit index includes:
wherein ,Rhat As an index of the benefit to be achieved,
for the i-th hour of the upper grid power, < >>
For the i-th hour, internet power price, < >>
For the ith hour of lower grid power, +.>
The grid for the ith hour is powered up.
Specifically, in order to realize better quantification of economic benefits generated by charging and discharging behaviors of the photovoltaic energy storage system, in the embodiment, the benefit index is set to be 1/24 of the difference value between the photovoltaic electricity selling income and the electricity outward purchasing cost which are finished in 24 hours a day, so that a better quantification effect is realized.
In a preferred embodiment, in step S32, the method for calculating the optimal benefit index includes:
wherein ,
r is the optimum benefit index k R is the number of all standard state information in the state mode hat ∈top10％R k Is standard state information with the benefit index of the first 10% in the state mode, R hat Is a benefit index of the standard state information.
Specifically, for the photovoltaic energy storage system in the prior art, when the linear programming model is adopted for scheduling, the problem that the extreme value cannot be achieved due to the guidance output of the strong objective function is easy, in this embodiment, after the benefit index of each piece of standard state information in the state mode is calculated, all pieces of standard state information in the state mode are ordered from large to small according to the benefit index, and the average value of the benefit index of the standard state information 10% before the order is extracted to be used as the optimal benefit index in the state mode, so that the problem that the model outputs the extreme value is avoided.
In a preferred embodiment, as shown in fig. 8, step S4 includes:
step S41: generating a sample to be predicted according to the pre-standard state information and the optimal benefit index, and generating a benefit sample according to the standard state information and the benefit index corresponding to the standard state information;
step S42: respectively calculating second sample distances between sample points of the sample to be predicted and sample points of each benefit sample;
step S43: generating a benefit sample set corresponding to the sample to be predicted according to the second sample distance;
step S44: and generating scheduling parameters corresponding to the samples to be predicted according to the benefit sample set.
Specifically, for the photovoltaic energy storage system in the prior art, when scheduling is performed, the corresponding scheduling instruction is simply determined according to a plurality of state parameters, and it is difficult to achieve the problem of maximizing economic benefit in a long-term operation process, in this embodiment, after calculating an optimal benefit index, a sample to be predicted is generated by combining the optimal benefit index and pre-scheduling information, and a benefit sample is generated according to standard state information and a benefit index corresponding to the standard state information, as shown in the following table 2:
TABLE 2
It should be noted that, the samples to be predicted generated herein, with respect to the prescheduling information, have fields of the "control instruction" portion removed, and the "benefit index" field added, and the benefit samples have "operation mode", "control instruction" and "benefit index" fields at the same time. By generating the sample to be predicted and the benefit sample, the scheduling parameter corresponding to the current state information, namely the relevant parameter of the control instruction part, can be obtained through regression according to the optimal benefit index and the current state information in the process, so that the optimal benefit index in the current mode is realized.
In order to achieve the above-mentioned process, in this embodiment, a plurality of benefit sample sets with relatively close pre-prediction points are obtained by calculating the second sample distance, and an average value is obtained according to a "control instruction" in the benefit sample sets, so as to achieve effective prediction of scheduling parameters to be implemented by the samples to be predicted.
In a preferred embodiment, before step S42, all the state parameters in the sample to be predicted and the benefit sample are normalized respectively;
wherein ,xnew For the normalized state parameter, X is the state parameter before normalization, max (X) is the maximum value of the state parameters of the same class, and min (X) is the minimum value of the state parameters of the same class.
Specifically, in order to achieve a better prediction effect on the scheduling parameters, in this embodiment, before calculating the second sample distance between the sample to be predicted and the benefit sample, a normalization process is performed on each state parameter to generate a standardized and unified state parameter, so as to achieve a better prediction effect.
In a preferred embodiment, in step S44, the method for generating scheduling parameters according to the standard state information set includes:
wherein ,pbat* For the scheduling parameters corresponding to the samples to be predicted, k is the number of benefit samples in the standard state information set, p bat Is a benefit sample in the standard state information set, S g Is a standard state information set, P bat Is the scheduling parameter of the benefit sample.
Specifically, in order to achieve a better prediction effect of the scheduling parameters of the samples to be predicted, in this embodiment, the benefit samples near the samples to be predicted are clustered based on the second sample distance in the prediction process, and the average value of the class is obtained by calculation, so that the scheduling parameters are generated, and the scheduling parameters are enabled to conform to the optimal benefit index in the current state mode.
The invention has the beneficial effects that: in the process of generating the scheduling parameters, the optimal benefit indexes which can be realized in different state modes are calculated, and the scheduling parameters which should be executed by the current state information are predicted by combining the optimal benefit indexes and the standard state information, so that the maximum benefit can be realized by the scheduling parameters which are finally used for controlling the photovoltaic energy storage system. Meanwhile, the current state information and the standard state information acquired in advance are clustered, and the state mode of the current state information is judged, so that the optimal benefit index which can be realized under different state modes is generated, the problem that in the prior art, extreme scheduling instructions which do not conform to the actual conditions and cannot be implemented are easily generated by prediction through a fixed single model is avoided, and the interpretability and the conservation of the output instructions are ensured.
The foregoing is merely illustrative of the preferred embodiments of the present invention and is not intended to limit the embodiments and scope of the present invention, and it should be appreciated by those skilled in the art that equivalent substitutions and obvious variations may be made using the description and illustrations of the present invention, and are intended to be included in the scope of the present invention.
Claims (8)
1. A method of scheduling a photovoltaic energy storage system, comprising:
step S1: acquiring current state information of the photovoltaic energy storage system and a plurality of different standard state information acquired in advance;
step S2: acquiring a plurality of corresponding standard state information according to the current state information, and judging the current state mode of the photovoltaic energy storage system;
step S3: generating an optimal benefit index corresponding to the state mode according to the state mode and a plurality of standard state information associated with the state mode;
step S4: generating scheduling parameters for controlling the photovoltaic energy storage system according to the optimal benefit index;
the current state information includes a plurality of state parameters, and the step S2 includes:
step S21: sequentially comparing a plurality of state parameters in the current state information according to a preset comparison rule, and generating corresponding prescheduling information according to a comparison result;
step S22: determining the current state mode according to the pre-scheduling information and the standard state information;
the standard state information comprises a plurality of state parameters and scheduling conditions, and is obtained by collecting and storing the photovoltaic energy storage systems in different periods;
the state pattern is obtained by clustering the prescheduled information and the standard state information.
2. The scheduling method according to claim 1, wherein the step S22 includes:
step S221: generating a first sample distance of a sample point of the prescheduling information and a sample point of each of the standard state information respectively;
step S222: clustering the sample points according to the first sample distance to generate a plurality of sample classes;
step S223: respectively calculating second sample distances between every two sample classes, and clustering the sample classes according to the second sample distances;
step S224: and repeating the step S223 until the number of the clustered sample classes reaches a set class threshold, and outputting the sample class where the sample point of the prescheduling information is located as the state mode.
3. The scheduling method according to claim 1, wherein the step S3 includes:
step S31: acquiring a plurality of standard state information in the state mode, and respectively calculating benefit indexes of each standard state information;
step S32: and generating the optimal benefit index in the state mode according to a plurality of the benefit indexes.
4. The scheduling method according to claim 3, wherein in the step S31, the method for calculating the benefit index includes:
wherein ,Rhat As an index of the benefit to be used,
for the i-th hour of the upper grid power, < >>
For the i-th hour, internet power price, < >>
For the ith hour of lower grid power, +.>
The grid for the ith hour is powered up.
5. The scheduling method according to claim 3, wherein in the step S32, the method for calculating the optimal benefit index includes:
wherein ,
r is the optimum benefit index k R is the number of all the standard state information in the state mode hat ∈top10％R k R is the standard state information with the benefit index of the first 10% in the state mode hat And the benefit index is the standard state information.
6. A scheduling method according to claim 3, wherein said step S4 comprises:
step S41: generating a sample to be predicted according to the standard state information and the optimal benefit index, and generating a benefit sample according to the standard state information and the benefit index corresponding to the standard state information;
step S42: respectively calculating second sample distances between the sample points of the sample to be predicted and the sample points of each benefit sample;
step S43: generating a benefit sample set corresponding to the sample to be predicted according to the second sample distance;
step S44: and generating the scheduling parameters corresponding to the samples to be predicted according to the benefit sample set.
7. The scheduling method according to claim 6, wherein, before the step S42, all the state parameters in the samples to be predicted and the benefit samples are normalized, respectively;
wherein ,xne w is the state parameter after normalization, X is the state parameter before normalization, max (X) is the maximum value of the state parameters in the same class, and min (X) is the minimum value of the state parameters in the same class.
8. The scheduling method according to claim 6, wherein in the step S44, the method for generating the scheduling parameters according to the standard state information set includes:
wherein ,Pbat* K is the number of the benefit samples in the benefit sample set, P, for the scheduling parameter corresponding to the sample to be predicted bat S for the benefit samples in the benefit sample set g For the benefit sample set, P bat And scheduling parameters for the benefit samples.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210938501.9A CN115642617B (en) | 2022-08-05 | 2022-08-05 | Scheduling method of photovoltaic energy storage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210938501.9A CN115642617B (en) | 2022-08-05 | 2022-08-05 | Scheduling method of photovoltaic energy storage system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115642617A CN115642617A (en) | 2023-01-24 |
| CN115642617B true CN115642617B (en) | 2023-06-09 |
Family
ID=84940488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210938501.9A Active CN115642617B (en) | 2022-08-05 | 2022-08-05 | Scheduling method of photovoltaic energy storage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115642617B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007295680A (en) * | 2006-04-24 | 2007-11-08 | Matsushita Electric Ind Co Ltd | Load control device |
| CN107153892A (en) * | 2017-05-12 | 2017-09-12 | 沈阳工程学院 | Distributed wind and optical energy integrated generated power forecasting system |
| CN114421530A (en) * | 2022-02-17 | 2022-04-29 | 科大智能科技股份有限公司 | Scheduling method and device of photovoltaic energy storage system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11742668B2 (en) * | 2020-10-30 | 2023-08-29 | Hygge Energy Inc. | Methods and systems for green energy charging of electrical vehicles |
-
2022
- 2022-08-05 CN CN202210938501.9A patent/CN115642617B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007295680A (en) * | 2006-04-24 | 2007-11-08 | Matsushita Electric Ind Co Ltd | Load control device |
| CN107153892A (en) * | 2017-05-12 | 2017-09-12 | 沈阳工程学院 | Distributed wind and optical energy integrated generated power forecasting system |
| CN114421530A (en) * | 2022-02-17 | 2022-04-29 | 科大智能科技股份有限公司 | Scheduling method and device of photovoltaic energy storage system |
Non-Patent Citations (1)
| Title |
|---|
| 微电网并网运行优化调度策略及应用;张海涛;《中国优秀硕士学位论文全文数据库》(第1期);第1-72页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115642617A (en) | 2023-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Barnes et al. | A semi-Markov model for control of energy storage in utility grids and microgrids with PV generation | |
| CN110048420A (en) | A kind of method, apparatus and medium of the scheduling of power distribution network random optimization | |
| CN108471143A (en) | Micro-grid multi-energy method for optimizing scheduling based on positive and negative feedback particle cluster algorithm | |
| CN111555347A (en) | Wind power prediction-based wind storage combined operation control method | |
| CN112381269A (en) | Independent micro-grid capacity optimal configuration method considering load importance and electricity price excitation | |
| CN107273968A (en) | A kind of Multiobjective Scheduling method and device based on dynamic fuzzy Chaos-Particle Swarm Optimization | |
| CN113022361A (en) | Charging pile-based ordered charging method under power demand response condition | |
| CN109572478A (en) | Charging station electric car steady charging system and method online | |
| Abdelhak et al. | Optimum sizing of hybrid PV/wind/battery using Fuzzy-Adaptive Genetic Algorithm in real and average battery service life | |
| CN110707711B (en) | User side comprehensive energy system hierarchical regulation and control method and system | |
| Jemaa et al. | Optimum sizing of hybrid PV/wind/battery system using Fuzzy-Adaptive Genetic Algorithm | |
| CN117254464B (en) | Control method and system of energy storage system | |
| CN105470947B (en) | A kind of micro-capacitance sensor dispatching method based on quantum-behaved particle swarm optimization | |
| CN115642617B (en) | Scheduling method of photovoltaic energy storage system | |
| CN114285086A (en) | Electrochemical energy storage power station energy scheduling method and system based on improved ant colony algorithm | |
| Jemaa et al. | Optimum sizing of hybrid PV/Wind/battery installation using a fuzzy PSO | |
| CN111160384A (en) | Mobile energy storage vehicle scheduling optimization method, system and device | |
| CN115238992A (en) | Power system source load storage coordination optimization method and device and electronic equipment | |
| CN114626622A (en) | Photovoltaic power prediction method, system, device and storage medium | |
| CN112821451A (en) | Distributed photovoltaic access coping method for smart town power distribution network based on demand side management and energy storage | |
| CN110717694B (en) | Energy storage configuration random decision method and device based on new energy consumption expected value | |
| CN109149644B (en) | Light-storage integrated online strategy matching and collaborative optimization method based on big data analysis | |
| CN113595149A (en) | Power coordination control method based on hydrogen-light-storage combined power generation system | |
| CN114709852A (en) | Rapid calculation and analysis method and system for micro-energy grid energy management response characteristics | |
| CN114447963A (en) | Energy storage battery power control method and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |