751 results about "Electricity cost" patented technology

The invention belongs to the technical field of power file rule extraction and change comparison, and particularly relates to a policy document intelligent rule extraction and change comparison method for electricity charge checking, which comprises the following steps: analyzing, reconstructing and optimizing an electricity charge related policy document, and retaining original context and logic level information; designing a core statement recognition Prompt template and a rule extraction and conversion Prompt template, constructing a policy and rule extraction agent, guiding a large language model to recognize core statements, extracting rule element information and forming standardized policy and rule description; according to the method, similar policy rules are retrieved from a historical policy rule description knowledge base, a policy rule comparison agent is constructed, and deep semantic comparison and change analysis are performed on current standardized policy rule description and historical similar policy rule description, so that automatic identification of newly added and modified contents of current rules and historical rules is realized; and a key technical support is provided for automation and intelligentization of electricity charge checking business rule generation.

The invention relates to an electric charge recovery dynamic risk assessment method and system based on dual-channel ensemble learning and dynamic PID regulation and control. The prediction method comprises the following steps: selecting power data of a certain number of enterprises for analysis, and screening Top-15 high contribution features; the XGBoost and the LightGBM are fused by adopting a Stacking integration method, and the arrearage probability of the user is predicted; proposing a tail risk capture mechanism of quantile random forest regression, and predicting the arrearage amount of the arrearage user based on the arrearage probability output by the classification model; and a two-channel joint framework of a classification model and a regression model is constructed, and two-dimensional early warning of arrearage probability prediction and arrearage amount quantitative analysis is realized. A dynamic risk scoring mechanism is constructed according to the arrearage probability of classification prediction and the large-amount arrearage risk of regression quantification, upgrading from a single index to a comprehensive score is completed, a dynamic risk regulation and control mechanism based on PID is provided, and intelligent grading and dynamic early warning of arrearage users are achieved.

The invention relates to the technical field of energy storage control, and discloses a demand control method and system based on industrial and commercial energy storage, and the method comprises the steps: obtaining and carrying out the standardized processing of a real-time load demand, an energy storage state and power grid dispatching data; establishing a load prediction model to generate demand baseline parameters, and constructing a dynamic adjustment rule base; the energy storage output is verified in real time, and the dynamic response trend of the power difference value is analyzed; and generating a demand control index to determine a charging and discharging strategy. The system comprises a load monitoring module, a strategy generation module, a dynamic execution module and a control judgment module which are respectively used for realizing data acquisition and processing, model construction, output verification analysis and strategy judgment functions. According to the scheme, through multi-dimensional data integration, dynamic rule base optimization and multi-constraint coordination technologies, the precision and economical efficiency of industrial and commercial energy storage demand control are improved, the demand electric charge can be effectively reduced, the electric energy utilization rate is improved, and the method is suitable for energy storage management and power grid collaborative optimization of industrial and commercial users.

The invention provides a regional intelligent power utilization method and system based on source-grid-load-storage cooperation and dynamic electricity price. The method comprises the following steps: collecting photovoltaic output, energy storage SOC, load demand and time-of-use electricity price data in real time; determining a corresponding dynamic control mode in combination with the economic target model, the environmental protection target model and the constraint conditions; when the running dynamic control mode is a light storage and charging cooperative arbitrage mode, dynamically determining an energy storage charging and discharging strategy; when the running dynamic control mode is a virtual power plant aggregation mode, forming scheduling capacity by aggregating distributed resources, and responding to a power grid peak regulation instruction; when the running dynamic control mode is a carbon-electricity joint optimization mode, a carbon trading platform is connected, green certificate binding sales is carried out, scheduling capacity is formed through dynamic integration of energy storage charging and discharging strategies and aggregation of distributed resources, the carbon trading platform is connected, green certificate binding sales is carried out, economic benefits are effectively improved, carbon emission is reduced, and the service life of the system is prolonged. And the double-target optimization of the electric cost and the carbon emission is realized.

The invention provides a power marketing archive intelligent management method, which comprises the steps of receiving archive data through a power data acquisition interface, matching an electricity price feature code in an archive based on a real-time electricity price policy identifier, and injecting a version calibration mark into unmatched data; constructing an electricity consumption abnormity prediction model based on the user historical load mode and the environmental factors; when a query request is responded, dynamic penalty parameters are generated based on the user behavior portrait and the rule base; a quantum key distribution path is generated based on a power grid topological structure, and cascade encryption is implemented along physical connection nodes; dynamically associating user operation authority with a power grid operation risk signal, and automatically disabling core operation in a high-risk state; and analyzing archive data in a security isolation environment to drive line loss optimization, electric charge tracing and fault pre-judgment service flow in real time, and outputting feedback archive update based on the service. According to the invention, the safety, reliability and operation efficiency of power marketing archive management are improved.

The invention relates to the technical field of community new energy control, and discloses an orderly and rapid charging new energy control method, which comprises the following steps: collecting photovoltaic output data, power grid voltage / current data, user charging behavior data and battery state parameters in real time; generating a dynamic charging strategy based on the power grid load data, the time-of-use electricity price information, the photovoltaic output fluctuation range and the battery health state evaluation result; generating a corresponding local optimization strategy based on the operation state data of each charging pile; an economic index and a technical index are calculated, and when any index exceeds a preset threshold value, a strategy adjustment instruction is triggered, and a charging mode switching threshold value is updated; an equipment health index is generated by combining inverter temperature, coil coupling efficiency and insulation impedance parameters with historical fault data, and maintenance early warning is triggered when the health index is lower than a safety threshold value. According to the invention, the electricity cost of the user can be reduced on the basis of improving the multi-energy collaborative optimization capability of the charging facility in the residential area.

The invention relates to the technical field of energy storage load scheduling, in particular to an energy storage load scheduling method and system based on multi-objective optimization, and the method comprises the steps: obtaining historical electricity price, load power and renewable energy power generation power data of each time period before the current time as input variables, and carrying out the normalization processing to obtain input data; inputting the input data into an LSTM-Transformer prediction model, and predicting to obtain the power grid electricity price, the load demand and the renewable energy power generation amount in a future time period; establishing a multi-objective optimization model including electric charge cost, operating profit and energy storage life; substituting the prediction data into the multi-objective optimization model, and solving a Pareto frontier based on a multi-objective optimization algorithm to obtain a non-inferior solution set satisfying the multi-objective optimization model; and taking each solution in the non-inferior solution set as input, and screening the solution with the maximum Sharpley value as an optimal energy storage charging and discharging adjustment strategy. By accurately controlling the working state of the energy storage system, the interactive operation mode of the energy storage system and the power grid is optimized.

The invention discloses a home electricity charge optimization method and device based on an improved ant lion algorithm, and relates to the technical field of home electricity utilization optimization, and the method comprises the steps: S1, constructing a home electricity charge model used for calculating the electricity charge of home electricity utilization equipment and a multi-objective optimization function combining a home electricity charge objective function and user dissatisfaction; s2, taking a multi-objective optimization function as a fitness function of an improved ant lion algorithm, and using the improved ant lion algorithm to solve the household electricity charge model; the improved ant lion algorithm uses chaotic mapping to initialize ants and ant lion populations; cauchy variation disturbance is introduced when local optimum is trapped by using Cauchy distribution. According to the invention, by constructing the household electricity charge model, double-target integration of electricity charge expenditure and user experience is formed, and collaborative optimization of electricity charge expenditure and user comfort is realized; the improved ant lion algorithm is used for solving the household electricity charge model, and the defect that a traditional ant lion algorithm is likely to sink into local optimum is overcome.

The invention provides a multi-stage desensitization electricity charge sensitive data protection system, belongs to the technical field of information security in the power industry, and relates to a full-life-cycle protection scheme of sensitive data such as an identity label, account information and contact information in an electricity charge service system. The problems that in the prior art, only simple masking or full-table encryption is carried out on a database layer, the desensitization dimension is single, multiple links are prone to leakage, no role fine-grained desensitization strategy exists, and exported files are difficult to trace are solved. The system comprises a data acquisition source and acquisition layer desensitization, a transmission layer encryption, a storage layer transparent encryption, an API gateway, a desensitization strategy center, a front-end dynamic mask, a watermark export, a log desensitization plug-in and an auditing log module, covers the whole process from data acquisition to log auditing, dynamically regulates and controls data display according to roles, and exports a file embedded identity watermark. And desensitizing the log and reserving operation marks. Full-link leakage prevention, fine-grained permission control and leakage traceability can be realized, and the transformation cost is low.

The invention discloses an energy storage operation optimization method and system based on hierarchical multi-agent reinforcement learning. The method comprises the following steps: firstly, initializing a hierarchical multi-agent reinforcement learning decision framework, and defining an interlayer communication synchronization mechanism; then, designing an upper layer reward function for balancing the electric charge income and the battery life loss cost, and optimizing an upper layer planning strategy; a lower layer reward function integrating current smoothness and budget tracking precision is designed, and a lower layer execution strategy is optimized; and finally, deploying the optimized upper-layer planning strategy and the optimized lower-layer execution strategy to an energy storage scheduling task, generating a charging and discharging power budget by an upper-layer planning agent in a day-ahead scheduling stage, and receiving a budget instruction and performing power adjustment by a lower-layer execution agent. According to the invention, by constructing the hierarchical decision-making architecture, coordinated optimization of short-term economic benefit and long-term life protection of the energy storage equipment is realized.

The invention provides a user electricity larceny suspicion coefficient determination method based on multi-dimensional abnormal feature analysis, and belongs to the technical field of electricity larceny prevention. According to the method, a user electricity stealing identification algorithm applied to an electricity utilization inspection system is provided, and on this basis, multi-dimensional parameters such as user longitudinal electricity utilization behavior characteristics and transverse environment correlation characteristics are creatively fused to construct a comprehensive electricity stealing characteristic index system. And after a significant deviation of an electricity consumption prediction value is found preliminarily, according to multiple characteristic quantities extracted by an index system, an abnormal weight coefficient of each characteristic quantity is dynamically determined and calculated in a combined manner, and finally an accurate electricity stealing suspicion coefficient is generated. According to the invention, potential electricity stealing behaviors can be identified more reliably, and the probability of single-index misinformation is reduced at the same time. The method emphasizes the mining of the abnormal power consumption mode of the user and the relationship between the abnormal power consumption mode and multiple factors, fully utilizes the alarm event and the electric charge settlement data of the local metering device, and significantly reduces the dependence on massive complex modeling.

The present application relates to a method, apparatus, computer device, and storage medium for determining a smart meter fault. The method includes: obtaining a data curve measured by the smart meter within a preset time period, where the data curve includes first voltage curves of multiple cycles and current curves corresponding to each first voltage curve. Extracting a preset number of first voltage curves from the data curve as target voltage curves, where the target voltage curves are the first voltage curves corresponding to the current curves with current amplitudes less than a preset value. Determining a target value of the voltage measurement error of the smart meter according to the target voltage curves. Thus, the error value of the voltage measurement caused by the fault of the smart meter is determined, and through this error value, the fault condition of the voltage is quantified, thereby realizing the determination of the meter fault. This enables the staff to repair or replace the smart meter in a timely manner, avoiding situations such as incorrect user electricity bill measurement or power outage caused by meter faults.

The invention provides a cross-day two-stage random scheduling method for an industrial park integrated energy system, and the method comprises the steps: fitting the output fluctuation characteristics of new energy power generation equipment in a cross-day time scale based on historical data, and constructing an uncertainty scene set containing a new energy prediction error; establishing a cross-day two-stage stochastic programming model; according to the two-stage model, an optimal scheduling scheme is solved so as to minimize the overall operation cost, and the operation cost comprises the demand electric charge, the electricity purchase electric charge, the new energy power abandoning cost, the unit start-stop cost and the standby penalty cost; and on the basis of tie line power constraint and dynamic response characteristics of the multi-energy coupling equipment, feasibility verification and rolling optimization adjustment are performed on the scheduling scheme. According to the method, the new energy consumption capability of the industrial park integrated energy system under the cross-day time scale can be effectively improved, the total operation cost is reduced, and collaborative scheduling of demand cost optimization and spot market participation is realized.

The invention discloses a glass factory load low-carbon regulation and control method considering capacity compensation and carbon quota, and aims to realize refined carbon emission control and flexible scheduling in the production process of a glass factory. By fusing multi-dimensional input of historical load power, load change rate, environment temperature, humidity, wind speed, electricity price, time and the like and utilizing an STFormer architecture to model a complex time dependency relationship, a kilowatt-hour electricity carbon emission factor in a future time period is predicted, and prior information is provided for low-carbon scheduling; with minimization of carbon emission and electric charge cost and maximization of capacity income as targets, a future load scheduling strategy is optimized under constraints of carbon quota, an electric power regulation range and equipment operation; and globally searching an optimal load control scheme through a quantum particle swarm algorithm, and generating a multi-scene-oriented dynamic regulation and control strategy under the constraints of a multi-target fitness function and a penalty mechanism. The method not only improves the precision and robustness of carbon factor prediction, but also realizes flexible scheduling of the glass factory load driven by carbon economy.

The invention discloses a method, a system, a medium and equipment for detecting abnormal data of electric charge, and belongs to the field of machine learning, and the method comprises the steps: collecting a historical power utilization data set of a user; based on a preset Affinity Propagation clustering algorithm, clustering division is carried out on the historical electricity consumption data set, and clustering clusters representing different electricity consumption behavior modes and clustering center parameters of the clustering clusters are obtained; recursively constructing an isolated tree for each cluster through a preset isolated forest algorithm, and obtaining a segmentation rule parameter of each isolated tree; integrating each clustering center parameter and a segmentation rule parameter of the isolated tree, and constructing an anomaly detection model; and detecting the current power consumption data according to the anomaly detection model, and outputting a detection result. Therefore, by implementing the method and the device, the problem of low abnormal electricity charge detection precision in a complex electricity consumption scene in the prior art can be solved.

The invention belongs to the technical field of intelligent electric charge questions and answers, and particularly relates to a hierarchical knowledge network construction and retrieval method for intelligent electric charge questions and answers. The invention provides an iterative adaptive enhanced RAG method, based on a hierarchical knowledge network, information retrieved by a first round of problems is used as a knowledge carrier, newly retrieved information is continuously updated into initialized information in subsequent multi-round iterations, information is adaptively collected from the perspective of knowledge increase, and the information retrieval efficiency is improved. New knowledge and collected knowledge are flexibly integrated, and the problem that information interaction among different retrieval steps is insufficient is solved; in addition, a self-adaptive exploration stopping strategy is formulated, uncertain active retrieval is replaced, time deviation of active retrieval prediction is effectively avoided, and continuous knowledge increase is ensured.

The invention discloses a photovoltaic-heat pump cooperative energy storage system defrosting control method, device and system, electronic equipment and a storage medium, the photovoltaic-heat pump cooperative energy storage system comprises a heat storage module, a heat circulation pipeline and a plurality of electric heating modules, and the heat storage module outputs heat energy to an evaporator through the heat circulation pipeline for defrosting. On one hand, the photovoltaic unit supplies power to the electric heating module for defrosting, and the heat storage module outputs heat energy for defrosting, so that the dependence of defrosting on a power grid can be reduced, the supply proportion of the photovoltaic unit in defrosting energy consumption is increased, the electric charge expenditure is saved for a user, the carbon emission is reduced, the peak load of the power grid is relieved, and the energy utilization rate of the photovoltaic unit is increased; partial defrosting can be achieved by supplying power to part of the electric heating modules through the photovoltaic unit, global defrosting is achieved by outputting heat energy through the heat storage module, different defrosting modes are adopted in different frosting states, the energy efficiency of the system is improved, and defrosting can be achieved through the heat storage module when the generating capacity of the photovoltaic unit is low in extreme weather.

The invention relates to the technical field of control and adjustment, in particular to an energy storage configuration point-based power consumption cost calculation method, which comprises the following steps of: acquiring power supply data, renewable energy output fluctuation data and computing power load fluctuation data, and generating a coupling influence feature vector; splicing the electricity price features and the coupling features to form configuration optimization input features; the input features are processed through a dual-objective optimization model, and robustness configuration parameters and economical efficiency operation parameters are output; calculating the reserve cost compensation amount of the extreme scene based on the robustness parameter, and calculating the power purchase cost and maintenance cost of the power grid based on the economical efficiency parameter; and aggregating the cost component and outputting a power consumption cost calculation result. According to the method, the interactive influence of wind-light fluctuation and load mutation is quantified through coupling features, the target conflict between robustness and economy is coordinated by adopting the Pareto algorithm, the risk compensation amount is generated in combination with a pressure test, a feature updating mechanism is fed back in a closed loop mode, and the problem that the operation cost deviates from expectation due to quantization deviation of an existing model is solved.

The invention relates to an intelligent charging station resource scheduling method and system based on data processing, and relates to the field of the vehicle charging technology, and the method comprises the steps: obtaining the remaining energy storage electric quantity; determining required supplementary electric quantity according to the full-load energy storage electric quantity and the residual energy storage electric quantity; determining energy storage demand duration according to the energy storage efficiency and the demand supplementary electric quantity; constructing a permissible energy storage time period and delimiting a unit interval; constructing a historical interval, determining a similar interval in the historical interval according to each unit interval, and determining a historical energy storage electricity price in the similar interval; combining each unit interval according to the energy storage demand duration to construct a simulated energy storage scheme, and determining the overall electricity price of the scheme according to each historical energy storage electricity price in each simulated energy storage scheme; and defining the simulation energy storage scheme corresponding to the scheme overall electricity price with the minimum numerical value as an effective energy storage scheme, and controlling the charging station to perform energy storage scheduling in a unit interval in the effective energy storage scheme. The charging station has the effect of reducing the power utilization cost of the charging station.

The invention provides a multi-energy collaborative grid-connected system containing roof photovoltaic, charging piles and energy storage cabinets. The multi-energy collaborative grid-connected system comprises a data acquisition module, a data processing module, a prediction module, an energy management strategy module, an execution control module, a user interface module and a safety management module. Through a prediction model driven by real-time data and a rolling optimization strategy, the system can quickly respond to photovoltaic power generation fluctuation and load change, the energy scheduling precision is remarkably improved, the time-of-use electricity price characteristics are combined, low-price electricity is fully utilized for energy storage and charging in the low ebb period, high-price electricity dependence is reduced in the peak period, meanwhile, the energy storage and charging and discharging efficiency is optimized, and the energy storage and charging efficiency is improved. And multi-energy collaborative management realizes maximum consumption of photovoltaic power generation, optimization of energy storage charging and discharging efficiency and reasonable power distribution of the charging pile, and the overall energy utilization rate is improved.

The invention provides an intelligent control method for a pump set, which belongs to the technical field of pump set control and comprises the following steps of: acquiring operation data and electricity price time period data of the pump set in real time; inputting the preprocessed data into a pre-trained liquid level prediction model to obtain liquid level prediction data; inputting the preprocessed data, the liquid level prediction data and the electricity price time period data into a pre-trained strategy optimization model to obtain a control instruction; the operation state of the pump set is controlled through the control instruction. Compared with the prior art, the control method has the advantages that the electricity price time period data is combined, the operation strategy of the pump set is dynamically adjusted by responding to the time-phased electricity price data, the electricity charge expenditure is reduced, and the problem of poor economical efficiency in the prior art is solved; and meanwhile, the control method is combined with liquid level prediction data to predict future working conditions, so that control parameters are adjusted, and the effects of avoiding liquid level abnormity and prolonging the service life of equipment are achieved. The system has the same beneficial effects.

The invention belongs to the technical field of refrigeration control of refrigeration houses, and provides an energy-saving method and device for ice slurry storage circulation in a refrigeration house and a medium, and the method comprises the following steps: monitoring operation parameters of the refrigeration house in real time, and obtaining and analyzing data to predict a cold load demand; in a low-ebb electricity price period, refrigerating parameters are automatically adjusted according to cold load prediction and cold storage tank reserves, and ice making is implemented; when the temperature of the refrigeration house is close to a set threshold value, energy-saving regulation and control are performed in combination with a prediction result According to the cold load and reserve conditions, different working condition stages of the refrigeration house are determined, and finally a circulation regulation and control result is generated based on the flow-state ice circulation requirement; according to the method, through cold load prediction and accurate regulation and control according to different working conditions, invalid operation and excessive refrigeration of refrigeration equipment are avoided, energy consumption is effectively reduced, ice making and cold storage are achieved through the low-ebb electricity price, electric energy is reasonably utilized, and the electricity utilization cost is reduced.

The invention provides an optimal control method and system for power system carbon emission, and relates to the technical field of carbon emission optimal control, and the method comprises the steps: collecting a real-time load, a power grid carbon emission factor and time-of-use electricity price, employing a clustering algorithm to automatically divide a power utilization period, carrying out the modeling of the dynamic change of the carbon emission factor at different time periods, and carrying out the optimal control of the power system carbon emission. An energy storage charging and discharging path is optimized according to the principle of peak period discharging, smoothing and valley period charging, and energy loss and the health state of an energy storage unit in the charging and discharging process are included in carbon emission accounting; and meanwhile, a multi-target collaborative optimization model is constructed to realize tradeoff optimization of the total carbon emission and the power consumption cost, so that the time sequence characteristics of the actual production load and the power grid carbon emission factor are accurately matched, the carbon emission collection precision and the scheduling optimization level are improved, and the carbon emission and the energy consumption cost in the production cycle are effectively reduced.

The invention discloses an arrearage risk management and control method, device and equipment. The method comprises the steps of firstly determining a target risk power consumer; predicting arrearage probability distribution and payment probability distribution of the target risk power consumer through a hybrid density network based on the feature data, the account balance and the step tariff use information of the target risk power consumer; determining an arrearage risk early warning time node corresponding to the target risk power user based on the arrearage probability distribution, and generating a collection prompt strategy corresponding to the target risk power user based on the payment probability distribution; and before the time reaches the arrearage risk early warning time node, performing electric charge collection prompting on the target risk power user based on the collection prompting strategy. According to the technical scheme, based on the arrearage probability distribution and the payment probability distribution predicted by the mixed density network, the occurrence probability of the arrearage behavior and the payment behavior of the user is predicted on the time scale, so that arrearage risk management and control are more finely realized, and the management and control effectiveness of the arrearage risk is improved.

The invention discloses an industrial and commercial electric charge optimized charging method based on big data analysis, and the method comprises the following steps: S1, multi-source data collection and preprocessing: collecting power utilization data of industrial and commercial users, user equipment operation logs and block chain node transaction data, and constructing a multi-dimensional data set; s2, feature extraction and completion; s3, dynamic prediction and optimization; s4, generating a personalized strategy; s5, performing feedback driving iterative optimization; the invention belongs to the technical field of power system optimization, and aims to solve the problem that power grid load data, user equipment operation logs and block chain transaction data are dispersed and independent and lack of effective integration in the prior art. The method has the technical effects that through a complete chain of data integration, feature fusion, dynamic optimization, credible execution and closed-loop iteration, full-period intelligent optimization of industrial and commercial electricity charges is realized, and the method has economical efficiency, stability and user friendliness.

The invention provides a battery replacement management method and system. Whether the battery is abnormal or not is judged according to the battery parameters including the real-time position parameters of the battery every other time interval, early warning operation is performed accordingly, the abnormal battery is handled in time, and the safety of the battery and use of a user is improved; the method comprises the following steps: when batteries of a plurality of compartments of a battery replacement cabinet request to be charged, controlling the battery of only one compartment of the battery replacement cabinet to be electrified at the same moment to ensure the accuracy of battery charging parameters, judging the billing time according to the battery electric quantity and the charging current of the batteries, and calculating the current cost according to the electric charge parameters. Under the condition of ensuring the income of the operator, the unreasonable cost of the user is reduced, and the use experience of the user is improved.

The invention provides a wind and light storage micro-grid optimization scheduling method and system containing small hydropower storage, and the method comprises the steps: obtaining historical operation data, and carrying out the prediction according to the historical operation data, and obtaining a full-dimension prediction data set; according to the full-dimension prediction data set, constructing a multi-objective optimization model with the goal of minimizing residual load, minimizing power abandoning cost, minimizing cascade water abandoning amount, maximizing green energy collaborative utilization efficiency and minimizing time weighted voltage-power comprehensive error; and solving the multi-objective optimization model by adopting a hybrid optimization algorithm fused by a Hanniac optimization algorithm and an improved sparrow search algorithm to obtain a final output. According to the invention, efficient consumption of green energy can be realized, the electricity abandoning phenomenon is reduced, carbon emission is reduced, and the stability, economical efficiency and environmental protection property of a power system are improved.

The invention discloses a multi-time-scale layered regulation and control method for a combined heat and power generation system considering light-storage-biomass collaboration, belongs to the technical field of power distribution network collaboration, and comprises the following steps: establishing a light-storage-biomass collaboration combined heat and power generation system model, and constructing cross-time-period energy storage constraints of a biogas digester biomass energy storage model and an energy storage battery model; a day-ahead-day-intra-day two-stage multi-time-scale layered regulation and control framework of a light-storage-biomass collaborative combined heat and power generation system is established, the comprehensive power utilization cost of the CHP system is minimized in the day-ahead stage of the upper layer, and the power deviation of photovoltaic power generation is reduced in the day-intra model of the lower layer; an intra-day rolling correction method based on model predictive control is provided, a light-storage-biomass collaborative combined heat and power generation system model is converted into a state-space equation, and dynamic compensation is performed by adopting short-time scale predictive information according to the predictive deviation of photovoltaic output and load demand in actual operation, so that the predictive deviation of the photovoltaic output and the load demand in actual operation is corrected. The problems that renewable energy is difficult to fully consume and the power of the power distribution network fluctuates are effectively solved.

The invention discloses a building air conditioner energy consumption-electric charge-comfort level intelligent control method based on MMOE and ParetoMTL, and the method comprises the following steps: (1) collecting the cooling load data of a large commercial building air conditioner, carrying out the abnormal value detection, and completing the normalization preprocessing; (2) constructing an environment-price-behavior multi-source time sequence data set and performing grading standardization; (3) dividing a training set, a verification set and a test set according to building grouping; (4) completing feature fusion and realizing task decoupling under cooperative constraint by using an MMOE mechanism; (5) jointly training a three-branch expert network, an MLP gating network and a PCGrad shared parameter optimization model; (6) generating a multi-task prediction and Pareto solution set on the test set; and (7) evaluating prediction performance and trade-off efficiency by using a plurality of indexes. According to the method, multi-target conflict, physical consistency and Pareto solution set missing difficulty can be effectively solved, and a new scheme is provided for demand response HVAC intelligent control.

The invention discloses an energy storage system combined with a supercritical carbon dioxide conveying pipeline and a control method of the energy storage system. The energy storage system comprises a gas storage unit, an energy storage unit, a supercritical carbon dioxide conveying pipeline and an energy release unit which are sequentially connected in a closed loop mode in the conveying direction of a carbon dioxide working medium, and a condensation unit is connected between the energy storage unit and the supercritical carbon dioxide conveying pipeline. A throttling unit is connected between the supercritical carbon dioxide conveying pipeline and the energy releasing unit, and a cold energy circulating unit is connected between the condensing unit and the throttling unit; the cold energy circulation unit is configured to be used for absorbing and storing cold energy from the throttling unit in the energy release stage and further used for inputting the stored cold energy into the condensation unit in the energy storage stage. According to the scheme, the investment construction cost and the operation cost of the energy storage system can be reduced, safe and long-time energy storage can be provided for oil and gas exploitation, and then the electricity utilization cost of oil and gas exploitation is reduced.