271 results about "Cooling load" patented technology

The invention belongs to the technical field of intelligent building energy management, and particularly discloses and provides a dual-mode cold storage air conditioning system based on human flow dynamic cooperative regulation, which comprises the following steps: acquiring dynamic human flow thermodynamic diagram data in real time, and accurately calculating a multi-region linkage cold load demand value based on a density change correlation coefficient and a heat conduction model; the real-time sensing of the flow density fluctuation and the dynamic refrigeration demand matching are realized; the phase change state of the coolant of the cold storage tank and the power consumption data of the refrigerating unit are collected in real time, the cold storage release proportion, the refrigerating power increment and other key parameters are dynamically adjusted, and the energy utilization rate is increased; the inherent defect of non-uniform cold and heat in zone control is overcome by calculating inter-zone cooling capacity migration parameters; temperature feedback data and a people flow thermodynamic diagram are collected in real time, the proportionality coefficient of the fan rotating speed and the air valve opening degree is dynamically adjusted, a closed-loop learning mechanism is formed, and the matching precision of a temperature control strategy and people flow distribution is continuously optimized.

The invention provides a high-efficiency control method and system for a central air conditioner refrigeration machine room, and relates to the technical field of automatic control, and the method comprises the steps: 1, obtaining chilled water supply and return water temperature difference and flow data, and calculating the dynamic cold load demand of a building in combination with the personnel distribution thermal imaging data of each floor; and 2, on the basis of the dynamic cooling load requirement, a dynamic adjustment model for the number of running water chilling units is built, matching degree calculation is conducted on the actual cooling load value and the single refrigerating capacity of the water chilling units through a fuzzy PID control algorithm, and a final unit running combination scheme is generated. By calculating the cooling load requirement, dynamically adjusting the operation parameters of the water chilling unit, the chilled water pump and the cooling tower and balancing the equipment operation time, the system energy efficiency is effectively improved, the energy consumption and the operation and maintenance cost are reduced, and stable operation of the refrigerating system is guaranteed.

The invention discloses an integrated energy load prediction method and system based on modal decomposition and TCN-Transform fusion, and aims to solve the key problems of low prediction precision, insufficient utilization of meteorological factor and load correlation, insufficient optimization of a model structure and the like in integrated energy system load prediction. The method comprises the following steps: comprehensively acquiring electric load, cold load, thermal load and various meteorological data, acquiring different types of data by adopting a special device, and then preprocessing the data; using a maximum information coefficient correlation analysis method to screen remarkably related meteorological features; determining an optimal decomposition parameter in combination with variational mode decomposition and a crown porcupine optimization algorithm; a prediction model fusing TCN and Transform advantages is constructed, and the structure is optimized according to load prediction characteristics; the precision and stability of load prediction of the integrated energy system are remarkably improved, the relation between the integrated energy load and external factors is reflected more comprehensively, and a reliable load prediction basis is provided for optimized operation and management of the integrated energy system.

The invention discloses an air conditioner resource allocation method and system based on a cold accumulation prediction algorithm, and relates to the field of air conditioner cold accumulation, and the method comprises the steps: collecting historical load operation data of an air conditioner, analyzing the historical load operation data through employing a grey relational analysis algorithm, and constructing a cold load prediction model in combination with the cold accumulation prediction algorithm; training the cold load prediction model by using a back propagation neural network algorithm, inputting load operation data collected in real time into the trained cold load prediction model, and outputting a cold load prediction result; and in combination with the cooling load prediction result and the electricity price information, an air conditioner resource allocation strategy is formulated, and a model prediction control algorithm is used for optimizing the allocation strategy. Through integration of the load prediction technology and the real-time electricity price information, the cold load demand of the whole day can be accurately predicted, energy waste is reduced, the energy utilization efficiency is improved, the dynamic electricity price market can be responded, and economic maximization is achieved.

The invention relates to a central air conditioner energy consumption optimization control method and system, electronic equipment and a storage medium, and the method comprises the steps that characteristic parameters of load calculation are obtained, and according to the characteristic parameters, the cooling load requirements of a central air conditioner under different working conditions are calculated through a dynamic load calculation model; acquiring real-time operation data of the central air conditioner; establishing a digital simulation model of the central air conditioner based on the cooling load demand and the operation data, and calculating the energy consumption distribution of each device of the central air conditioner under different working conditions through the digital simulation model; with the overall energy efficiency optimization of the central air conditioner as the target, the optimal operation parameter combination of the central air conditioner is obtained through an intelligent optimization algorithm; and synchronously displaying the operation data of the central air conditioner, the energy consumption distribution of each device and the optimal operation parameter combination through a visual interface, and executing an optimized operation strategy according to a user instruction based on the optimal operation parameter combination. According to the method, the accuracy of energy consumption calculation is improved, and the overall energy consumption of the central air conditioner is reduced.

The invention is suitable for the technical field of intelligent control, and discloses a water cooling control method, system and device and a medium. Based on the preprocessed data, constructing a thermal load trend prediction model based on LSTM to obtain a cold load prediction value; based on the cold load prediction value, a PID adjusting signal is generated in combination with the temperature error value; based on the PID adjusting signal, a water pump target frequency instruction is obtained in combination with the cooling load predicted value; based on the water pump target frequency instruction, a valve target opening instruction is obtained in combination with the actually-measured water flow; based on the valve target opening instruction, the fault alarm and emergency instruction is generated, the preset emergency measures are executed, the PID control parameters are updated, the performance evaluation report and the feedback information are obtained, and the response speed, the operation stability and the autonomous decision-making capacity of the water cooling system under the dynamic load and abnormal working conditions are improved.

The invention provides a power transformer electromagnetic loss control method and device in an intelligent power grid environment, and relates to the field of intelligent power grids, and the method comprises the steps: carrying out the cooling demand prediction of a transformer according to a predicted power load sequence and a space temperature sequence, and outputting a predicted cooling load sequence; and with meeting of the predicted cooling load sequence as a constraint and minimization of energy consumption and oil temperature fluctuation as optimization targets, cooling parameters of the forced oil cooling device are optimized, an optimal cooling parameter sequence is output, and the forced oil cooling device is controlled to dissipate heat of the transformer. The method aims to solve the technical problems that a traditional control method lacks cooling strategy dynamic adjustment capacity, temperature rise abnormity is prone to occurring in a high-load or high-temperature environment, transformer iron core loss and winding loss are remarkably increased, and electromagnetic loss is high, accurate and efficient cooling control can be achieved, the electromagnetic loss is effectively reduced, and the service life of a transformer is prolonged. And the operation efficiency and stability of the transformer are improved.

The invention discloses a new energy building integration energy-saving design analysis method, and relates to the technical field of new energy building integration, and the method comprises the following steps: carrying out the time sequence alignment and unit normalization processing of collected heat flow data, temperature rise data and power output data; according to the heat conduction characteristic of the heat conduction structure and the thermal inertia parameters of the building enclosure structure, a heat flux track and a thermal response profile with a unified thermal resistance reference axis are constructed; and based on the heat flux track and the thermal response profile, extracting a reverse heat flux strength parameter and a heat flux continuous influence duration parameter, and combining the parameters with a temperature control target and a heat conduction structure attribute set in the building to construct a reverse heat conduction interference atlas for judging the heat conduction interference degree of the cold load in the building. The problem of cold load misjudgment caused by the fact that photovoltaic heat is transmitted through a high-heat-conduction structure is solved, and cold and heat conduction accurate recognition and energy consumption dynamic regulation and control are achieved.

The invention relates to a data center equipment type selection method based on electrical and heating ventilation load linkage, and belongs to the technical field of data center infrastructure design. The model selection method comprises the steps of setting basic data, obtaining the number of machine rooms and the number of IT devices in a single machine room, obtaining the total power of the IT devices, setting an energy efficiency index set value, obtaining the project power consumption scale, obtaining the total cooling load, selecting models of air conditioners at the tail ends of the machine rooms and substations, selecting models of water chilling units, selecting models of heat exchangers, selecting models of cooling water pumps and chilled water pumps and selecting models of cooling towers. And obtaining the total power of the air conditioner, obtaining an energy efficiency index accounting value, and carrying out PUE verification. According to the method, through closed-loop iteration of electrical load-heating and ventilation load-PUE, model selection and quantity selection of all key equipment are completed at a time; professional splitting, repeated adjustment and modification and capacity redundancy caused by traditional serial design are avoided, the design period is remarkably shortened, and initial investment is reduced.

The invention relates to the technical field of electrical performance testing, in particular to a method and system for measuring loss of an inductance winding, and the method comprises the following steps: applying a direct current to a measured inductance winding, synchronously monitoring the temperature, and multiplying a pre-measured direct current resistance value by a direct current value to obtain a direct current loss power value. The direct current is applied to the inductance winding, the temperature is monitored synchronously, the direct-current loss power is obtained by combining the direct-current resistance value and the current value, the temperature curve in the initial stage is extracted, the temperature rise rate is calculated, and therefore the winding heat capacity parameter is obtained, loss measurement can be closely associated with thermal response, and the measurement accuracy is improved. Introduction of a heat capacity factor is added in loss calculation, dynamic characteristics of a winding material on a thermodynamic level can be reflected, instantaneous current with load step change is applied after an inductor is cooled, an instantaneous loss power curve is generated by collecting a voltage sequence and a current sequence at the same time, and loss calculation is not limited to average value or steady state measurement any more.

The invention discloses a water energy accumulator and ground source heat pump combined control method, relates to the technical field of building environment and equipment engineering, accurately captures a time sequence change rule of a building cold load based on the load prediction capability of a time convolution network, overcomes the defect that a traditional method is insufficient in response to sudden fluctuation, and improves the control efficiency. The system can plan an energy storage strategy in advance; an electricity price-load change rate sensitivity index is introduced, and through an adaptive weight adjustment mechanism, economic operation and load tracking requirements are dynamically balanced, so that strategy stiffness caused by fixed priorities is avoided, and the utilization efficiency of time-of-use electricity price signals is remarkably improved; according to the joint optimization design of the mixed integer linear programming model, the equipment operation constraint and the cost target are comprehensively considered, the collaborative decision of the energy accumulator charging and discharging strategy and the heat pump frequency setting is realized, and the direct energy supply dependence in the midday high electricity price period is effectively reduced.

The invention relates to the technical field of heat energy storage and heating, and provides a refrigeration and heating integrated system based on phase change heat storage and a control method, the refrigeration and heating integrated system comprises a solar heat collection module, a heat storage oil tank, a phase change heat storage module, an absorption refrigeration module, a heating and heat supplementing module and a multi-mode control module; the multi-mode control module is used for controlling the phase change heat storage module to store heat in a heating period in response to the valley electricity time; monitoring the temperature of a heat storage oil tank in response to the non-valley electricity time, switching a heat supply mode of the system based on a comparison result of the temperature of the heat storage oil tank and a set threshold value, and controlling the phase change heat storage module to store heat or driving the absorption type refrigeration module to refrigerate in response to triggering of a user cold load demand in a cold supply period; and in response to the situation that the user cold load demand is not triggered, the heating and heat supplementing module is controlled to supplement heat to the phase change heat storage module. By integrating solar heat collection, phase change heat storage and valley electricity heat compensation strategies, efficient utilization and multi-source cooperative energy supply of clean energy are achieved.

The embodiment of the invention relates to the technical field of refrigeration control, and discloses a self-adaptive load refrigerating unit energy-saving operation method which comprises the following steps: acquiring a to-be-refrigerated space area, and determining an initial division area of the to-be-refrigerated space area; controlling and generating initial control parameters of each refrigerating unit according to the regional refrigeration demand information so as to perform refrigeration operation on the initially divided regions; matching the activity intensity information of each initial division area with a set condition, and if not, generating refrigeration adjustment information according to a matching result of the activity intensity information of the corresponding initial division area and the set condition; and generating equipment control parameters of each refrigerating unit according to the refrigerating adjustment information and the regional refrigerating requirements so as to perform refrigerating adjustment on the refrigerating units. The refrigerating unit provided by the embodiment of the invention can respond to the cold load change caused by factors such as personnel activities in the space in real time. The operating parameters of the refrigerating unit can be accurately adjusted in real time according to the load change, so that the refrigerating system operates more stably.

The invention discloses a data center dynamic air-conditioning load rapid calculation method, which comprises the following steps of: 1, summarizing data center cold load influence factors as an input condition of a calculation model; 2, constructing a standardized data center reference model based on building energy consumption simulation software; 3, based on the building geometrical characteristics and thermal performance of the target data center, correcting the enclosing structure load of the reference model by adopting an area correction method, and constructing an enclosing structure load rapid calculation model; 4, automatically resetting an internal heat source load calculation result, and constructing an internal heat source load rapid calculation model; 5, correcting the fresh air load of the reference model by adopting a volume correction method based on the geometric characteristics of the target data center building, and constructing a fresh air load rapid calculation model; and step 6, forming a target data center dynamic air-conditioning load rapid calculation method, and obtaining a hourly cooling load prediction result required for covering the whole year or a design stage.

The invention relates to the technical field of ground source heat pump control, in particular to an intelligent cooperative control system for a ground source heat pump system and building energy management. The method comprises the steps that a data collecting and preprocessing unit collects multiple types of data in real time and preprocesses the data to form system state vectors; the load and power generation prediction unit predicts future cooling and heating load and photovoltaic power generation power of the building through a machine learning regression model and a time sequence prediction model; the operation optimization unit generates an optimal operation strategy of the ground source heat pump based on a depth deterministic strategy gradient algorithm; and the multi-source energy coordinated control unit realizes multi-device coordinated control through multi-target mixed integer linear programming. Through combination of prediction data and an optimization algorithm, a dynamic matching relation between load fluctuation and energy supply is fully considered, and the problems of soil heat imbalance and unstable comprehensive energy efficiency ratio of the ground source heat pump system in a traditional fixed parameter operation mode are solved.

The invention discloses an industrial circulating water evaporation water consumption water-saving control method based on artificial intelligence. According to the method, an efficient air cooling device is additionally arranged on the basis of an existing open type cooling tower circulating water system, and a dry-wet combined cooling system is formed through integration of pipelines and valves. The system collects the temperature, flow, pressure, energy consumption and environmental parameters of each node in real time, and after data fusion and preprocessing, the cooling load and evaporation water consumption are calculated based on thermodynamic equilibrium and hydraulic equilibrium models. A multi-objective optimization model which takes minimization of evaporation water consumption as a main part and minimization of energy consumption as an auxiliary part is adopted, an artificial intelligence algorithm is used for real-time solving, optimal control parameters such as flow distribution, fan rotating speed and valve opening degree are output, and dynamic adjustment of the cooling system is achieved. The system continuously corrects and optimizes model parameters through a closed-loop feedback and self-learning mechanism, ensures that the water supply temperature reaches the standard, the evaporation water consumption is minimum and the energy consumption is optimal, and remarkably improves the water saving and operation efficiency of the industrial circulating water system.

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 relates to the technical field of energy management, and discloses a thermal management system energy consumption optimization method based on a lightweight neural network, which comprises the following steps: step 1, collecting operation data and environment information of an energy storage system, constructing a unified feature input set, performing timestamp alignment and normalization processing on the collected operation data and environment information, and obtaining a feature input set; periodic time features are extracted, and a structured feature matrix used for model input is formed; step 2, based on the structured feature matrix, inputting the structured feature matrix into a long-term trend prediction model to predict future charge and discharge starting time and deadline; and step 3, extracting a prediction result of the long-term trend prediction model. The dynamic cooling regulation and control strategy based on the real-time operation data and the environment parameters is adopted, the temperature prediction model and the cooling load demand analysis mechanism are established, the operation state of the cooling equipment is adjusted according to needs, and the technical effects of flexible regulation and control according to actual needs and reduction of overall energy consumption are achieved.

The invention relates to the technical field of air conditioning refrigerating systems, in particular to a chilled water cascade energy-saving control method and a chilled water cascade energy-saving control system for a chilled water cold storage system, and the method comprises the following steps: calculating low-temperature load cold storage capacity, medium-temperature load cold storage capacity and high-temperature load cold storage capacity of a cold storage container; according to a local power grid policy, determining peak, flat and valley periods; determining low-temperature, medium-temperature and high-temperature load cooling time; collecting hourly cold loads and corresponding meteorological parameters of low-temperature, medium-temperature and high-temperature chilled water when the refrigerating system operates; training to obtain a model; according to meteorological parameters of hourly weather forecast of the next day; summing the predicted high-temperature, medium-temperature and low-temperature hourly loads of the next day in the peak period of the power grid; a low-temperature load cold release strategy is formulated; formulating a medium-temperature load cold release strategy; a high-temperature load cold release strategy is formulated; and according to the determined low-temperature, medium-temperature and high-temperature cold release time, opening and closing of each valve of the system are controlled, and each cold release process is completed.

The invention discloses an optimal control method for metering a cold and heat storage air conditioning system in a laboratory, and relates to the technical field of optimal control, and the method comprises the following steps: predicting hourly cold load and heat load in a future preset period, and generating hourly load prediction data; obtaining time-of-use electricity price information, and generating electricity price time period division data; formulating an energy storage strategy based on hourly load prediction data and electricity price time division data; the method specifically comprises the steps that in the valley electricity price period, when it is predicted that a load demand exists in the future peak electricity price period, a cold and heat source module is controlled to operate, energy is stored in a cold and heat storage module till the rated capacity is reached or the valley period is ended, and the temperature and humidity in a laboratory are maintained within a first set range through a tail end processing module in the energy storage period; and formulating an energy release and conventional operation strategy based on hourly load prediction data, electricity price time division data and the real-time energy storage state of the cold storage and heat storage module. The method has the effect of improving the optimization control efficiency.

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 a multi-modal information fusion load prediction method based on a cross attention mechanism. The method is suitable for an integrated energy station energy efficiency optimization scene. The method comprises the following steps: firstly, collecting and preprocessing multi-source time sequence data such as meteorological texts, satellite cloud pictures and temperature and humidity, and extracting high-dimensional semantic representations through texts, images and a time sequence encoder respectively; secondly, setting a modal significance pre-gating mechanism, and adaptively adjusting the importance of each modal feature; a time lag compensation cross attention module is introduced to realize time alignment and semantic association among multiple modes; and finally, realizing unified representation of weather, space and time information through a multi-modal fusion network, and outputting a cooling load prediction result. According to the method, the dynamic change rule of the cooling load of the comprehensive energy station can be accurately described under the complex meteorological condition, the prediction precision and stability are remarkably improved, and technical support is provided for cold machine starting and stopping, energy storage scheduling and demand response optimization of the comprehensive energy station.

The invention relates to the technical field of refrigerating machine room load prediction, in particular to a cooling load prediction regulation and control method for an air conditioner refrigerating machine room, which comprises the following steps of: constructing and training a cooling load prediction model through a machine learning algorithm based on machine room air conditioner historical data; inputting the processed environment parameters and the target temperature into a model, outputting corresponding machine room air conditioner parameters, then judging whether the machine room air conditioner parameters are set to be qualified or not according to a thermal radiation difference value, and judging reasons according to a water hammer wave propagation speed difference value when the machine room air conditioner parameters are not set to be qualified; and then working parameters of the water pump, the electric control valve and the cooling tower are corrected according to corresponding reasons, and notifications are sent out. Through cold load prediction, rapid fault diagnosis and intelligent correction, the problems of poor temperature control precision, complex fault processing and the like of an existing air conditioner refrigerating machine room are solved, intelligent management of the air conditioner refrigerating machine room is achieved, and reliable temperature control guarantee is provided for places such as machine rooms with strict temperature requirements.

The invention provides a demand response strategy determination method and device for a central air conditioner, equipment and a medium, and the method comprises the steps that a cooling load prediction value needed by a tail end is determined based on a first weather prediction parameter corresponding to a demand response time period; based on the mass of water stored in the water supply pipe, the mass of water stored in the water return pipe, the water supply temperature upper and lower limits of the water supply pipe and the water return temperature upper and lower limits of the water return pipe, the system cold storage capacity is determined; based on the cold load predicted value and the system cold storage capacity, the power consumption of the refrigerating system is determined; determining a response capacity predicted value based on the cold load predicted value, the system cold storage capacity and the refrigerating system power consumption; determining a target demand response strategy based on the response capacity predicted value, the bid-winning response capacity issued by the organizer, the electric power price and the first demand response strategy; the target demand response strategy is the demand response strategy with the maximum income. According to the invention, the evaluation response capability is improved, and the rationality, accuracy and income of the demand response strategy are further improved.

The invention provides a dynamic optimization control method for a building chilled water storage central air-conditioning system, which comprises the following steps of: predicting a historical cold load of the building air-conditioning system through a pre-trained cold load prediction model, and calculating a cold load prediction error rate and uncertainty distribution; performing power consumption prediction by using the power consumption prediction model; sampling the cold load prediction error rate in the next 24 hours by using a Monte Carlo method; and in combination with the initial predicted cooling load and the dynamic time-of-use electricity price, with the goal of minimizing the daily electricity consumption cost, an optimal control signal of the hourly cold charging or discharging capacity of the chilled water storage device in the next 24 hours is obtained through a particle swarm algorithm. According to the method, quantitative modeling is carried out on random distribution of the error rate of cold load prediction, and the control signal of the cold charging or discharging capacity of the chilled water storage device is optimized through the Monte Carlo method and the particle swarm optimization, so that the optimal control robustness under the condition that the cold load prediction is uncertain is improved; and the operation cost of the chilled water storage central air-conditioning system under the dynamic electricity price is saved.

The invention provides a space refrigeration load regulation type virtual power plant regulation characteristic and boundary modeling method. The method comprises the following steps: constructing a space refrigeration load monomer discrete physical model; constructing a load polymer model by integrating a consistency control algorithm and the load monomer discrete physical model; using statistics to represent load polymer model parameters and curve parameters; calculating polymer model parameters based on the load equipment monomer parameter statistics; based on the difference between the basic model time scale and the actual scheduling time scale, updating the multi-time scale aggregation model parameters; and based on the updated multi-time scale aggregation model, calculating an adjustment boundary by comprehensively considering power constraint and energy constraint, and quantitatively evaluating the maximum up-regulation power and the maximum down-regulation power of the virtual power plant under the specified adjustment duration. According to the method, the adjustment characteristics and the adjustment boundary of the space refrigeration type load virtual power plant are accurately described, a parameter dynamic updating mechanism is designed for different scheduling cycles, and the time scale adaptability of the model is enhanced.

The invention relates to the technical field of cold supply load prediction, and discloses a cold supply system load prediction method based on artificial intelligence, and the method comprises the steps: obtaining a meteorological parameter, a time parameter and a date type parameter of a to-be-predicted day; the obtained data is preprocessed; respectively calculating a meteorological similarity factor, a time similarity factor and a date type similarity factor of the to-be-predicted day and each historical day; further calculating the comprehensive similarity between each historical day and the to-be-predicted day; selecting a plurality of historical days of which the comprehensive similarity is greater than a preset similarity threshold as similar days, and setting upper and lower limits of deviation according to the total load data of the similar days to eliminate redundant similar days; and calculating and outputting an hourly cold load prediction value of the to-be-predicted day by utilizing a regression type support vector machine model and combining the hourly load data of the similar days and the comprehensive similarity of the hourly load data. According to the invention, through multi-dimensional similarity quantitative analysis and artificial intelligence processing, high precision, high robustness and universality of load prediction of the cooling system are realized.

The invention belongs to the field of polymorphic energy storage aggregation scheduling control, and discloses a collaborative aggregation regulation and control method and system based on house building polymorphic composite energy storage, and the method comprises the steps: collecting the internal temperature and outdoor temperature of a machine room at a certain moment, and building an equivalent thermal parameter model based on temperature change; introducing an energy reference zero point, and converting the equivalent thermal parameter model based on temperature change into a dimensionless energy storage state model; according to the dimensionless energy storage state model, the energy change in the virtual standard machine room is expressed, and a standardized control strategy is output based on the energy change in the virtual standard machine room; machine rooms are grouped through a clustering algorithm to form machine room clusters with similar thermal characteristics, and each machine room cluster is subjected to intra-cluster unified control through a standardized control strategy. According to the invention, the cooling load of each machine room can be accurately controlled through the regulation and control mode based on the heat storage state. The house can be equivalent to other polymorphic composite energy storage, has similar characteristics, provides a collaborative optimization method for composite energy storage with differentiated dynamic characteristics and storage duration, effectively reduces energy waste, optimizes load response of a power system, and improves energy utilization efficiency.

The invention discloses a data center multi-cold-source intelligent regulation and control method and system based on characteristic temperature prediction, and the method comprises the steps: building a machine room characteristic temperature model through an entropy method, and obtaining a machine room characteristic temperature value through calculation; establishing a machine room cooling load and characteristic temperature prediction model based on the characteristic temperature value and the historical operation data; constructing an energy consumption mathematical model of main energy consumption equipment of the refrigeration system; establishing a cost function taking cold energy supply and demand balance as a constraint condition; performing rolling optimization on the cost function by using a particle swarm optimization algorithm, and solving to obtain an optimal control sequence of the chilled water supply temperature and the chilled water flow; and the field control cabinet transmits a water supply temperature setting signal to the refrigerator control cabinet for execution, transmits a flow setting signal to the flow control valve for execution, and realizes automatic optimization regulation and control of the refrigeration system through real-time feedback correction. On the premise that the temperature of the data center machine room is stable, the energy consumption of the refrigerating system is remarkably reduced, and the operation efficiency and the intelligent level of the system are improved.

The invention relates to the technical field of intelligent optimization, in particular to a cooler load optimization algorithm of a central air-conditioning water chilling unit based on a large language model, which comprises the following steps of: extracting a cooling load lexical item through a word vector analysis scheduling request, calculating an offset sequence, identifying a load switching point by a sliding window and dividing regulation and control stages; a regulation and control instruction is generated based on TF-IDF screening equipment actions, target parameters are extracted according to a dependency syntax, conflict items are filtered to form a parameter chain, and pump frequency is calculated through linear mapping to generate an execution instruction. According to the method, a cold load offset sequence is dynamically generated through semantic analysis and word vector distance of a natural language scheduling request, a sliding window recognizes a switching point to precisely segment a regulation and control stage, a parameter chain is constructed in combination with co-occurrence frequency and dependency analysis to filter a conflict instruction, response precision and strategy matching are improved, implicit intention capture is enhanced, and the method is high in practicability. The data dependence and experience deviation are reduced, the multi-unit collaborative optimization safety is guaranteed, and the energy efficiency fluctuation risk is reduced.