System and method for assessing green facility performance

MYPI2025003346A0Undetermined Publication Date: 2024-08-17HITACHI LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
MYPI2025003346
Authority / Receiving Office
MY · MY
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-02-17
Publication Date
2024-08-17

AI Technical Summary

Technical Problem

Current green finance assessment systems face challenges in providing credible and up-to-date data for benchmarking green facility performance due to inconsistencies and subjectivity, making it difficult for investors to evaluate greenness and for capital seekers to access suitable green finance products.

Method used

A system and method for assessing green facility performance by generating and utilizing credible datasets through collecting information from green facilities, technology providers, and capital seekers, using performance prediction models and benchmark calculation models to provide standardized and consistent benchmarking results.

Benefits of technology

Ensures credible and effective prediction and benchmarking of green facility performance, helping investors identify preferred investments and capital seekers access discounted green finance, while ensuring the credibility of sustainable finance products.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure PI2025003346_DRAWING_001
    Figure PI2025003346_DRAWING_001
  • Figure PI2025003346_DRAWING_002
    Figure PI2025003346_DRAWING_002
  • Figure PI2025003346_DRAWING_003
    Figure PI2025003346_DRAWING_003
Patent Text Reader

Abstract

A method for assessing green facility performance comprising: generating a green feature dataset using operation information collected from at least one green facility, green feature information collected from at least one technology provider and green facility information collected from at least one capital seeker; and predicting a performance parameter of a proposed green facility using a performance prediction model based on inputting information of the proposed green facility and the generated green feature dataset for assessing the performance of the proposed green facility. FIG. 2A
Need to check novelty before this filing date? Find Prior Art

Description

SYSTEM AND METHOD FOR ASSESSING GREEN FACILITY PERFORMANCETECHNICAL FIELD

[0001] This disclosure relates to a method and a system for benchmarking / assessing green facility performance. The assessment result may be used for benchmarking.BACKGROUND

[0002] The following discussion of the background to the invention is intended to facilitate an understanding of the present invention only. It should be appreciated that the discussion is not an acknowledgement or admission that any of the material referred to was published, known or part of the common general knowledge of the person skilled in the art in any jurisdiction as at the priority date of the invention.

[0003] Following the adoption of Paris Agreement and Sustainable Development Goals (SDGs), green / sustainable finance has been identified to be essential in financing climate change actions.

[0004] There are some barriers constraining the growth of green finance. For capital seekers, it is difficult to define, select and verify eligible investment due to lack of credible data and methodology. For investors, it is difficult to evaluate a level of greenness based on capital seeker’s customized definition and selection criteria.

[0005] In addition, different green finance products may engage different consultants and external reviewers to assess the sustainability impacts. In some situations, a green finance product may include different consultants and external reviewers engaged at different stages of green finance, such as definition, selection, and verification stages. This may result in inconsistencies and subjectivity.

[0006] Existing energy efficiency rating program / software used by capital seekers to demonstrate sustainable performance includes Leadership in Energy and Environmental Design (LEED), Singapore’s Green Mark and IFC’s Excellence in Design for Greater Efficiencies (EDGE). These rating systems come with different rating schemes and make it difficult for investors to compare projects from different systems. None of these rating systems can attract all / majority of capital seekers because they have not integrated features and functions to support green finance. One of the key technical difficulties for these existingprograms to integrate with green finance is that they need to use more transparent and up to date information of green features and existing facilities to generate credible prediction and benchmarking results. For example, EDGE makes assumption of baseline and determines choice and qualifications of green features based on market studies and data collection conducted by multiple country-based institutions, and national / local building performance codes. In order to stay relevant and effective, EDGE needs to update the assumptions and green feature information as the market evolves. However, because of the lengthy and hierarchical data collection and processing process, the information is not transparent and unlikely to stay up to date as green technologies and green facility performance are evolving fast.

[0007] Therefore, there exists a need to develop a technical assessment system to standardize the impact and benchmark the performance of green facilities.SUMMARY

[0008] The present disclosure was conceptualized to provide a method and a system that generates and utilizes credible, and up-to-date datasets for prediction and benchmarking of green facilities, by collecting and processing green facility information from various parties, including, but not limited to, green facility, capital seeker (or capital seeker’s representatives, e.g., consultants), and green technology provider.

[0009] A technical solution is provided in the form of a system and a method for assessing green facility performance.

[0010] The method for assessing green facility performance comprises: generating a green feature dataset using operation information collected from at least one green facility, green feature information collected from at least one technology provider and green facility information collected from at least one capital seeker; and predicting a performance parameter of a proposed green facility using a performance prediction model based on inputting information of the proposed green facility and the generated green feature dataset into the performance prediction model, wherein the performance parameter is output from the performance prediction model for assessing the performance of the proposed green facility.

[0011] The method can further comprise: generating a benchmark dataset using the collected operation information, the collected green facility information and the generated green feature dataset; calculating at least one benchmark of the proposed green facility using a benchmark calculation model based on the information of the proposed green facility and thegenerated benchmark dataset; and comparing the predicted performance parameter of the proposed green facility with the calculated benchmark to obtain benchmarking results for assessing the performance of the proposed green facility.

[0012] The method can further comprise: recommending a green finance product to the capital seeker and / or recommending a green facility to an investor based on the obtained prediction and benchmarking results.

[0013] The method can further comprise: evaluating and selecting a green project to use proceeds and / or implement based on the obtained prediction and benchmarking results; and monitoring and verifying the use of proceeds.

[0014] The method can further comprise: verifying achieved performance of the proposed green facility, comprising: calculating at least one updated benchmark of the proposed green facility based on the updated information of the proposed green facility and the generated benchmark dataset; and comparing the calculated updated benchmark with the achieved performance of the proposed green facility.

[0015] The method can further comprise: determining benchmarking type based on Key Point Indicators, Sustainability Performance Targets, and / or project eligibility criteria determined in green finance definition; calculating the at least one benchmark using the performance prediction model based on historical performance data of existing facility, information of the existing facility and the information of the proposed green facility, if the benchmarking type is against itself; determining the at least one benchmark using the generated benchmark dataset and / or the benchmark calculation model based on the information of the proposed green facility, if the benchmarking type is not against itself; predicting the performance parameter of the proposed green facility using the performance prediction model based on the information of the proposed green facility, the existing facility performance data and the green feature dataset; and comparing the predicted performance parameter of the proposed green facility with the at least one benchmark to obtain benchmarking results.

[0016] The performance prediction model can be a system model (such as a simplified engineering calculation and a complex computer simulation model) and / or a machine learning based model.

[0017] In another aspect, the system for assessing green facility performance comprises: a green facility interface configured for collecting operation information from at least one green facility; a user interface configured to connect with one or more users; and a processorconnected to the green facility interface and the user interface, wherein the processor is configured to: generate green feature dataset using operation information collected from at least one green facility, green feature information collected from at least one technology provider and green facility information collected from at least one capital seeker; predict a performance parameter of a proposed green facility using a performance prediction model based on inputting information of the proposed green facility and the generated green feature dataset for assessing the performance of the proposed green facility.

[0018] The processor can be configured to: generate a benchmark dataset using the collected operation information, the collected green facility information and the generated green feature dataset; calculate at least one benchmark of the proposed green facility using a benchmark calculation model based on the information of the proposed green facility and the generated benchmark dataset; and compare the predicted performance parameter of the proposed green facility with the calculated benchmark to obtain benchmarking results for assessing the performance of the proposed green facility.

[0019] The system can further comprise a data storage configured to store data, the data comprising the operation information, the green feature information, the green facility information, the generated green feature dataset, the generated benchmark dataset and the prediction and benchmarking results.

[0020] The data storage can be centralized or distributed data storage system.

[0021] The data storage can be a blockchain.

[0022] The processor can be configured to: recommend a green finance product to the capital seeker and / or recommend a green facility to an investor based on the obtained prediction and benchmarking results.

[0023] The processor can be configured to: evaluate and select a green project to use proceeds and / or implement based on the obtained prediction and benchmarking results; and monitor and verify the use of proceeds.

[0024] The processor can be configured to verify achieved performance of the proposed green facility, wherein in the verification of achieved performance, the processor is further configured to: calculate at least one updated benchmark of the proposed green facility based on the updated information of the proposed green facility and the generated benchmark dataset; and compare the calculated updated benchmark with the achieved performance of the proposed green facility.

[0025] The processor can be configured to determine benchmarking type based on Key Point Indicators, Sustainability Performance Targets, and / or project eligibility criteria determined in green finance definition; calculate the at least one benchmark using the performance prediction model based on historical performance data of existing facility, information of the existing facility and the information of the proposed green facility, if the benchmarking type is against itself; determine at least one benchmark using the generated benchmark dataset and / or the benchmark calculation model based on the information of the proposed green facility, if the benchmarking type is not against itself; predict the performance parameter of the proposed green facility using the performance prediction model based on the information of the proposed green facility, the existing facility performance data and the green feature dataset; and compare the predicted performance parameter of the proposed green facility with the at least one benchmark to obtain benchmarking results.

[0026] The performance prediction model can be a system model (such as a simplified engineering calculation and a complex computer simulation model) and / or a machine learning based model.

[0027] The present disclosure provides a system which can ensure that a consistent, credible, and effective prediction and benchmarking method is used across different stages of different projects, conducted by different sustainability engineering professionals.

[0028] The common / standardized technical assessment system to quantify the impact and benchmark the performance of green facilities helps to ensure the credibility of sustainable finance product. In addition, it can help green investors to identify available investments they prefer and help capital seekers to access discounted green finance.

[0029] The dependent claims define some examples associated with the system and method, respectively.BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The present disclosure will be better understood with reference to the detailed description when considered in conjunction with the non-limiting examples and the accompanying drawings, in which:- FIG.l shows a system for benchmarking / assessing green facility performance in accordance with some embodiments of the present disclosure;- FIG.2A shows a system for benchmarking / assessing green facility performance in accordance with some embodiments of the present disclosure;- FIG.2B shows a system for benchmarking / assessing green facility performance in accordance with some embodiments of the present disclosure;- FIG.3A shows an example of blockchain implementation of the system for benchmarking / assessing green facility performance;- FIG.3B shows an example of the smart contract with contract name of “performance prediction”;- FIG.4 shows an integrated system combining the system for benchmarking / assessing green facility performance and a stock exchange system;- FIG.5A illustrates a method for benchmarking / assessing green facility performance in accordance with some embodiments of the present disclosure;- FIG.5B illustrates a method for benchmarking / assessing green facility performance in accordance with some embodiments of the present disclosure;- FIG.6 shows the overview of the prediction and benchmarking by a benchmarking and prediction unit;- FIG.7A shows the detailed prediction and benchmarking by a benchmarking and prediction unit;- FIG.7B shows an example of a performance prediction model;- FIG.8 shows a method for benchmarking / assessing green facility performance using an example of green bond;- FIG.9A shows the green feature dataset generation process by a green product assessment unit;- FIG. 9B shows an example of a green feature dataset;- FIG.10A shows the benchmark dataset generation process;- FIG. 10B shows an example of a benchmark dataset;- FIG. IOC shows an example of a benchmark calculation model;- FIG.11 shows the recommendation process by Financial Product Recommendation Unit, Green Finance Definition Recommendation Unit, Green Feature Recommendation Unit, Interest Recommendation Unit, and Property Value Prediction Unit;- FIG.12 shows the project selection (validation) process by validation unit;- FIG.13 shows the performance verification process by performance verification unit;- FIG.14 shows the calibrated benchmarking process by benchmarking and prediction unit;- FIG.15 shows the proceeds monitoring and verification process by proceeds monitoring and verification unit;- FIG.16 shows the green financial product report generation process by reporting unit;- FIG.17 shows the investor carbon impact report generation process by reporting unit and asset impact calculation unit;- FIG.18 shows an example of the project selection (validation), with blockchain implementation.DETAILED DESCRIPTION

[0031] The following detailed description refers to the accompanying drawings that show, by way of illustration, specific details and embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure. Other embodiments may be utilized and structural, and logical changes may be made without departing from the scope of the disclosure. The various embodiments are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments.

[0032] Embodiments described in the context of one of the systems or methods are analogously valid for the other systems or methods.

[0033] Features that are described in the context of an embodiment may correspondingly be applicable to the same or similar features in the other embodiments. Features that are described in the context of an embodiment may correspondingly be applicable to the other embodiments, even if not explicitly described in these other embodiments. Furthermore, additions and / or combinations and / or alternatives as described for a feature in the context of an embodiment may correspondingly be applicable to the same or similar feature in the other embodiments.

[0034] In the context of various embodiments, the articles “a”, “an” and “the” as used with regard to a feature or element include a reference to one or more of the features or elements.

[0035] As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items.

[0036] As used herein, the term “data” may be understood to include information in any suitable analog or digital form, for example, provided as a file, a portion of a file, a set of files, a signal or stream, a portion of a signal or stream, a set of signals or streams, and the like. The term data, however, is not limited to the aforementioned examples and may take various forms and represent any information as understood in the art.

[0037] As used herein, the term “processor” refers to, or forms part of, or include an Application Specific Integrated Circuit (ASIC); an electronic circuit; a combinational logic circuit; a field programmable gate array (FPGA) that executes code; other suitable hardware components that provide the described functionality; or a combination of some or all of the above, such as in a system-on-chip. The processor may include non-transitory computer readable medium such as memory (shared, dedicated, or group) that stores code executed by the processor.

[0038] FIGs.l, 2A and 2B show a schematic illustration of the system 100 for benchmarking / assessing green facility performance according to some embodiments of the present disclosure. The system 100 comprises a green facility interface 106, a user interface 107 and a processor 120 connected to the green facility interface 106 and the user interface 107. The green facility interface 106 is configured to connect with at least one green facility 105 and collect operation data from the at least one green facility 105. The user interface 107 is configured to connect with the users including at least one capital seeker 102, at least one investor 103, and at least one technology provider 104.

[0039] The green facility interface 106 can receive data (e.g., operation information of the green facility) automatically (e.g. via a PUSH / PULL API) from the green facility’s data collection and processing system (e.g., smart energy management system) via a cloud network. In some embodiments, the green facility interface 106 may be implemented representational state transfer application programming interface (REST API).

[0040] The system 100 can send and collect data from the users 102, 103, 104 via the user interface 107. The system 100 collects green facility information 102a from the capital seeker (e.g., green facility developer) 102 and sends information generated by the system 100 to the capital seeker 102. The green facility information 102a may include information about green project, applicant, green facility design and operation, use of proceeds, etc. The informationreceived by capital seeker 102 from system 100 includes information generated to facilitate decision making and activities of capital seeker 102, such as green finance definition recommendation, green finance product recommendation; green project evaluation and verification results, and reports. The system 100 collects green finance product information 103 a from the investor 103 and sending information generated by the system 100 to the investor 103. The green finance product information 103 a may include types of green finance product they offer or intend to invest in, the requirements of green finance product, etc. The information received by investor 103 from system 100 includes information generated to facilitate decision making and activities of investor 103, such as green facility recommendations, green project recommendations, property value prediction results, use of proceeds information, and reports. The system 100 collects green feature information 104a from the technology provider 104 and sends information generated by the system 100 to the technology provider 104. The green feature information 104a may include information about green product (e.g., product efficiencies and materials), green services (e.g., energy audit service information) and confirmation of use of proceeds when green product / service is provided to capital seeker 102. The information received by technology provider 104 from system 100 includes information generated to facilitate decision making and activities of technology provider 104, such as assessment and / or certification result of green technologies. In this green finance marketplace, capital flows from investor 103 to capital seeker 102 as investment, and from capital seeker 102 to technology provider 104 when green products and services are purchased. The user interface 107 can send and receive data via a cloud network. An example of user interface 107 is REST API. The user interface 107 may be reached from, e.g., a web application in browser.

[0041] The processor 120 is configured to benchmark / assess the green facility performance. The processor 120 can comprise multiple calculation units to support multiple functions and services of the platform. These calculation units include: a green product assessment unit lOlal to assess and / or certify green product, and generate and / or update green feature dataset, a benchmark dataset generation unit 101a2 to generate benchmark dataset, a prediction and benchmarking unit 101a3 to predict green facility performance and obtain at least one benchmark, a green finance definition recommendation unit 101a4 to recommend green product eligibility criteria, KPIs and SPTs,a financial product recommendation unit 101a5 to recommend green finance product to investors and capital seekers, a green feature recommendation unit 101a6 to recommend suitable green features (including products and services provided by technology provider) to capital seekers by using the prediction and benchmarking results and performing cost benefit analysis, an interest recommendation unit 101a7 to recommend interest of bond and loans to capital seeker and investor using statistical and / or machine learning method based on information such as project information, maturity, prevalent market interest rates, and similar green bond interest rates, a property value prediction unit 101a8 to predict the value of properties using methods, such as machine learning, based on data related to property value, such as property type, location, environmental impacts, etc., a validation unit 101a9 to validate and select green projects based on prediction and benchmarking results, a proceeds monitoring and verification unit lOlalO to monitor and verify use of proceeds based on green expenditure information from capital seekers and green technology providers, a performance verification unit 101 al l to verify the environmental impact of green facility based on operation data, an asset impact calculation unit 101al2 to calculate the impact of investor green investments based on the environmental impacts of the green investments, a reporting unit 10 lai 3 to generate reports on validation results, proceeds verification results, and environmental impact verification results.

[0042] The system 100 can further comprise a data storage 101b. The data storage 101b may be centralized or distributed data storage system, such as a blockchain. The data storage 101b also supports multiple functions and services of the system 100. The stored data may include operation information of the green facility, facility design information, green feature dataset, benchmark dataset, prediction and benchmarking result (including predicted performance, calculated at least one benchmark, and benchmarking results), KPI dataset, validation result, performance verification result, financial product information, predicted property value, recommended interest rate, records of proceeds, reports, and / or report templates.

[0043] FIG. 3A shows an example of blockchain implementation of the system 100 for benchmarking / assessing green facility performance. A full node 1710 is connected to green facility 105 via the green facility interface 106. The green facility interface 106 is configured to receive data automatically from the green facility 105’s data collection and processing system (e.g., smart energy management system) via cloud network. An example of the green facility interface 106 is REST API. The full node 1710 is also connected to different types of users, including capital seeker 102, investor 103 and technology provider 104, via a user interface 107. The user interface 107 is configured to send and receive data via a cloud network. An example of the user interface 107 is REST API. The user interface 107 may be reached from e.g., a web application in browser.

[0044] The blockchain network may contain other types of nodes that only have partial function of the full node 1710. For example, a light node stores and provides just the necessary data to accommodate daily activities or faster transactions. They are not involved in validating the blocks and just stores the block headers.

[0045] The full node 1710 can comprise transaction management 1710a, distributed ledger 1710b, smart contract 1710c, consensus management 1710d, security management 1710e, and replication management 1710f. The transaction management 1710a manages the process of transaction request, transaction receipt, and transaction validation through a consensus algorithm, transaction storage, and block creation. It also manages the execution of a smart contract. A transaction in this application can be, e.g., capital seeker committing to KPIs and SPTs, evaluation results generation for a green project, or verification of use of proceeds, etc. The consensus management 1710d defines how the network participants can reach a consensus so that a transaction is considered valid. There are three categories of consensus protocols: compute-intensive based consensus protocols, capability-based consensus protocols, and voting-based consensus protocols. The capacity-based and voting -based consensus protocols are recommended for the proposed solution. The distributed ledger 1710b stores the transactions, which is updated by the transaction management function 1710a and is synched among the nodes in the network by the replication management 1710f, which ensures consistency and availability of data by using a replication strategy. The security management 1710e is responsible for user authentication by using an encryption technique and for data privacy via a hashing technique.

[0046] The smart contracts 1710c are used to help generate transactions which can be subsequently distributed to every node in the network. In this application, the smart contract 1710c is used to realize the functions in the system 100 for defining, selecting, monitoring, reporting and verification of green finance. The smart contract 1710c sets out the rules of what activities each type of users can do and should do. It also sets out the rules to generate outputs for defining, selecting, monitoring, reporting and verification of green finance. The smart contract 1710c may be integrated with machine learning models to generate results. The smart contract 1710c may interact with data outside the blockchain network by technologies, such as Oracle. An example of the smart contract 1710c with contact name of “performance prediction” is shown in FIG.3B. To support the performance prediction process, multiple functions are defined, such as energy prediction function, emission_prediction function with respective variable names. Calculation logic is also defined to generate desired output of predicted energy and predicted emissions, etc. by executing calculations and calling defined functions in sequence.

[0047] The system 100 can be realized as a platform to provide services on defining, selecting, monitoring, reporting and verification of green finance for key stakeholders, such as capital seekers 102 and investors 103, of sustainable / green finance products including but not limited to green bond, green loan, sustainability bond, sustainability-linked bond, sustainability-linked loan. The system 100 can also be used by technology (product / service) providers 104 to demonstrate products and services to customers (e.g., capital seekers 102) in order to grow business.

[0048] Potential user of the system 100 may include:Capital seekers 102, such as green building developers, who may want to use the system 100 to demonstrate their green finance products and attract investments. This system 100 has the potential of significantly reducing their research, reporting and service time and cost.Organizational investors 103, such as banks, who may want to use the system 100 for ensuring sustainability impact of their green products.Individual investors 103, who may want to use the system 100 for green / sustainability investments while saving research cost.Policymakers such as government organizations, who may want to use the system 100 to regulate the green finance market.Technology (product / service) providers 104 to demonstrate products and services.

[0049] In addition, the system 100 can be used as a platform to facilitate carbon pricing, e.g., carbon tax and carbon trading, by providing functions for benchmarking, prediction and verification of carbon emissions of green facilities.

[0050] The system 100 can also be integrated in a larger system, which not only provides technical assessment for green finance projects but also manages investment and the flow of proceeds, such as stock exchanges. FIG. 4 shows an integrated system 1810 combining the system 100 and a stock exchange system 1820. The system 100 and the stock exchange system 1820 exchange information about financial transactions and the results generated by the system 100, and hence the integrated system 1810 is able to provide the users (capital seeker 102, investor 103, technology provider 104) with relevant information via the user interface 107. For example, the stock exchange system 1820 may update the system 100 on the change of the ownership of a green bond. The system 100 may then update the access control of green facility information due to the change in ownership.

[0051] FIG. 5A and 5B illustrate a method 200 for benchmarking / assessing green facility performance using the system 100 according to some embodiments of the present disclosure. In step 210, green feature dataset is generated using operation information collected from at least one green facility 105, green feature information collected from at least one technology provider 104 and green facility information collected from at least one capital seeker 102. The green feature information collected from at least one technology provider 104 may comprise information about green product (e.g., product efficiencies and materials), information of the green services (e.g., energy audit service information). The green facility information collected from the at least one capital seeker 102 may comprise information about the green project, green facility design and operation. For example, the collected green facility information can be facility characteristics, system specifications and green features, historical performance data of existing facilities).

[0052] In step 220, benchmark dataset is generated using operation data collected from at least one green facility, green facility information collected from at least one capital seeker 102 and green feature dataset generated in step 210. In step 230, a performance parameter of a proposed green facility is predicted using a performance prediction model based on inputting information of the proposed green facility and the generated green feature dataset into the performance prediction model, wherein the performance parameter is output from theperformance prediction model for assessing the performance of the proposed green facility. The information of the proposed green facility can comprise facility characteristics, system specifications and green features of the proposed green facility. At least one benchmark of the proposed green facility is calculated using a benchmark calculation model based on the information of the proposed green facility and the generated benchmark dataset. The predicted performance parameter of the proposed green facility and the calculated at least one benchmark are compared to obtain benchmarking results for assessing the performance of the proposed green facility. In step 240, a green finance product can be recommended to the capital seeker and / or a green facility can be recommended to an investor based on the obtained prediction and benchmarking results. Recommendations are made to capital seeker 102 and / or investor 103, based on prediction and benchmarking results obtained in step 230, for green finance definition, i.e., eligibility criteria of green projects or activities (below used “projects” to represent both projects and activities) for proceeds-based model (e.g., green bond and green loan), and Key Point Indicators (KPIs) and Sustainability Performance Targets (SPTs) for performance-based model (e.g., sustainability-linked bond and sustainability-linked loans). In step 250, green projects are evaluated and selected to use proceeds and / or implement based on the prediction and benchmarking results obtained in step 230. In step 260, for proceeds-based model, the use of proceeds is monitored and verified. In step 270, the achieved performance of the proposed green facility is verified based on prediction and benchmarking results obtained in step 230 using green facility operation data. For verifying the achieved performance of the proposed green facility, at least one updated benchmark of the proposed green facility is calculated based on the updated information of the proposed green facility and the generated benchmark dataset, and the calculated updated benchmark is compared with the achieved performance of the proposed green facility. The achieved performance can be performance achieved by the proposed green facility after the completion of the green project. In step 280, reports, including green finance product report and investor carbon impact report, are generated.

[0053] FIG. 6 shows the prediction and benchmarking process (step 230) by a prediction and benchmarking unit 101a3 according to some embodiments of the present disclosure. In step 310, an information (e.g. facility charatoristices, system specifications and green features, historical performance data of existing facilites) of a proposed green facility is obtained from at least one capital seeker 102. In step 320, at least one benchmark are calculated based on the obtained information of the proposed green facility and the generated benchmark dataset. Instep 330, a performance parameter of the proposed green facility is predicted based on the information of the proposed green facility and the generated green feature dataset. In step 340, the calculated at least one benchmark and the predicted performance parameter of the proposed green facility are compared to obtain the benchmarking results.

[0054] FIG. 7 shows the prediction and benchmarking process (step 230) by a prediction and benchmarking unit according to some embodiments of the present disclosure. In step 410, benchmarking type is determined based on the KPIs, SPTs, and / or project eligibility criteria determined in the green finance definition process. Example of benchmarking types are:• Compare against itself over time, (applicable to existing facility only);• Compare against statistics of similar facilities;• Compare against prediction model generated benchmarks, which may consider facility’s characteristics, baseline system efficiencies, schedules, etc.

[0055] In step 420, the benchmarking type is checked if it is “against itself’. In step 430a, if the benchmarking type is “against itself ’, the historical performance data of existing facility is processed and used together with information on existing and proposed new facility characteristics (e.g., space types and area, schedules), to calculate the “business-as-usual” performance parameter using the performance prediction model. The calculated “business-as- usual” performance parameter will be used as the at least one benchmark. The “business-as- usual” performance means performance with the historical / existing system efficiency but proposed new facility usage information, such as schedule, space types and area.

[0056] The method used to calculate the “business-as-usual” performance could be based on the performance prediction model, e.g., using system modeling and / or machine learning approach. The system modeling approach could be ranging from simplified engineering calculation method based on the physics of the system (usually low accuracy but easy) to complex computer simulation models (usually high accuracy but resource intensive), e.g. EnergyPlus and IES VE. Machine learning approach could be used to make predictions with relatively high accuracy and low resources. The machine learning approach uses relevent data and machine learning algorithms to generate and validate models, which can be used to predict the green facilities’ performance.

[0057] Information of facility characteristics (e.g. building type, air-conditioning area), system specifications (e.g. lighting efficacy) and green features (e.g. smart lighting control), and green feature dataset (which provids green feature’s effects on performance, e.g. percentage of energy savings of smart lighting control product) can be used as input of the performance prediction model. The performance prediction model generates the predicted performance parameter (e.g. Energy Use Intensity of a green building) based on the input information. FIG.7B shows an example of a performance prediction model. In the performance prediction model as shown in FIG. 7B, the building type can be office, air-conditioning area can be 50%, the lighting efficacy can be 160 Im / W, the green features can be smart lighting control, and the predicted Energy Use Intensity (EUI) can be 50 kWh / m2.yr.

[0058] In step 430b, if the benchmarking type is not “against itself’, the at least one “non- against-self’ benchmark are determined using the generated benchmark dataset and / or the benchmark calculation model based on the information of the proposed green facility including proposed facility characteristics (e.g. space types and area, schedules). In some embodiment, both “against itself’ and “non-against-itself ’ benchmarking method may be applied depending on capital seeker’s committed definition.

[0059] In step 440, the performance parameter of the proposed green facility is predicted using the performance prediction model based on the information of the proposed green facility, including proposed facility characteristics (e.g., space types and area, schedules), proposed system specifications and green features, existing facility performance data (for existing facility only), and the green feature dataset. The performance parameter of the proposed green facility may be user proposed or system generated when making recommendations, e.g. from green feature recommendation unit 101a6. The performance data of existing facilities may be collected from loT platforms (e.g. smart energy management system), utility companies and other available sources. The performance data collected from existing facilities is saved in data storage and may be used to generate the benchmark dataset and assess green product performance in the green feature dataset generation (green product assessment and certification).

[0060] In step 450, the predicted performance parameter of the proposed green facility is compared with the at least one benchmark generated from 430a and / or 430b to obtain the benchmarking results.

[0061] FIG. 8 shows the method 200 for benchmarking / assessing green facility performance using an example of green bond, according to some embodiments.

[0062] In step 510, after receiving capital seeker’s green finance project request, a new green finance project is created and capital seeker is required to input basic information about the green finance project, which may include but not limited to key applicant information (e.g., identity, company information, etc.) and key project information (e.g., project name, project type, location, amount of proceeds required, etc.).

[0063] In step 520, recommendations are made to facilitate decision making of capital seekers based on key project information. The recommendations may include but not limited to suitable green finance product, eligibility criteria of green projects, KPIs, SPTs, green features, etc., based on a green finance product dataset. The recommendation of eligibility criteria of green projects, KPIs, SPTs, and green features are based on the obtained prediction and benchmarking results.

[0064] In step 530, capital seeker’s selection of green finance product and commitments on eligibility criteria of projects or KPIs and SPTs are received.

[0065] In step 540, information of the green finance project is displayed and / or recommended to investors based on investor’s preference and predicted green property value, which is generated by a property value prediction unit using methods such as machine learning, based on datasets related to property value. Thereafter, investor’s agreement on investment of green finance project is obtained.

[0066] In step 550, green facility information (e.g., design and operation information) is collected from capital seeker, manually via e.g., web-based portal and / or automatically via, e.g., loT platform. The performance parameter of a proposed green facility is predicted and the green project is validated, using the obtained prediction and benchmarking results, based on the information of the proposed green facility, the generated green feature dataset and the generated benchmark dataset to obtain validation results.

[0067] In step 560, the use of proceeds is monitored using green expenditure information and proofs of the green expenditure, e.g., tax invoice, photos / videos of products / services installed, collected from the capital seeker. Image / video recognition techniques may be implemented for analyzing product / service implementation. The use of proceeds is verified based on confirmation of green expenditures collected from technology provider to obtain proceeds verification results.

[0068] In step 570, environmental impacts are verified using the prediction and benchmarking results based on the operation information collected from green facility after the green facility is built / upgraded, to obtain environmental impact verification results.

[0069] In step 580, green finance report is generated periodically or when requested, based on the obtained validation results, the obtained proceeds verification results, and the obtained environmental impact verification results, to support validation reporting, proceeds verification reporting, and performance verification reporting, respectively.

[0070] In step 590, investor carbon impact report is generated periodically or when requested, based on the investor’s identity and investor’s assets / green investments information, such as the green investments’ environmental impacts.

[0071] In other embodiments, the sequence and users of steps 510, 520, 530, 540 and 550 may be changed / skipped to adapt to different type of green finance product, such as green loan. For instance, in step 510, instead of letting capital seeker create a green finance project of green bond, investors, such as banks, may create a green loan scheme. In step 540, instead of recommending green bond products to investors, the created green loan scheme is recommended to capital seekers. In addition, depending on the model of green finance, steps 560 and 570 may be skipped. For proceeds-based model, the step 570 can be optional. For performance-based model, the step 560 can be optional.

[0072] FIG.9A shows the green feature dataset generation process (step 210) by the green product assessment unit lOlal. The green feature dataset generation process also serves as green product assessment and certification service.

[0073] A green feature dataset may include a name of each product, green feature type that the product belongs to, efficiency of the product, and other characteristics related to the green feature. Note that some green feature may not need to have a respective product, e.g., design of nature ventilation for green buildings. FIG. 9B shows an example of a green feature dataset.

[0074] In step 710, product information is received from technology provider, who wants to assess, demonstrate, and / or certify their green product. Green feature dataset is updated based on the received product information, which may include information about raw material, manufacturing, use and end of life.

[0075] In step 720, product performance is assessed using statistical method, machine learning method and / or the performance prediction model illustrated above, based on preinstallation and post-installation performance data of the facilities which have the specificproduct installed, and other information which may affect the assessment of efficiency, such as weather data. The assessment result (e.g., verified product efficiency and life cycle emission) will be added or updated in the green feature dataset.

[0076] In step 730, assessment result is checked against the green product criteria. If the criteria are met, the green product can be certified, and the certificate may be sent to the applicant in step 740. If the criteria are not met, the applicant may be notified on the results in step 750.

[0077] FIG.10A shows the benchmark dataset generation process (step 220). FIG. 10B shows an example of a benchmark dataset. FIG. 10C shows an example of a benchmark calculation model. Benchmark may be obtained based on overall facility type (e.g., building types), or sub-systems of facility (e.g., space types within a building, system types belong to a building, such as lighting system). For each of the benchmark type, a best performance value, a typical / median performance value, and / or a performance value of a certain percentile, etc., may be generated to use as at least one benchmark. For each of the benchmark type, a condition information may be added to define where and how the data can be applied, such as, only applicable to certain cities.

[0078] In some embodiments, a benchmark calculation model may be used to generate at least one benchmark for a green facility. Information, such as building type, space type, and air-conditioning area, may be input into the benchmark calculation model to generate at least one benchmark, such as best, typical performance, etc. The benchmark calculation model uses the same methodology as the performance prediction model, except that the input of the benchmark calculation model are benchmark values of sub-system, such as best / typical efficiency of an air-conditioning system.

[0079] In step 810, relevant data for benchmark dataset generation is collected. These data may include existing facility performance dataset, existing facility design dataset, and green feature dataset. In step 820, data is processed and / or cleaned to prepare for benchmark dataset generation. In step 830, benchmark dataset and / or benchmark calculation model is generated using statistical methods and / or machine learning method. In step 840, the new / updated benchmark dataset and benchmark calculation model is saved.

[0080] FIG.11 shows the recommendation process (steps 240, 520) by financial product recommendation unit 101a5, green finance definition recommendation unit 101a4, green feature recommendation unit 101a6, interest recommendation unit 101a7, and property valueprediction unit 101a8. In step 910, user information and project information are received. User information can comprise information collected from the capital seeker 102, the investor 103, and / or technology provider 104. In step 920, suitable financial product is identified based on the user and project information, and the green finance product dataset. Green finance product dataset can include different types of available green finance products, such as green bond, sustainability linked bonds, green loans, sustainability linked loans. The bonds will need capital seeker to determine their definitions. The loans have been defined by investors, and suitable loans will be identified and recommended to capital seekers. Step 920 may be skipped if the user has already decided on the green product type. In step 930, depending on the recommended / chosen types of the green finance product, KPIs, SPTs and / or eligibility criteria is identified using the obtained prediction and benchmarking results based on the project information, KPI dataset (which defines the KPIs of different project types), and benchmark dataset. In step 940, suitable green features are identified, and cost and benefit analysis are performed by the green feature recommendation unit 101a6 based on the project information, green feature dataset and predictions made by the prediction and benchmarking unit 101a3. In step 950, the recommended interest rate of green finance product, e.g., green bond, are generated based on the project information and interest rate dataset, which includes the interest rates of existing financial products in the market. In step 960, recommendations from steps 920 to 950 are sent to user and user is required to make selections / decisions to define the green finance product. In step 970, user’s selections / decisions are received and saved in data storage 101b as financial product information.

[0081] FIG. 11 shows the recommendation process of green bond defined by capital seekers 102. However, depending on the type of user, some steps may be skipped and / or changed. For example, if the user is an investor, such as a bank, who wants to define a green loan scheme, step 940 may be skipped for the investor because it will be the green loan applicant, i.e., capital seeker, receiving the recommendations of green feature, cost benefit analysis and predicted results in step 940.

[0082] FIG. 12 shows the project selection (validation) process (steps 250, 550) by validation unit 101a9. In step 1010, project information including facility characteristics (e.g., space types and area, schedules), system specifications and green features, and historical performance data for existing facility, and information of the proposed green facility is received from capital seeker. Based on the received project information, benchmark type determined bygreen finance product definition, benchmark dataset, and green feature dataset, the prediction and benchmarking unit 101a3 predicts the performance parameter of the proposed green facility performance using performance prediction model and performs benchmarking in step 1020. In step 1030, the eligibility of the proposed project is checked against the determined KPIs and SPTs, or defined eligibility criteria. If the project is eligible to use green proceeds and / or suitable to be implemented, the project will be labelled as “eligible” in the database and user will be notified in step 1040. If the project is not eligible, additional green features will be recommended by the green feature recommendation unit 101a6 in step 1050 for user to revise project design and resubmit the project validation application.

[0083] FIG. 13 shows the performance verification process (step 270) by performance verification unit 101 al l.

[0084] In step 1110, capital seeker’s updates on facility characteristics (e.g., space types and area, schedules), system specifications, green features, and facility performance data are received after project completion.

[0085] In step 1120, based on the updated information, benchmark dataset and green feature dataset, calibrated benchmarking (explained in the next figure) is performed to benchmark the achieved green facility performance based on the actual green facility design and operation. The achieved green facility performance is performance achieved by the proposed green facility after the completion of the green project.

[0086] In step 1130, the achieved green facility performance is checked against the determined KPIs and SPTs, or defined eligibility criteria.

[0087] In step 1140, if the project meets the requirement, the project will be marked as “verified” in the database. In some embodiments, the individual green features / products used by the green facility can be evaluated and marked as “verified”. In some embodiments, the respective proceeds used for the green feature and / or the green facility can be marked as “performance verified”. Performance may be energy savings, carbon emission reduction, etc. Performance may be on whole facility basis or on individual green feature basis. For example, a daylighting product may increase the indoor illuminance level and hence reduce the operation lighting power density (LPD). If the reduction of operation LPD is verified based on power meter data of lighting system, the performance of the said daylighting product is considered verified, and the proceeds used on the daylighting product can be marked as “performance verified.”

[0088] In step 1150, if the project does not meet the requirements, actions, such as examining the correctness of the implemented green features, will be required for capital seekers to take to achieve the expected performance of green facility.

[0089] FIG.14 shows the calibrated benchmarking process (step 1120) by prediction and benchmarking unit 101a3. In step 1210, benchmarking type is determined based on the KPIs, SPTs, and / or project eligibility criteria determined in the green finance definition process. In step 1220, the benchmarking type is checked if it is against itself.

[0090] In step 1230a, if the benchmarking type is “against itself’, the historical and / or new performance data of existing facility is processed and used, together with information on existing and implemeneted facility characteristics (e.g., space types and area, schedules), to recalculate the “business-as-usual” performance, which will be used as benchmark. The “business-as-usual” performance means performance with the historical / existing system efficiency but implemented new facility usage information, such as schedule, space types and area. The performance prediction model for re-calculating the “business-as-usual” performance should use the same methodology as illustrated above.

[0091] In step 1230b, if the benchmarking type is not “against itself’, the at least one “non- against-self’ benchmark is re-calculated using benchmark dataset and / or the benchmark calculation model based on the implemented facility characteristics (e.g. space types and area, schedules) and / or new performance data. In some embodiment, both “against itself’ and “non- against-itself ’ benchmarking method may be applied depending on capital seeker’s committed definition.

[0092] In step 1240, the achieved green facility performance is determined by processing the new performance data, and implemented facility characteristics. In steps 1230a, 1230b and 1240, the historical / existing and / or new performance data of the green facilities may be collected through loT platforms (e.g. smart energy management system), utility companies and other available sources. The data collected from the green facilities is saved in data storage 101b, which will be used to generate benchmark dataset in step 220 and assess green product performance in the green feature dataset generation (green product assessment and certification) process (step 210).

[0093] In step 1250, the achieved green facility performance from 1240 is compared with the re-calculated at least one benchmark from 1230a and / or 1230b to generate the calibrated benchmarking results.

[0094] FIG. 15 shows the proceeds monitoring and verification process 260 by proceeds monitoring and verification unit lOlalO.

[0095] In step 1310, capital seeker’s update on expenditure, which may include proof of expenditure and / or proof of implementation of green features, is received. In step 1320, request is sent for the respective product / service provider to confirm the supply of product / service to the capital seeker and / or the receipt of payment from the capital seeker from the step 1310. In step 1330, the product / service provider’s confirmation is received. In step 1340, the capital seeker’s claim is compared with the product / service provider’s confirmation. If the two match, the use of proceeds will be marked as verified in step 1350. If the two do not match, the capital seeker will be requested to resubmit the claim.

[0096] FIG.16 shows the green financial product report generation process (steps 280, 580) by reporting unit 101al3. In step 1410, report type, such as validation report, proceeds verification report, and performance verification report, is obtained based on user’s or system’s request, such as, to support periodical reporting function. Respective template is selected based on the report type. In step 1420, respective information required by the template is obtained from the data storage unit 101b. The required information may include validation information, performance verification information, proceeds and verification information. Report is generated based on the obtained information, report type and report template. In step 1430, the generated report is sent to respective users.

[0097] FIG.17 shows the investor carbon impact report generation process (steps 280, 590) by reporting unit 101al3 and asset impact calculation unit 101al2. In step 1510, investor’s identity is obtained and all the related assets’ information of the investor in the corresponding period is retrieved from data storage 101b. In step 1520, assets’ overall performance and emission in the corresponding period is calculated by asset impact calculation unit 101al2, based on the expected and / or achieved green facility performance and emission information of each investment. In step 1530, report is generated based on the calculation result of the step 1520 and sent to the respective user.

[0098] While the system 100 can be implemented on a conventional centralized data storage and processing system, it can also be implemented in a distributed data storage and processing system, e.g., blockchain network system. FIG.18 shows an example of the project selection (validation) (step 250), with blockchain implementation. In step 1610, a blockchain node receives capital seeker’s input on project information from a user interface 107. The capitalseeker’s input may include facility characteristics (e.g., space types and area, schedules), system specifications and green features, and historical performance data (for existing facility only). In step 1620, this input is used, together with data stored in the blockchain network, including benchmark dataset, green feature dataset, determined KPIs and SPTs, and / or defined green project criteria, to predict green facility performance, perform benchmarking and check eligibility by executing smart contract in blockchain node. In step 1630, the node performs data hashing and encryption and broadcasts transaction data (including input data, predicted results, prediction and benchmarking results and eligibility results) and signature to the network. In step 1640, validator nodes validate transaction and broadcast it to block generators. In step 1650, block generator is selected based on consensus and it verifies the validated transactions, groups them into a block and broadcasts the block to the network. In step 1660, validator nodes verify the validity of the block. In step 1670, new block is added in the blockchain network and can be viewed by relevant users via the user interface 107.

[0099] Furthermore, one or more of the steps of a method described herein may be performed in parallel rather than sequentially.

[0100] While the disclosure has been particularly shown and described with reference to specific embodiments, it should be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the present disclosure as defined by the appended claims. The scope of the present disclosure is thus indicated by the appended claims and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced.

Claims

CLAIMS1. A method for assessing green facility performance comprising: generating a green feature dataset using operation information collected from at least one green facility, green feature information collected from at least one technology provider and green facility information collected from at least one capital seeker; and predicting a performance parameter of a proposed green facility using a performance prediction model based on inputting information of the proposed green facility and the generated green feature dataset into the performance prediction model, wherein the performance parameter is output from the performance prediction model for assessing the performance of the proposed green facility.

2. The method of claim 1, further comprising: generating a benchmark dataset using the collected operation information, the collected green facility information and the generated green feature dataset; calculating at least one benchmark of the proposed green facility using a benchmark calculation model based on the information of the proposed green facility and the generated benchmark dataset; and comparing the predicted performance parameter of the proposed green facility with the calculated benchmark to obtain benchmarking results for assessing the performance of the proposed green facility.

3. The method of claim 1, further comprising: recommending a green finance product to the capital seeker and / or recommending a green facility to an investor based on the obtained prediction and benchmarking results.

4. The method of claim 1, further comprising: evaluating and selecting a green project to use proceeds and / or implement based on the obtained prediction and benchmarking results; and monitoring and verifying the use of proceeds.

5. The method of claim 2, further comprising: verifying achieved performance of the proposed green facility, comprising: calculating at least one updated benchmark of the proposed green facility based on the updated information of the proposed green facility and the generated benchmark dataset; and comparing the calculated updated benchmark with the achieved performance of the proposed green facility.

6. The method of claim 2, further comprising: determining benchmarking type based on Key Point Indicators, Sustainability Performance Targets, and / or project eligibility criteria determined in green finance definition; calculating the at least one benchmark using the performance prediction model based on historical performance data of existing facility, information of the existing facility and the information of the proposed green facility, if the benchmarking type is against itself; determining the at least one benchmark using the generated benchmark dataset and / or the benchmark calculation model based on the information of the proposed green facility, if the benchmarking type is not against itself; predicting the performance parameter of the proposed green facility using the performance prediction model based on the information of the proposed green facility, the historical performance data of the existing facility and the green feature dataset; and comparing the predicted performance parameter of the proposed green facility with the at least one benchmark to obtain benchmarking results.

7. The method of claim 1, wherein the performance prediction model is a simplified engineering calculation, a complex computer simulation model, or a machine learning based model.

8. A system for assessing green facility performance comprising:a green facility interface configured for collecting operation information from at least one green facility; a user interface configured to connect with one or more users; and a processor connected to the green facility interface and the user interface, wherein the processor is configured to: generate green feature dataset using operation information collected from at least one green facility, green feature information collected from at least one technology provider and green facility information collected from at least one capital seeker; predict a performance parameter of a proposed green facility using a performance prediction model based on inputting information of the proposed green facility and the generated green feature dataset for assessing the performance of the proposed green facility.

9. The system of claim 8, wherein the processor is configured to: generate a benchmark dataset using the collected operation information, the collected green facility information and the generated green feature dataset; calculate at least one benchmark of the proposed green facility using a benchmark calculation model based on the information of the proposed green facility and the generated benchmark dataset; and compare the predicted performance parameter of the proposed green facility with the calculated benchmark to obtain benchmarking results for assessing the performance of the proposed green facility.

10. The system of claim 9, further comprising a data storage configured to store data, the data comprising the operation information, the green feature information, the green facility information, the generated green feature dataset, the generated benchmark dataset and the prediction and benchmarking results.

11. The system of claim 10, wherein the data storage is centralized or distributed data storage system.

12. The system of claim 11, wherein the data storage is a blockchain.

13. The system of claim 9, wherein the processor is configured to: recommend a green finance product to the capital seeker and / or recommend a green facility to an investor based on the obtained prediction and benchmarking results.

14. The system of claim 9, wherein the processor is configured to: evaluate and select a green project to use proceeds and / or implement based on the obtained prediction and benchmarking results; and monitor and verify the use of proceeds.

15. The system of claim 9, wherein the processor is configured to: verify achieved performance of the proposed green facility, wherein in the verification of achieved performance, the processor is further configured to: calculate at least one updated benchmark of the proposed green facility based on the updated information of the proposed green facility and the generated benchmark dataset; and compare the calculated updated benchmark with the achieved performance of the proposed green facility.

16. The system of claim 9, wherein the processor is configured to: determine benchmarking type based on Key Point Indicators, Sustainability Performance Targets, and / or project eligibility criteria determined in green finance definition; calculate the at least one benchmark using the performance prediction model based on historical performance data of existing facility, information of the existing facility and the information of the proposed green facility, if the benchmarking type is against itself; determine at least one benchmark using the generated benchmark dataset and / or the benchmark calculation model based on the information of the proposed green facility, if the benchmarking type is not against itself;predict the performance parameter of the proposed green facility using the performance prediction model based on the information of the proposed green facility, the historical performance data of the existing facility and the green feature dataset; and compare the predicted performance parameter of the proposed green facility with the at least one benchmark to obtain the benchmarking results.

17. The system of claim 8, wherein the performance prediction model is a simplified engineering calculation, a complex computer simulation model, or a machine learning based model.