CN117829499A - Low-carbon electricity utilization scheduling method for photovoltaic power generation sewage plant and computer readable medium - Google Patents
Low-carbon electricity utilization scheduling method for photovoltaic power generation sewage plant and computer readable medium Download PDFInfo
- Publication number
- CN117829499A CN117829499A CN202311840019.2A CN202311840019A CN117829499A CN 117829499 A CN117829499 A CN 117829499A CN 202311840019 A CN202311840019 A CN 202311840019A CN 117829499 A CN117829499 A CN 117829499A
- Authority
- CN
- China
- Prior art keywords
- sewage plant
- day
- history
- period
- photovoltaic
- 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
Links
- 239000010865 sewage Substances 0.000 title claims abstract description 271
- 230000005611 electricity Effects 0.000 title claims abstract description 127
- 238000010248 power generation Methods 0.000 title claims abstract description 105
- 238000000034 method Methods 0.000 title claims abstract description 62
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 31
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 42
- 238000005457 optimization Methods 0.000 claims abstract description 32
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 30
- 230000003203 everyday effect Effects 0.000 claims abstract description 18
- 238000011478 gradient descent method Methods 0.000 claims abstract description 6
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 44
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 37
- 229910052760 oxygen Inorganic materials 0.000 claims description 37
- 239000001301 oxygen Substances 0.000 claims description 37
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 31
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 31
- 229910052698 phosphorus Inorganic materials 0.000 claims description 31
- 239000011574 phosphorus Substances 0.000 claims description 31
- 239000000126 substance Substances 0.000 claims description 31
- 229910052757 nitrogen Inorganic materials 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 230000002354 daily effect Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 101000604223 Homo sapiens Nocturnin Proteins 0.000 claims description 3
- 102100038815 Nocturnin Human genes 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 2
- 238000005265 energy consumption Methods 0.000 abstract description 4
- 238000004134 energy conservation Methods 0.000 abstract description 2
- 230000009467 reduction Effects 0.000 abstract description 2
- 238000013519 translation Methods 0.000 description 8
- 230000004044 response Effects 0.000 description 6
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 5
- 238000004146 energy storage Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 239000003344 environmental pollutant Substances 0.000 description 4
- 231100000719 pollutant Toxicity 0.000 description 4
- 238000009434 installation Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000005273 aeration Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 239000010802 sludge Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000004065 wastewater treatment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a low-carbon electricity utilization scheduling method for a photovoltaic power generation sewage plant and a computer readable medium. Acquiring water quality parameters of inflow water of each period of a sewage plant history every day, electric power required by a blower and the rest equipment except the blower, industrial electricity price, photovoltaic surplus electricity selling price and meteorological data, and calculating photovoltaic power generation power of the corresponding period; constructing a water quality constraint condition of the effluent, taking the minimum total electricity charge of a plurality of time periods per day of a history of a sewage plant as an optimization target, and solving the power required by the blower after optimizing each time period per day of the history through a traversal method; constructing each group of samples and corresponding real labels thereof, inputting a convolutional neural network, and optimizing parameters by a gradient descent method; and acquiring various data of the sewage plant history in each time period every day in real time, and predicting by using the optimized convolutional neural network to obtain the power required by the blower after optimizing each time period every day next. The method can rapidly and accurately predict the low-carbon electricity utilization strategy and realize energy conservation and consumption reduction of the sewage plant.
Description
Technical Field
The invention relates to the technical field of low-carbon power dispatching, in particular to a low-carbon power dispatching method for a photovoltaic power generation sewage plant and a computer readable medium.
Background
The aim of double carbon is put forward in China, and various industries take measures of reducing carbon and reducing consumption for response. The sewage treatment industry consumes a great deal of energy while reducing pollutant discharge, and the energy consumption sources mainly comprise electricity consumption, medicine consumption, transportation and the like. Wherein, the electricity consumption cost generally accounts for 60% -80% of the total cost. According to the statistical data of the national energy bureau, the power consumption of the sewage treatment plant in 2020 is 184 hundred million degrees, which accounts for 0.24 percent of the power consumption of the whole country. Under the support of relevant national policies, the photovoltaic power generation project of the sewage treatment plant adopting the mode of self-power-consumption and surplus electricity surfing is greatly developed in recent years. The grid-connected power generation of the sewage treatment plant in the Yixing city is smoothly realized in the 2017 year, and the grid-connected power generation of the sewage treatment plant in the North of the Beijing magnet is realized in the 2018 year. In 2022, the largest domestic sewage treatment plant distributed photovoltaic power generation project, namely the north lake sewage treatment plant formally runs in a grid-connected mode, can generate about 2200 ten thousand degrees per year, saves about 0.5 ten thousand tons of generated coal, and is equivalent to reducing emission of 2 ten thousand tons of carbon dioxide. Photovoltaic power generation projects such as Shanghai mountain in the winter port sewage plant, hunan Liaojia ward water plant, ocean lake water plant, flower bridge water purification plant and the like finish grid-connected production in 2023, and therefore the installation of a photovoltaic power generation system in a sewage treatment plant becomes a hot spot.
The sewage treatment plant usually has a certain occupied area, and can be embedded into the photovoltaic by comprehensively utilizing the building roof, the area above the treatment structure and other places. The daytime photovoltaic power generation capacity is sufficient, the solar energy photovoltaic power generation system can be used for power plant power consumption of sewage treatment, and the surplus power is integrated into a power grid. The method can reduce the electricity cost of the sewage treatment plant, reduce the carbon emission and have economic benefit and environmental benefit.
However, photovoltaic power generation is affected by meteorological conditions, the power generation amount of each period in one day fluctuates greatly, and power generation is unstable. Under the condition of sufficient solar energy, the surplus photovoltaic power generation amount cannot be fully utilized by a sewage treatment plant and can only be sold on the internet. Taking Hubei provincial power price policy as an example, the price of photovoltaic Internet surfing electricity selling is far lower than the industrial electricity price of a sewage treatment plant. The method means that the sewage treatment plant fully utilizes the electric energy generated by the photovoltaic power generation as much as possible, so that more electricity purchasing cost can be saved and more carbon emission can be reduced compared with the 'residual electricity surfing'. Therefore, how to fully utilize the electric energy generated by photovoltaic power generation in the sewage treatment plant to further reduce the electricity cost is a problem to be solved in the application of the photovoltaic power generation system in the sewage treatment plant.
Currently, there are two main solutions to the above problem, namely adding energy storage devices and performing demand side response by scheduling the electricity consumption of the devices of the sewage treatment plant. The energy storage equipment can store the surplus electric quantity of the photovoltaic power generation, and discharge is carried out for the load of the sewage plant to use when the photovoltaic power generation capacity can not meet the power consumption of the sewage treatment plant. However, adding energy storage equipment not only increases the initial cost of a sewage treatment plant, but also causes a certain hidden environmental pollution trouble. The demand side response means that the power consumer temporarily changes the power consumption behavior according to price or excitation measures, and increases or decreases the power consumption, namely, the power supply and demand balance is promoted through load translation, the stable operation of the power grid is ensured, and the short-term behavior of the power price rise is restrained, so that additional design and installation of energy storage equipment are not needed.
By combining the power requirement of the sewage treatment plant and the power generation flexibility of the cogeneration system, the required scale of the renewable power grid in Australia is optimized through load translation, so that good supply and demand matching is realized, and the power cost is reduced. Taking a sewage plant in California as a research object, examining the capacity of the sewage plant for carrying out load translation according to price excitation measures, summarizing the conditions required by the sewage plant to participate in a power consumption demand plan through power consumption load transfer, and indicating two difficulties existing in the power consumption load translation of the sewage plant, namely determining the power consumption load translation time and the power consumption load translation size. The minimization of power consumption of a sewage treatment plant-smart grid system is achieved by the demand response of the sewage treatment plant and the residential building, which simultaneously takes into account the scheduling of pumps and blowers. The domestic photovoltaic sewage plant starts later than overseas, and the construction of the first photovoltaic sewage plant integrated project of the domestic Beijing good country satellite urban sewage treatment plant is completed in 2011. At present, domestic researches on a photovoltaic sewage plant mainly focus on investment benefit analysis, process parameter optimization, cost estimation and the like for the sewage plant through sewage plant simulation software and a neural network. Moreover, due to lack of related national policy incentives and matched automation technology, domestic sewage plants are still blank in the search of demand side response.
In combination with the actual condition of domestic sewage plants, aeration is a high energy consumption duty ratio link of the sewage treatment plants in China, and the adjustment and control of the air blower do not need to be additionally provided with additional facilities, so that the method is a starting point for carrying out better electric load translation. Furthermore, the photovoltaic power generation capacity can be fully utilized by tracking the power consumption load of the photovoltaic power generation capacity translation blower according to the water inlet condition, the photovoltaic power generation power and the industrial time-of-use power price of the sewage plant, so that the power consumption cost of the sewage treatment plant is reduced and the carbon emission is reduced on the premise that the effluent quality meets the standard. The hysteresis of sewage treatment, the power generation instability of photovoltaics, and the complexity of considering multiple factors simultaneously make the generation of power utilization scheduling strategies challenging. Therefore, how to consider the low-carbon electricity dispatching strategy of the sewage plant is worth thinking.
Disclosure of Invention
The invention aims to overcome the problem of insufficient utilization of photovoltaic power generation capacity of a sewage treatment plant through a demand side response, and aims to provide a low-carbon power consumption scheduling method and a computer readable medium for the photovoltaic power generation sewage plant.
The invention discloses a low-carbon electricity utilization scheduling method for a photovoltaic power generation sewage plant, which is characterized by comprising the following steps of:
acquiring a plurality of water quality parameters of water inflow of a sewage plant in each time period of each day; electric power required by the blower and electric power required by the rest of equipment except the blower; meteorological data, and calculating to obtain the photovoltaic power generation power of each period of each day of the history of the photovoltaic power generation system arranged in the sewage plant; acquiring the current industrial electricity price and the current photovoltaic surplus electricity selling price of the sewage plant in each time period;
constructing constraint conditions and total electricity charge of each time period of the history of the sewage plant, taking minimization of total electricity charge of a plurality of time periods of the history of the sewage plant in each day as an optimization target, taking electric power required by a blower in each time period of the history of the sewage plant as an optimization solving object, and solving through a traversal method to obtain electric power required by the blower after optimization in each time period of the history in each day;
constructing each group of samples and real labels corresponding to each group of samples;
inputting each group of samples into a convolutional neural network for training, and training by a gradient descent method to obtain optimized parameters and then obtaining the convolutional neural network;
and acquiring various water quality parameters of water inflow of the sewage plant in each time period every day, the electric power required by the air blower, the electric power required by the rest equipment except the air blower and meteorological data in real time, calculating to obtain the photovoltaic power generation power of a photovoltaic power generation system arranged in the sewage plant, the industrial electricity price of the sewage plant and the photovoltaic rest electricity selling price, calculating the electric power required by the air blower after optimization of the corresponding time period, and predicting through a convolutional neural network after optimizing the parameters to obtain a prediction result of the electric power required by the air blower after optimization of each time period in the next day.
The method comprises the following specific steps:
step 1: acquiring chemical oxygen demand, ammonia nitrogen content, total phosphorus content, blower required power of each time period of history daily and residual equipment required power except the blower of a sewage plant; acquiring meteorological data of each time period of a history of a place where a sewage plant is located, and calculating to obtain photovoltaic power generation power of each time period of the history of a photovoltaic power generation system arranged in the sewage plant; acquiring the current industrial electricity price and the current photovoltaic surplus electricity selling price of the sewage plant in each time period;
preferably, the meteorological data in step 1 includes: irradiation intensity, ambient temperature;
and (2) calculating the photovoltaic power generation power of each period of each day of the history of the photovoltaic power generation system arranged in the sewage plant, wherein the photovoltaic power generation power is specifically as follows:
wherein, the standard test conditions;
P PV，j，i representing the photovoltaic power generation power of a historical jth day i period of a photovoltaic power generation system arranged in a sewage plant;
P * the nominal direct current power of the photovoltaic generator set in the standard state is represented;
G j，i indicating the irradiation intensity of the sewage plant in the j th day and i th period of the history;
G * representing the total irradiation intensity of the sun in a standard state;
k represents a relative change coefficient of generated power due to a change in panel temperature;
T c，j，i representing the temperature of the photovoltaic cell panel in the operation state of the jth period of the history;
the temperature of the photovoltaic cell panel in the standard state is represented;
f G representing a loss coefficient of the photovoltaic module related to the incident irradiation level, wherein the loss coefficient is in a value range of 0-1;
f DC representing all loss coefficients in the direct current power output process, wherein the value range is between 0 and 1;
f AC representing conversion from nominal DC powerThe value range of the loss coefficients in the alternating current output process is 0-1;
η INV the conversion efficiency of the inverter is represented, and the value range is 0-1;
the relationship between the photovoltaic panel temperature of each time period of the history of the sewage plant and the ambient temperature of each time period of the history of the sewage plant is as follows:
wherein T is a，j，i The environmental temperature of the jth day and the ith period of the jth day of the history of the sewage plant is obtained; NOCT is the nominal operating cell temperature, defined as exposure of the photovoltaic module to solar irradiance of 800Wm -2 The temperature reached by the battery when the ambient temperature is 20 ℃ and the wind speed is 1m/s,
G t，j，i total solar irradiance for the historical jth day i period;
step 2: according to the electric power required by the blower of each time period of the history of the sewage plant, the electric power required by all equipment except the blower and the photovoltaic power generation power, the electric power purchased of each time period of the history of the sewage plant and the photovoltaic residual electricity selling electric power are calculated respectively, the constraint conditions are built by combining the chemical oxygen demand of water, the ammonia nitrogen content, the total nitrogen content and the total phosphorus content of each time period of the history of the sewage plant, the electric power purchased of each time period of the history of the sewage plant, the industrial electric price, the photovoltaic residual electricity selling electric power of each time period of the history of the sewage plant and the photovoltaic residual electricity selling electric price, the total electric charge of each time period of the history of the sewage plant is built, the total electric charge of a plurality of time periods of each day of the history of the sewage plant is minimized, the electric power required by the blower of each time period of each day of the history of the sewage plant is used as an optimization solving object, and the electric power required by the blower of each time period of each day of the history of the sewage plant is obtained according to the following method: firstly, dividing the power consumption of the blower of the sewage plant into different grades according to the given power and the power adjusting range of the blower, solving the power consumption of the blower after optimizing each time period every day through a traversal method;
Step 3: taking the photovoltaic power generation power, the chemical oxygen demand of the inflow water, the ammonia nitrogen content, the total phosphorus content, the industrial electricity price and the power required by the optimized blower in a plurality of periods of the history of the sewage plant as each group of samples, and taking the power required by the optimized blower in a plurality of periods of the next day of the history as a real label corresponding to each group of samples;
step 4: constructing a convolutional neural network, inputting each group of samples into the convolutional neural network for training to obtain classification labels corresponding to each group of samples, constructing a loss function model by combining the real labels corresponding to each group of samples, and training by a gradient descent method to obtain optimized parameters and then obtaining the convolutional neural network;
step 5: the method comprises the steps of collecting chemical oxygen demand, ammonia nitrogen content, total phosphorus content of inlet water of a sewage plant in each period in real time, calculating electric power required by blowers in each period every day, electric power required by residual equipment except the blowers, irradiation intensity and temperature of a place where the sewage plant is located to obtain photovoltaic power generation power of a photovoltaic power generation system arranged in the sewage plant, industrial electricity price of the sewage plant and electricity selling price of photovoltaic residual electricity, obtaining electric power required by optimized blowers in corresponding periods through processing in steps 1 and 2, inputting the electric power required by the optimized blowers in each period into a convolutional neural network for prediction, and obtaining a prediction result of the electric power required by the optimized blowers in each period in the next day.
Preferably, the calculating of the power consumption of the sewage plant in step 2 is performed at each time period of the history of the sewage plant, specifically as follows:
wherein j is E [1, D]，i∈[1，F]D represents the number of historical days, F represents the number of time periods per day, P buy，j，i For the power purchase of the j-th day and i-th period of the history of the sewage plant, P exc BL，j，i Power required for all equipment except the blower in the jth and ith period of history of sewage plant, P PV，j，i Is sewage plant calendarShi Di j day i period photovoltaic power generation, P BL，j，i The electric power required by the blower in the ith period of the jth day of the history of the sewage plant;
preferably, in the step 2, the calculation of the photovoltaic electricity remaining power for selling electricity of each period of the sewage plant history is specifically as follows:
wherein P is sell，j，i Selling electric power for photovoltaic residual electricity in the j-th day and i-th period of history of sewage plant, P exc BL，j，i Power required for all equipment except the blower in the jth and ith period of history of sewage plant, P PV，j，i The photovoltaic power generation power P of the ith period of the jth day of the history of the sewage plant BL，j，i The electric power required by the blower in the ith period of the jth day of the history of the sewage plant;
preferably, the construction constraint conditions described in the step 2 are specifically as follows:
COD j，i ＜α；NH 3 -N j，i ＜β；TN j，i ＜γ；TP j，i ＜δ
wherein, COD j，i Effluent chemical oxygen demand, NH, for the j-th day and i-th period of a sewage plant history 3 -N j，i For the ammonia nitrogen content and TN of effluent of the j th day and i th period of the history of the sewage plant j，i For the total nitrogen content, TP, of effluent water in the j-th day and i-th period of the history of a sewage plant j，i For the total phosphorus content of the effluent of the j-th day and i-th period of the history of the sewage plant, alpha, beta, gamma and delta are respectively the highest limit values of the chemical oxygen demand of the effluent, the ammonia nitrogen content of the effluent, the total nitrogen content of the effluent and the total phosphorus content of the effluent of the sewage plant;
preferably, the total electricity charge of each period of each day of the sewage plant history in step 2 is as follows:
Price j，i ＝(P buy，j，i ×F buy，j，i )-(P sell，j，i ×F sell，j，i )
wherein, price j，i For the sum of the j th day and i th period of the history of the sewage plantElectric charge, P buy，j，i For the power purchasing power of the sewage plant in the j-th day and i-th period, F buy，j，i For the historical j-th day and i-th period of the sewage plant, P sell，j，i Selling electric power for photovoltaic residual electricity in the j-th day and i-th period of history of sewage plant, F sell，j，i The price of the electricity selling for the photovoltaic residual electricity in the ith period of the j th day of the history of the sewage plant;
preferably, the optimization objective in step 2 is as follows:
wherein, price j Is the total electricity charge on the j th day of the history of the sewage plant, P buy，j，i For the power purchasing power of the sewage plant in the j-th day and i-th period, F buy，j，i For the historical j-th day and i-th period of the sewage plant, P sell，j，i Selling electric power for photovoltaic residual electricity in the j-th day and i-th period of history of sewage plant, F sell，j，i The price of the electricity selling for the photovoltaic residual electricity in the ith period of the j th day of the history of the sewage plant;
Preferably, each set of samples described in step 3 is as follows:
Data k ＝(P PV，k ，COD k ，NH 3 -N k ，TN k ，TP k ，F buy，k ，OP BL，k )
P PV，k ＝(P PV，(k-1)*L+1 ，P PV，(k-1)*L+2 ，…，P PV，(k-1)*L+L )
P PV，(k-1)*L+l ＝(P PV，(k-1)*L+l，1 ，P PV，(k-1)*L+l，2 ，…，P PV，(k-1)*L+l，24 )
COD k ＝(COD (k-1)*L+1 ，COD (k-1)*L+2 ，…，COD (k-1)*L+L )
COD (k-1)*L+l ＝(COD (k-1)*L+l，1 ，COD (k-1)*L+l，2 ，…，COD (k-1)*L+l，24 )
NH 3 -N k ＝(NH 3 -N (k-1)*L+1 ，NH 3 -N (k-1)*L+2 ，…，NH 3 -N (k-1)*L+L )
NH 3 -N (k-1)*L+l ＝(NH 3 -N (k-1)*L+l，1 ，NH 3 -N (k-1)*L+l，2 ，…，NH 3 -N (k-1)*L+l，24 )
TN k ＝(TN (k-1)*L+1 ，TN (k-1)*L+2 ，…，TN (k-1)*L+L )
TN (k-1)*L+l ＝(TN (k-1)*L+l，1 ，TN (k-1)*L+l，2 ，…，TN (k-1)*L+l，24 )
TP k ＝(TP (k-1)*L+1 ，TP (k-1)*L+2 ，…，TP (k-1)*L+L )
TP (k-1)*L+l ＝(TP (k-1)*L+l，1 ，TP (k-1)*L+l，2 ，…，TP (k-1)*L+l，24 )
F buy，k ＝(F buy，(k-1)*L+1 ，F buy，(k-1)*L+2 ，…，F buy，(k-1)*L+L )
F buy，(k-1)*L+l ＝(F buy，(k-1)*L+l，1 ，F buy，(k-1)*L+l，2 ，…，F buy，(k-1)*L+l，24 )
OP BL，k ＝(OP BL，(k-1)*L+1 ，OP BL，(k-1)*L+2 ，…，OP BL，(k-1)*L+L )
OP BL，(k-1)*L+l ＝(OP BL，(k-1)*L+l，1 ，OP BL，(k-1)*L+l，2 ，…，OP BL，(k-1)*L+l，24 )
wherein k is [1, N ]]，l∈[1，L]，i∈[1，F]N represents the total number of samples, L represents the number of historical days in each group of samples, F represents the number of time periods per day, k represents the kth group of samples, P PV，k 、COD k 、NH 3 -N k 、TN k 、TP k 、F buy，k 、OP BL，k Respectively representing the photovoltaic power generation power, the chemical oxygen demand of the inlet water, the ammonia nitrogen content, the total phosphorus content and the engineering of the sewage plant in the kth group of samplesElectric price and power required by the blower after optimization, P PV，(k-1)*L+l 、COD (k-1)*L+l 、NH 3 -N (k-1)*L+l 、TN (k-1)*L+l 、TP (k-1)*L+l 、F buy，(k-1)*L+l 、OP BL，(k-1)*L+l The method is characterized in that the method comprises the steps of (1) photovoltaic power generation power of a sewage plant on the first historical day in a k group of samples, chemical oxygen demand of inlet water, ammonia nitrogen content, total nitrogen content and total phosphorus content, industrial electricity price, and power sequence required by an optimized blower, and P PV，(k-1)*L+l，i 、COD (k-1)*L+l，i 、NH 3 -N (k-1)*L+l，i 、TN (k-1)*L+l，i 、TP (k-1)*L+l，i 、F buy，(k-1)*L+l，i 、OP BL，(k-1)*L+l，i Photovoltaic power generation power of a sewage plant in the i period in the power sequence required by the blower after optimization on the first historical day, chemical oxygen demand of inlet water, ammonia nitrogen content, total nitrogen content and total phosphorus content, industrial power price and power required by the blower after optimization are obtained;
preferably, the real labels corresponding to each group of samples in step 3 are:
(OP BL，k，(k-1)*L+L+1，1 ，OP BL，k，(k-1)*L+L+1，2 ，…，OP BL，k，(k-1)*L+L+1，24 )
wherein OP BL，k，(k-1)*L+L+1，i The optimized blower power for the i-th period of historical (k-1) l+l+1 days in the k-th set of samples;
Preferably, the real labels corresponding to each group of samples in step 4 are:
(OP BL，k，(k-1)*L+L+1，1 ，OP BL，k，(k-1)*L+L+1，2 ，…，OP BL，k(k-1)*L+L+1，24 )
wherein OP BL，k，(k-1)*L+L+1，i The optimized blower power for the i-th period of historical (k-1) l+l+1 days in the k-th set of samples;
and 4, the prediction labels corresponding to each group of samples are as follows:
wherein,the predicted output of the power required by the blower after optimizing the ith period of the historic (k-1) th (L+L+1) day in the kth group of samples for the convolutional neural network;
preferably, the loss function model in step 4 is defined as follows:
wherein MSE is mean square error, N is total number of samples, OP BL，k，(k-1)*L+L+1，i The power required by the blower after optimization for the i-th period of historical (k-1) th L +1 day in the k-th group of samples,the predicted output of the power required by the blower after optimizing the ith period of the historic (k-1) th (L+L+1) day in the kth group of samples for the convolutional neural network;
the invention also provides a computer readable medium storing a computer program executed by an electronic device, which when run on the electronic device, executes the steps of the low-carbon electricity scheduling method of the photovoltaic power generation sewage plant.
The invention has the following advantages and effects:
the low-carbon electricity utilization scheduling strategy is based on the convolutional neural network, so that the low-carbon electricity utilization strategy under different working conditions can be rapidly and accurately predicted, and guidance is provided for actual production; the electricity utilization strategy meets the standard of the effluent quality, simultaneously realizes energy conservation and consumption reduction of the sewage plant, further responds to the national double-carbon target, and is a low-carbon electricity utilization strategy which accords with the photovoltaic power generation sewage plant in China.
Drawings
Fig. 1: the flow chart of the method of the embodiment of the invention is shown in the schematic diagram;
fig. 2: the convolutional neural network result schematic diagram of 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.
In particular, the method according to the technical solution of the present invention may be implemented by those skilled in the art using computer software technology to implement an automatic operation flow, and a system apparatus for implementing the method, such as a computer readable storage medium storing a corresponding computer program according to the technical solution of the present invention, and a computer device including the operation of the corresponding computer program, should also fall within the protection scope of the present invention.
The following describes a specific embodiment of the invention with reference to fig. 1-2 as a low-carbon electricity dispatching method for a photovoltaic power generation sewage plant, wherein the specific implementation flow steps are as follows:
Step 1: acquiring the chemical oxygen demand, ammonia nitrogen content, total nitrogen content and total phosphorus content of the inflow water of each time period of a sewage plant history, the power required by a blower of each time period of each day and the power required by the rest equipment except the blower; acquiring meteorological data of each time period of a history of a place where a sewage plant is located, and calculating to obtain photovoltaic power generation power of each time period of the history of a photovoltaic power generation system arranged in the sewage plant; acquiring the current industrial electricity price and the current photovoltaic surplus electricity selling price of the sewage plant in each time period;
the blower power per day of the history directly affects the dissolved oxygen content of the sewage treatment link per day of the history of the sewage plant, and a larger power generally means that more oxygen is injected into the sewage. And sufficient dissolved oxygen (2-3 mg/L) is the key for ensuring that microorganisms in the sewage effectively degrade pollutants. The chemical oxygen demand, ammonia nitrogen content, total nitrogen content and total phosphorus content of the effluent water in each period of each day of history generally decrease along with the increase of dissolved oxygen, and when the increase of the dissolved oxygen reaches saturation (2 mg/L and above), the concentration of pollutants is not reduced any more. Therefore, the blower power corresponding to the dissolved oxygen content required when the chemical oxygen demand, the ammonia nitrogen content, the total nitrogen content and the total phosphorus content of the effluent in each time period of each day of the history are ensured to reach the standard is the power required by the blower in each time period of each day of the history.
Considering that a photovoltaic power generation system arranged in a sewage plant does not contain an energy storage facility, a mode of 'self-power-consumption and residual electricity surfing' is adopted, and the capacity of the photovoltaic power generation system is larger than the total power consumption load of the sewage plant. The power load of the sewage plant is stable every time period of the history every day, and the photovoltaic power generation power fluctuates with time.
TABLE 1 statistics of photovoltaic panel installation area for certain sewage plants
In the period of 6:00-9:00 and the period of 15:00-18:00, the photovoltaic power generation power is generally smaller than the total power load of the sewage plant, only the load demand of partial electric equipment of the sewage plant can be met, and the sewage plant needs to purchase partial electric power to the power grid to meet the total power load demand; in the period of 9:00-15:00, the photovoltaic power generation power is usually larger than the total power load of the sewage plant, and the surplus photovoltaic power which cannot be consumed by the sewage plant is sold to a power grid; during the period 18:00-6:00 of the next day, no photovoltaic power generation is basically generated, and the power grid is used for supplying power to the sewage plant completely. According to the mountable area of the photovoltaic equipment of the sewage plant, the photovoltaic power generation power of each period of the history of the sewage plant can be calculated according to the table 1.
The meteorological data in step 1 comprises: irradiation intensity, ambient temperature;
and (2) calculating the photovoltaic power generation power of each period of each day of the history of the photovoltaic power generation system arranged in the sewage plant, wherein the photovoltaic power generation power is specifically as follows:
Wherein, the irradiance is 1000Wm -2 The solar spectrum distribution accords with the AM1.5 condition, and the ambient temperature is 25 ℃;
P * : nominal dc power of the photovoltaic generator set in the standard state;
G j，i : historical j-th day and i-th period of irradiation intensity of the place where the sewage plant is located;
G * : total solar irradiation intensity in standard state;
k: the relative change coefficient of the generated power caused by the temperature change of the battery plate is in the range of 0.22 to 0.71 percent;
T c，j，i : historical temperature of the photovoltaic cell panel in the j-th day and i-th period running state;
the temperature of the photovoltaic cell panel in a standard state;
f G : the loss coefficient of the photovoltaic module related to the incident irradiation level is in the range of 0-1;
f DC : all loss coefficients in the direct current power output process are in a value range of 0-1;
f AC : all loss coefficients in the process of converting nominal direct current power into alternating current output range between 0 and 1;
η INV : the conversion efficiency of the inverter is in the range of 0-1;
photovoltaic cell panel temperature (T) c，j，i ) And ambient temperature (T) a，j，i ) The relationship between them is as follows:
wherein T is a，j，i The environmental temperature of the jth day and the ith period of the jth day of the history of the sewage plant is obtained; NOCT is the nominal operating cell temperature, defined as exposure of the photovoltaic module to solar irradiance of 8 00Wm -2 The temperature reached by the battery at an ambient temperature of 20℃and a wind speed of 1m/s is obtained from the manufacturer's data manual;
G t，j，i total solar irradiance for the historical jth day i period;
step 2: according to the electric power required by the blower of each time period of a certain sewage plant history, the electric power required by all equipment except the blower and the photovoltaic power generation power, the electric power purchased of each time period of the sewage plant history and the photovoltaic residual electricity selling electric power are respectively calculated, the constraint conditions are constructed by combining the chemical oxygen demand of water, the ammonia nitrogen content, the total nitrogen content and the total phosphorus content of each time period of the sewage plant history, the electric power purchased of each time period of the sewage plant history, the industrial electric price, the photovoltaic residual electricity selling electric power of each time period of the sewage plant history and the photovoltaic residual electricity selling electric price, the total electric charge of each time period of the sewage plant history is constructed, the total electric charge of a plurality of time periods of each day of the sewage plant history is minimized, the electric power required by the blower of each time period of each day of the sewage plant history is used as an optimization solving object, and the electric power required by the blower after the optimization of each time period of the sewage plant history is obtained according to the following method: firstly, dividing the power consumption of a blower of a sewage plant into different grades according to the given power and the power adjusting range of the blower (the divided grade corresponds to a specific power value), solving the power consumption of the blower after each time period optimization of the history daily through a traversal method, and verifying the power consumption of the blower after optimization through an international general activated sludge model No. 2, wherein the power consumption can meet the constraint condition that the effluent quality meets the standard;
And step 2, dividing the electric power of the blower of the sewage plant into different grades according to the given power and the power adjusting range of the blower, wherein the specific steps are as follows:
the total power load of a sewage plant is 1350kW, a single group of aerobic tanks is aerated by two blowers, the power of the single blower is 300kW, the power adjusting range is 70% -100%, and considering that the power of the single blower can be only set to be 70% and 100%, the power of the blower can be divided into the following conditions, see table 2
Table 2 electric power level division for blower
| Grade level | Electric power (kW) for blower 1 | Electric power (kW) for blower 2 | Average electric power (kW) |
| 1 | 0 | 210 | 105 |
| 2 | 0 | 300 | 150 |
| 3 | 210 | 210 | 210 |
| 4 | 210 | 300 | 255 |
| 5 | 300 | 300 | 300 |
Note that: considering that the blowers are not suitable for frequent start-stop operation, the working condition that both blowers are stopped is omitted.
And step 2, calculating the electricity purchasing power of the sewage plant history in each time period every day, wherein the electricity purchasing power is specifically as follows:
wherein j is E [1, D]，i∈[1，F]D=631 represents the number of history days, f=24 represents the number of daily periods, P buy，j，i For the power purchase of the j-th day and i-th period of the history of the sewage plant, P excBL，j，i Power required for all equipment except the blower in the jth and ith period of history of sewage plant, P PV，j，i The photovoltaic power generation power P of the ith period of the jth day of the history of the sewage plant BL，j,i The electric power required by the blower in the ith period of the jth day of the history of the sewage plant;
and step 2, calculating the photovoltaic surplus electricity selling power of each period of the history of the sewage plant every day, wherein the photovoltaic surplus electricity selling power is specifically as follows:
wherein P is sell,j,i Selling electric power for photovoltaic residual electricity in the j-th day and i-th period of history of sewage plant, P exc BL,j,i Power required for all equipment except the blower in the jth and ith period of history of sewage plant, P PV,j,i The photovoltaic power generation power P of the ith period of the jth day of the history of the sewage plant BL,j,i The electric power required by the blower in the ith period of the jth day of the history of the sewage plant;
taking Hubei province as an example, according to the industrial electricity policy of Hubei province in 2020, one day can be divided into flat-section electricity price time periods (7:00-9:00, 15:00-20:00, 22:00-23:00), peak electricity price time periods (20:00-22:00), peak electricity price time periods (9:00-15:00) and off-peak electricity price time periods (23:00-next day 7:00), and the electricity purchase price and the electricity selling price of the photovoltaic sewage plant are shown in Table 3.
Table 3 photovoltaic sewage plant purchase price and photovoltaic selling price
The construction constraint conditions in the step 2 are specifically as follows:
COD j，i ＜α；NH 3 -N j，i ＜β；TN j，i ＜γ；TP j，i ＜δ
wherein, COD j，i Effluent chemical oxygen demand, NH, for the j-th day and i-th period of a sewage plant history 3 -N j，i For the ammonia nitrogen content and TN of effluent of the j th day and i th period of the history of the sewage plant j，i For the total nitrogen content, TP, of effluent water in the j-th day and i-th period of the history of a sewage plant j，i For the total phosphorus content of the effluent of the j-th day and i-th period of the history of the sewage plant, alpha, beta, gamma and delta are respectively the highest limit values of the chemical oxygen demand of the effluent, the ammonia nitrogen content of the effluent, the total nitrogen content of the effluent and the total phosphorus content of the effluent of the sewage plant;
the constraint condition in the step 2 is constructed according to the first-level A standard in pollutant emission Standard of urban wastewater treatment plant (GB 18918-2002), and is specifically as follows:
COD j，i ＜50mg/L；NH 3 -N j，i ＜5mg/L；TN j，i ＜15mg/L；TP j，i ＜0.5mg/L
wherein, COD j,i Chemical oxygen demand (mg/L) of effluent water in the j-th day and i-th period of the history of sewage plants, NH 3 -N j,i For the ammonia nitrogen content (mg/L) of effluent water in the j th day and i th period of the history of the sewage plant, TN j，i TP (total nitrogen content (mg/L) of effluent of the jth day and the ith period of the history of a sewage plant) j，i Total phosphorus content (mg/L) of effluent water in the ith period of the j th day of the history of the sewage plant;
and 2, the history of the sewage plant is the total electricity charge of each time period every day, and the total electricity charge is specifically as follows:
Price j，i ＝(P buy，j，i ×F buy，j，i )-(P sell，j，i ×F sell，j，i )
wherein, price j，i The total electric charge of the j th day and i th period of the history of the sewage plant is P buy，j，i For the power purchasing power of the sewage plant in the j-th day and i-th period, F buy，j，i For the historical j-th day and i-th period of the sewage plant, P sell，j，i Selling electric power for photovoltaic residual electricity in the j-th day and i-th period of history of sewage plant, F sell，j，i The price of the electricity selling for the photovoltaic residual electricity in the ith period of the j th day of the history of the sewage plant;
the optimization objective described in step 2 is specifically as follows:
Wherein, price j Is the total electricity charge on the j th day of the history of the sewage plant, P buy，j，i For the power purchasing power of the sewage plant in the j-th day and i-th period, F buy，j，i For the historical j-th day and i-th period of the sewage plant, P sell，j，i Selling electric power for photovoltaic residual electricity in the j-th day and i-th period of history of sewage plant, F sell，j，i The price of the electricity selling for the photovoltaic residual electricity in the ith period of the j th day of the history of the sewage plant;
step 3: training samples are constructed on the basis of the principles described in steps 1 and 2.
Taking the photovoltaic power generation power, the chemical oxygen demand of the inflow water, the ammonia nitrogen content, the total phosphorus content, the industrial electricity price and the power required by the optimized blower in a plurality of periods of the history of the sewage plant as each group of samples, and taking the power required by the optimized blower in a plurality of periods of the next day of the history as a real label corresponding to each group of samples;
step 3, the photovoltaic power generation power, the chemical oxygen demand of the inflow water, the ammonia nitrogen content, the total nitrogen content and the total phosphorus content of the sewage plant in a plurality of days and a plurality of time periods, the industrial electricity price and the electricity power required by the blower after optimization are taken as each group of samples, and the concrete steps are as follows:
Data k ＝(P PV，k ，COD k ，NH 3 -N k ，TN k ，TP k ，F buy，k ，OP BL，k )
P PV，k ＝(P PV,(k-1)*L+1 ，P PV,(k-1)*L+2 ，…，P PV,(k-1)*L+L )
P PV,(k-1)*L+l ＝(P PV，(k-1)*L+l，1 ，P PV，(k-1)*L+l，2 ，…，P PV，(k-1)*L+l，24 )
COD k ＝(COD (k-1)*L+1 ，COD (k-1)*L+2 ，…，COD (k-1)*L+L )
COD (k-1)*L+l ＝(COD (k-1)*L+l，1 ，COD (k-1)*L+l，2 ，…，COD (k-1)*L+l，24 )
NH 3 -N k ＝(NH 3 -N (k-1)*L+1 ，NH 3 -N (k-1)*L+2 ，…，NH 3 -N (k-1)*L+L )
NH 3 -N (k-1)*L+l ＝(NH 3 -N (k-1)*L+l，1 ，NH 3 -N (k-1)*L+l，2 ，…，NH 3 -N (k-1)*L+l,24 )
TN k ＝(TN (k-1)*L+1 ，TN (k-1)*L+2 ，…，TN (k-1)*L+L )
TN (k-1)*L+l ＝(TN (k-1)*L+l，1 ，TN (k-1)*L+l，2 ，…，TN (k-1)*L+l,24 )
TP k ＝(TP (k-1)*L+1 ，TP (k-1)*L+2 ，…，TP (k-1)*L+L )
TP (k-1)*L+l ＝(TP (k-1)*L+l，1 ，TP (k-1)*L+l，2 ，…，TP (k-1)*L+l,24 )
F buy，k ＝(F buy,(k-1)*L+1 ，F buy,(k-1)*L+2 ，…，F buy，(k-1)*L+L )
F buy,(k-1)*L+l ＝(F buy，(k-1)*L+l，1 ，F buy,(k-1)*L+l，2 ，…，F buy，(k-1)*L+l,24 )
OP BL，k ＝(OP BL，(k-1)*L+1 ，OP BL，(k-1)*L+2 ，…，OP BL，(k-1)*L+L )
OP BL，(k-1)*L+l ＝(OP BL，(k-1)*L+l，1 ，OP BL，(k-1)*L+l，2 ，…，OP BL，(k-1)*L+l，24 )
wherein k is [1, N ]]，l∈[1，L]，i∈[1，F]N=315 denotes the total number of samples, l=2 denotes the number of historical days in each group of samples, f=24 denotes the number of time periods per day, k denotes the kth group of samples, P PV，k 、COD k 、NH 3 -N k 、TN k 、TP k 、F buy，k 、OP BL，k Respectively representing the photovoltaic power generation power of the sewage plant, the chemical oxygen demand of the inlet water, the ammonia nitrogen content, the total nitrogen content and the total phosphorus content in the k group of samples, the industrial electricity price, the power required by the optimized blower and P PV，(k-1)*L+l 、COD (k-1)*L+l 、NH 3 -N (k-1)*L+l 、TN (k-1)*L+l 、TP (k-1)*L+l 、F buy,(k-1)*L+l 、OP BL，(k-1)*L+l The method is characterized in that the method comprises the steps of (1) photovoltaic power generation power of a sewage plant on the first historical day in a k group of samples, chemical oxygen demand of inlet water, ammonia nitrogen content, total nitrogen content and total phosphorus content, industrial electricity price, and power sequence required by an optimized blower, and P PV，(k-1)*L+l，i 、COD (k-1)*L+l，i 、NH 3 -N (k-1)*L+l，i 、TN (k-1)*L+l，i 、TP (k-1)*L+l，i 、F buy，(k-1)*L+l，i 、OP BL，(k-1)*L+l，i Photovoltaic power generation power of a sewage plant in the i period in the power sequence required by the blower after optimization on the first historical day, chemical oxygen demand of inlet water, ammonia nitrogen content, total nitrogen content and total phosphorus content, industrial power price and power required by the blower after optimization are obtained;
and 3, the real labels corresponding to each group of samples are as follows:
(oP BL，k,(k-1)*L+L+1，1 ，OP BL,k,(k-1)*L+L+1，2 ，…，OP BL,k，(k-1)*L+L+1,24 )
wherein OP BL，k，(k-1)*L+L+1，i The optimized blower power for the i-th period of historical (k-1) l+l+1 days in the k-th set of samples;
step 4: constructing a convolutional neural network, inputting each group of samples into the convolutional neural network for training to obtain classification labels corresponding to each group of samples, constructing a loss function model by combining the real labels corresponding to each group of samples, and training by a gradient descent method to obtain optimized parameters and then obtaining the convolutional neural network;
And 4, the real labels corresponding to each group of samples are as follows:
(OP BL,k,(k-1)*L+L+1，1 ，OP BL,k,(k-1)*L+L+1，2 ，…，OP BL,k,(k-1)*L+L+1,24 )
wherein OP BL，k，(k-1)*L+L+1，i The optimized blower power for the i-th period of historical (k-1) l+l+1 days in the k-th set of samples;
and 4, the prediction labels corresponding to each group of samples are as follows:
wherein,the predicted output of the power required by the blower after optimizing the ith period of the historic (k-1) th (L+L+1) day in the kth group of samples for the convolutional neural network;
and (4) defining a loss function model as follows:
wherein MSE is mean square error, N is total number of samples, OP BL,k,(k-1)*L+L+1,i As a real tag it is possible to provide a real tag,is a predictive tag;
step 5: performing low-carbon electricity scheduling of the sewage plant by utilizing the convolutional neural network constructed in the step 4;
the method comprises the following specific steps: the method comprises the steps of collecting chemical oxygen demand, ammonia nitrogen content, total nitrogen content and total phosphorus content of inflow water of a sewage plant in each period in real time, calculating the required electric power of a blower in each period every day and the required electric power of the rest equipment except the blower, the irradiation intensity, wind speed, wind direction, temperature and humidity of a place where the sewage plant is located to obtain the photovoltaic power generation power of a photovoltaic power generation system arranged in the sewage plant, the industrial power consumption price of the sewage plant and the photovoltaic surplus electricity selling price of the photovoltaic power plant, obtaining the required electric power of the optimized blower in the corresponding period through processing in the steps 1 and 2, inputting the required electric power of the blower into an optimized convolutional neural network, and predicting to obtain the required electric power of the blower in each period in the next day. The prediction results are shown in Table 4
TABLE 4 convolutional neural network prediction results
The table counts the predicted results of the power required by the blower after the optimization of the sewage plant for 135 days and 24 time periods, and the total of 135×24=3240 results.
In the table, the samples with the real class of grade 1 are predicted to be 2213 in number of the samples with grade 1 through the model, and the prediction result is correct; the number of samples with the real class of grade 1 predicted by the model as grade 2 is 30, and the predicted result is wrong. The error rate of the prediction can be calculated according to the convolutional neural network prediction result to be 3.43%, the prediction accuracy is 96.57%, and both the accuracy and the recall rate indicate that the prediction effect is good.
The computer readable medium is a server workstation;
the server workstation stores a computer program executed by the electronic equipment, and when the computer program runs on the electronic equipment, the electronic equipment executes the steps of the low-carbon electricity utilization scheduling method for the photovoltaic power generation sewage plant.
It should be understood that parts of the specification not specifically set forth herein are all prior art.
It should be understood that the foregoing description of the embodiments is not intended to limit the scope of the invention, but rather to make substitutions and modifications within the scope of the invention as defined by the appended claims without departing from the scope of the invention.
Claims (10)
1. The low-carbon electricity utilization scheduling method for the photovoltaic power generation sewage plant is characterized by comprising the following steps of:
acquiring various water quality parameters of water inflow of a sewage plant in each time period every day, electric power required by a blower, electric power required by the rest equipment except the blower and meteorological data, and calculating to obtain the historical photovoltaic power generation power of a photovoltaic power generation system arranged in the sewage plant in each time period every day; acquiring the current industrial electricity price and the current photovoltaic surplus electricity selling price of the sewage plant in each time period;
constructing constraint conditions and total electricity charge of each time period of the history of the sewage plant, taking minimization of total electricity charge of a plurality of time periods of the history of the sewage plant in each day as an optimization target, taking electric power required by a blower in each time period of the history of the sewage plant as an optimization solving object, and solving through a traversal method to obtain electric power required by the blower after optimization in each time period of the history in each day;
constructing each group of samples and real labels corresponding to each group of samples;
inputting each group of samples into a convolutional neural network for training, and training by a gradient descent method to obtain optimized parameters and then obtaining the convolutional neural network;
and acquiring various water quality parameters of water inflow of the sewage plant in each time period every day, the electric power required by the air blower, the electric power required by the rest equipment except the air blower and meteorological data in real time, calculating to obtain the photovoltaic power generation power of a photovoltaic power generation system arranged in the sewage plant, the industrial electricity price of the sewage plant and the photovoltaic rest electricity selling price, calculating the electric power required by the air blower after optimization of the corresponding time period, and predicting through a convolutional neural network after optimizing the parameters to obtain a prediction result of the electric power required by the air blower after optimization of each time period in the next day.
2. The low-carbon electricity scheduling method for the photovoltaic power generation sewage plant according to claim 1, wherein the method comprises the following steps of:
step 1: acquiring chemical oxygen demand, ammonia nitrogen content, total phosphorus content, blower required power of each time period of history daily and residual equipment required power except the blower of a sewage plant; acquiring meteorological data of each time period of a history of a place where a sewage plant is located, and calculating to obtain photovoltaic power generation power of each time period of the history of a photovoltaic power generation system arranged in the sewage plant; acquiring the current industrial electricity price and the current photovoltaic surplus electricity selling price of the sewage plant in each time period;
step 2: according to the electric power required by the blower of each time period of the history of the sewage plant, the electric power required by all equipment except the blower and the photovoltaic power generation power, the electric power purchased of each time period of the history of the sewage plant and the photovoltaic residual electricity selling electric power are calculated respectively, the constraint conditions are built by combining the chemical oxygen demand of water, the ammonia nitrogen content, the total nitrogen content and the total phosphorus content of each time period of the history of the sewage plant, the electric power purchased of each time period of the history of the sewage plant, the industrial electric price, the photovoltaic residual electricity selling electric power of each time period of the history of the sewage plant and the photovoltaic residual electricity selling electric price, the total electric charge of each time period of the history of the sewage plant is built, the total electric charge of a plurality of time periods of each day of the history of the sewage plant is minimized, the electric power required by the blower of each time period of each day of the history of the sewage plant is used as an optimization solving object, and the electric power required by the blower of each time period of each day of the history of the sewage plant is obtained according to the following method: firstly, dividing the power consumption of the blower of the sewage plant into different grades according to the given power and the power adjusting range of the blower, solving the power consumption of the blower after optimizing each time period every day through a traversal method;
Step 3: taking the photovoltaic power generation power, the chemical oxygen demand of the inflow water, the ammonia nitrogen content, the total phosphorus content, the industrial electricity price and the power required by the optimized blower in a plurality of periods of the history of the sewage plant as each group of samples, and taking the power required by the optimized blower in a plurality of periods of the next day of the history as a real label corresponding to each group of samples;
step 4: constructing a convolutional neural network, inputting each group of samples into the convolutional neural network for training to obtain classification labels corresponding to each group of samples, constructing a loss function model by combining the real labels corresponding to each group of samples, and training by a gradient descent method to obtain optimized parameters and then obtaining the convolutional neural network;
step 5: the method comprises the steps of collecting chemical oxygen demand, ammonia nitrogen content, total phosphorus content of inlet water of a sewage plant in each period in real time, calculating electric power required by blowers in each period every day, electric power required by residual equipment except the blowers, irradiation intensity and temperature of a place where the sewage plant is located to obtain photovoltaic power generation power of a photovoltaic power generation system arranged in the sewage plant, industrial electricity price of the sewage plant and electricity selling price of photovoltaic residual electricity, obtaining electric power required by optimized blowers in corresponding periods through processing in steps 1 and 2, inputting the electric power required by the optimized blowers in each period into a convolutional neural network for prediction, and obtaining a prediction result of the electric power required by the optimized blowers in each period in the next day.
3. The low-carbon electricity scheduling method for the photovoltaic power generation sewage plant according to claim 2, wherein the method comprises the following steps of:
the meteorological data in step 1 comprises: irradiation intensity, ambient temperature;
and (2) calculating the photovoltaic power generation power of each period of each day of the history of the photovoltaic power generation system arranged in the sewage plant, wherein the photovoltaic power generation power is specifically as follows:
wherein, the standard test conditions;
P PV,j,i a historical jth day i period representing a photovoltaic power generation system provided in a sewage plantIs a photovoltaic power generation power of (a);
P * the nominal direct current power of the photovoltaic generator set in the standard state is represented;
G i,t indicating the irradiation intensity of the sewage plant in the j th day and i th period of the history;
G * representing the total irradiation intensity of the sun in a standard state;
k represents a relative change coefficient of generated power due to a change in panel temperature;
T c,j,i representing the temperature of the photovoltaic cell panel in the operation state of the jth period of the history;
the temperature of the photovoltaic cell panel in the standard state is represented;
f G representing a loss coefficient of the photovoltaic module related to the incident irradiation level, wherein the loss coefficient is in a value range of 0-1;
f DC representing all loss coefficients in the direct current power output process, wherein the value range is between 0 and 1;
f AC all loss coefficients in the process of converting nominal direct current power into alternating current output are represented, and the value range is between 0 and 1;
η INV The conversion efficiency of the inverter is represented, and the value range is 0-1;
the relationship between the photovoltaic panel temperature of each time period of the history of the sewage plant and the ambient temperature of each time period of the history of the sewage plant is as follows:
wherein T is a,j,i The environmental temperature of the jth day and the ith period of the jth day of the history of the sewage plant is obtained; NOCT is the nominal operating cell temperature, defined as exposure of the photovoltaic module to solar irradiance of 800Wm -2 The temperature reached by the battery when the ambient temperature is 20 ℃ and the wind speed is 1m/s,
G t,j,i total solar irradiance for the historical jth day i period.
4. The low-carbon electricity scheduling method for the photovoltaic power generation sewage plant according to claim 3, wherein the method comprises the following steps of:
and step 2, calculating the electricity purchasing power of the sewage plant history in each time period every day, wherein the electricity purchasing power is specifically as follows:
wherein j is E [1, D]，i∈[1,F]D represents the number of historical days, F represents the number of time periods per day, P buy,j,i For the power purchase of the j-th day and i-th period of the history of the sewage plant, P exc BL,j,i Power required for all equipment except the blower in the jth and ith period of history of sewage plant, P PV,j,i The photovoltaic power generation power P of the ith period of the jth day of the history of the sewage plant BL,j,i And (5) the electric power required by the blower in the ith period of the jth day of the history of the sewage plant.
5. The low-carbon electricity scheduling method for the photovoltaic power generation sewage plant according to claim 4, wherein the method comprises the following steps of:
and step 2, calculating the photovoltaic surplus electricity selling power of each period of the history of the sewage plant every day, wherein the photovoltaic surplus electricity selling power is specifically as follows:
wherein P is sell,j,i Selling electric power for photovoltaic residual electricity in the j-th day and i-th period of history of sewage plant, P exc BL,j,i Power required for all equipment except the blower in the jth and ith period of history of sewage plant, P PV,j,i The photovoltaic power generation power P of the ith period of the jth day of the history of the sewage plant BL,j,i And (5) the electric power required by the blower in the ith period of the jth day of the history of the sewage plant.
6. The low-carbon electricity scheduling method for the photovoltaic power generation sewage plant according to claim 5, wherein the method comprises the following steps of:
the construction constraint conditions in the step 2 are specifically as follows:
COD j,i <α；NH 3 -N j,i <β；TN j,i <γ；TP j,i <δ
wherein, COD j,i Effluent chemical oxygen demand, NH, for the j-th day and i-th period of a sewage plant history 3 -N j,i For the ammonia nitrogen content and TN of effluent of the j th day and i th period of the history of the sewage plant j,i For the total nitrogen content, TP, of effluent water in the j-th day and i-th period of the history of a sewage plant j,i For the total phosphorus content of the effluent of the j-th day and i-th period of the history of the sewage plant, alpha, beta, gamma and delta are respectively the highest limit values of the chemical oxygen demand of the effluent, the ammonia nitrogen content of the effluent, the total nitrogen content of the effluent and the total phosphorus content of the effluent of the sewage plant;
Preferably, the total electricity charge of each period of each day of the sewage plant history in step 2 is as follows:
Price j,i ＝(P buy,j,i ×F buy,j,i )-(P sell,j,i ×F sell,j,i )
wherein Pricr j,i The total electric charge of the j th day and i th period of the history of the sewage plant is P buy,j,i For the power purchasing power of the sewage plant in the j-th day and i-th period, F buy,j,i For the historical j-th day and i-th period of the sewage plant, P sell,j,i Selling electric power for photovoltaic residual electricity in the j-th day and i-th period of history of sewage plant, F sell,j,i And (5) selling electricity price for the photovoltaic residual electricity in the ith period of the j th day of the history of the sewage plant.
7. The low-carbon electricity scheduling method for the photovoltaic power generation sewage plant according to claim 6, wherein the method comprises the following steps of:
the optimization objective described in step 2 is specifically as follows:
wherein the method comprises the steps of，Price j Is the total electricity charge on the j th day of the history of the sewage plant, P buy,j,i For the power purchasing power of the sewage plant in the j-th day and i-th period, F buy,j,i For the historical j-th day and i-th period of the sewage plant, P sell,j,i Selling electric power for photovoltaic residual electricity in the j-th day and i-th period of history of sewage plant, F sell,j,i And (5) selling electricity price for the photovoltaic residual electricity in the ith period of the j th day of the history of the sewage plant.
8. The low-carbon electricity scheduling method for the photovoltaic power generation sewage plant according to claim 7, wherein the method comprises the following steps of:
each set of samples described in step 3 is as follows:
Data k ＝(P PV,k ,COD k ,NH 3 -N k ,TN k ,TP k ,F buy,k ,OP BL,k )
P PV,k ＝(P PV,(k-1)*L+1 ,P Pv,(k-1)*L+2 ,…,P PV,(k-1)*L+L )
P PV,(k-1)*L+l ＝(P PV,(k-1)*l+l,1 ,P PV,(k-1)*L+l,2 ,…,P PV,(k-1)*L+l,24 )
COD k ＝(COD (k-1)*L+1 ,COD (k-1)*L+2 ,…,COD (k-1)*L+L )
COD (k-1)*L+l ＝(COD (k-1)*L+l,1 ,COD (k-1)*L+l,2 ,…,COD (k-1)*L+l,24 )
NH 3 -N k ＝(NH 3 -N (k-1)*L+1 ,NH 3 -N (k-1)*L+2 ,…,NH 3 -N (k-1)*L+L )
NH 3 -N (k-1)*L+l ＝(NH 3 -N (k-1)*L+l，1 ,NH 3 -N (k-1)*L+l,2 ,…,NH 3 -N (k-1)*L+l,24 )
TN k ＝(TN (k-1)*l+1 ,TN (k-1)*L+2 ,…,TN (k-1)*L+L )
TN (k-1)*L+l ＝(TN (k-1)*L+l,1 ,TN (k-1)*L+l,2 ,…,TN (k-1)*L+l,24 )
TP k ＝(TP (k-1)*L+1 ,TP (k-1)*L+2 ,…,TP (k-1)*L+L )
TP (k-1)*L+l ＝(TP (k-1)*L+L,1 ,TP (k-1)*L+l,2 ,…,TP (k-1)*L+l,24 )
F buy,k ＝(F buy,(k-1)*L+1 ,F buy,(k-1)*L+2 ,…,F buy,(k-1)*L+L )
F buy,(k-1)*L+l ＝(F buy,(k-1)*L+l,1 ,F buy,(k-1)*L+l,2 ,…,F buy,(k-01)*L+l,24 )
OP BL,k ＝(OP BL,(k-1)*L+1 ,OP BL,(k-1)*L+2 ,…,OP BL,(k-1)*L+L )
OP BL,(k-1)*L+l ＝(OP BL,(k-1)*L+l,1 ,OP BL,(k-1)*L+l,2 ,…,OP BL,(k-1)*L+l,24 )
wherein k is [1, N ]]，l∈[1,L]，i∈[1,F]N represents the total number of samples, L represents the number of historical days in each group of samples, F represents the number of time periods per day, k represents the kth group of samples, P PV,k 、COD k 、NH 3 -N k 、TN k 、TP k 、F buy,k 、OP BL,k Respectively representing the photovoltaic power generation power of the sewage plant, the chemical oxygen demand of the inlet water, the ammonia nitrogen content, the total nitrogen content and the total phosphorus content in the k group of samples, the industrial electricity price, the power required by the optimized blower and P PV,(k-1)*L+l 、COD (k-1)*L+l 、NH 3 -N (k-1)*L+l 、TN (k-1)*L+l 、TP (k-1)*L+l 、F buy,(k-1)*L+l 、OP BL,(k-1)*L+l The method is characterized in that the method comprises the steps of (1) photovoltaic power generation power of a sewage plant on the first historical day in a k group of samples, chemical oxygen demand of inlet water, ammonia nitrogen content, total nitrogen content and total phosphorus content, industrial electricity price, and power sequence required by an optimized blower, and P PV,(k-1)*L+l,i 、COD (k-1)*L+l,i 、NH 3 -N (k-1)*L+l,i 、TN (k-1)*L+l,i 、TP (k-1)*L+l,i 、F buy,(k-1)*L+l,i 、OP BL,(k-1)*L+l,i The optimized blower power sequence for the first historical day of the k group of samplesPhotovoltaic power generation power of a sewage plant, chemical oxygen demand of inflow water, ammonia nitrogen content, total phosphorus content, industrial electricity price and power required by an optimized blower in i time periods;
and 3, the real labels corresponding to each group of samples are as follows:
(OP BL,k,(k-1)*L+L+1,1 ,OP BL,k,(k-1) *L+L+1,2,…,OP BL,k,(k-1)*L+L+1,24 )
wherein OP BL,k,(k-1)*L+L+1,i The power required by the blower after optimization for the i-th period of historical (k-1) th L+L+1 day in the k-th group of samples.
9. The low-carbon electricity scheduling method for the photovoltaic power generation sewage plant according to claim 8, wherein the method comprises the following steps of:
and 4, the real labels corresponding to each group of samples are as follows:
(OP BL,k,(k-1)*L+L+1,1 ,OP BL,k,(k-1)*L+L+1,2 ,…,OP BL,k,(k-1)*L+L+1,24 )
wherein OP BL,k,(k-1)*L+L+1,i The optimized blower power for the i-th period of historical (k-1) l+l+1 days in the k-th set of samples;
And 4, the prediction labels corresponding to each group of samples are as follows:
wherein,the predicted output of the power required by the blower after optimizing the ith period of the historic (k-1) th (L+L+1) day in the kth group of samples for the convolutional neural network;
and (4) defining a loss function model as follows:
wherein MSE is mean square error, N is total number of samples, OP BL,k,(k-1)*L+L+1,i The power required by the blower after optimization for the i-th period of historical (k-1) th L +1 day in the k-th group of samples,predicted output of the blower power required after optimization for the ith period of historical (k-1) l+l+1 days in the kth set of samples for the convolutional neural network.
10. A computer readable medium, characterized in that it stores a computer program for execution by an electronic device, which computer program, when run on the electronic device, causes the electronic device to perform the steps of the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311840019.2A CN117829499A (en) | 2023-12-27 | 2023-12-27 | Low-carbon electricity utilization scheduling method for photovoltaic power generation sewage plant and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311840019.2A CN117829499A (en) | 2023-12-27 | 2023-12-27 | Low-carbon electricity utilization scheduling method for photovoltaic power generation sewage plant and computer readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117829499A true CN117829499A (en) | 2024-04-05 |
Family
ID=90509054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311840019.2A Pending CN117829499A (en) | 2023-12-27 | 2023-12-27 | Low-carbon electricity utilization scheduling method for photovoltaic power generation sewage plant and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117829499A (en) |
-
2023
- 2023-12-27 CN CN202311840019.2A patent/CN117829499A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858759B (en) | Industrial park comprehensive energy balance scheduling method | |
| Piacentino et al. | Sustainable and cost-efficient energy supply and utilisation through innovative concepts and technologies at regional, urban and single-user scales | |
| CN114243694B (en) | Grid-connected micro-grid optimal configuration method considering ladder carbon transaction and demand response | |
| CN111445107A (en) | Multi-objective optimization configuration method for cold-heat-power combined supply type micro-grid | |
| CN102930343A (en) | Energy optimization method for distributed power generation and energy supply system | |
| CN108711878B (en) | Photovoltaic power station multi-type component capacity configuration method considering output characteristics | |
| CN112086998B (en) | Energy optimization scheduling method for direct-current micro-grid in island mode | |
| Sun et al. | Multi-objective robust optimization of multi-energy microgrid with waste treatment | |
| CN110932261A (en) | Multi-energy system combined installation planning method based on global benefit maximization | |
| CN116599148A (en) | Hydrogen-electricity hybrid energy storage two-stage collaborative planning method for new energy consumption | |
| CN115630473A (en) | Sewage treatment plant optimized operation method considering sewage reuse | |
| Chen et al. | Economic and ecological assessment of photovoltaic systems for wastewater treatment plants in China | |
| CN113541195B (en) | Method for consuming high-proportion renewable energy in future power system | |
| CN106026191B (en) | For minimizing the method for abandoning the power displacement electricity assessment of optical quantum photovoltaic power station power generation | |
| CN105896535B (en) | For minimizing the method for the wind power plant Swap of Generation Right electricity assessment for abandoning wind-powered electricity generation amount | |
| Sadullaev et al. | Micro-grid based power supply of remote consumers located away from the centralized power grid | |
| CN117829499A (en) | Low-carbon electricity utilization scheduling method for photovoltaic power generation sewage plant and computer readable medium | |
| CN114139830B (en) | Optimal scheduling method and device for intelligent energy station and electronic equipment | |
| Duarte et al. | Increasing self-sufficiency of a wastewater treatment plant with integrated implementation of anaerobic co-digestion and photovoltaics | |
| CN115907393A (en) | Multi-time scale scheduling method for virtual power plant with long-time energy storage | |
| CN114611793A (en) | Comprehensive energy system optimization method and device considering short-term load prediction | |
| Zhang et al. | Bi-level Optimal Design of Integrated Energy System with Synergy of Renewables, Conversion, Storage and Demand | |
| CN106410780A (en) | New energy source acceptance space discrete probability sequence calculation method | |
| Sun et al. | Optimal scheduling of virtual power plant considering demand side response | |
| Jinglin et al. | Multi-objective Collaborative Planning Method for Micro-energy Systems Considering Thermoelectric Coupling Clusters |
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 |