Taipower Smart Grid

Taipower has installed AMI meters for large (all extra-high-voltage and high-voltage) customers in 2013. The load structure of Taiwan’s power system is mainly composed of large-scale (high-voltage) industrial and commercial users, and their power consumption is about 60%. For small (low-voltage) customers, Taipower plans to install up to two hundred thousand, one million and three million AMI meters in 2018, 2020 and 2024 respectively. The schedule was approved by Executive Yuan in September 2016.

There are more than 14 million electricity customers supplied by Taipower. Even if finishing 3 million small customers’ AMI deployment in 2024, the penetration of AMI users is only about 21%. However, the power usage of large-scale customers with installed AMI are about 60%, after finishing 3 million customers’ AMI deployment in 2024, Taipower could handle around 81% of power usage information of Taiwan’s power system.

Deployment Schedule

Taipower conducted low voltage AMI smart meter deployment via separate tendering of meter, communication, and meter data management system. The current status of deployment is as shown below:

Meter
The procurement of 200,000 units of low voltage AMI smart meters was completed in 2017. The accumulated installation of 230 thousand smart meters was completed in 2018 and 600 thousand smart meters in 2023. Last year Taipower has deployed about 2.7 million smart meters for commercial and residential customers, which occupies about 79.2% of all customers’ power usage in Taiwan.
Communication module
The procurement of 200 thousand units of communication modules was completed in July 2018. The installation of 230 thousand communication modules was completed in March 2019. In 2023, we have installed about 2.7 million communication modules. The total system connection rate between MDMS and smart meter is over 97%.
Metering data management system
Metering data management system (MDMS) has been on-line system in 2020, and it can successfully collect and manage 1.8 million meters data.

The buildings in Taiwan are mostly apartments. In order to cope with the bottle neck of communication, the innovative pluggable dual-communication module has been launched. Route A can access the data or events from metering unit through P1 interface and communicate with head-end server through P3 interface (wide-area communication network). Each head-ends will send information to MDMS in Taipower through P6 interface. Two types of communication module (wireless Wi-SUN and wired PLC) have been applied to deal with different on-site situations. The modules are optional according to the communication quality test of concentrator.

On the other hand, Route B has been kept for offering an on-demand channel for customer to access meter data directly, which can open the probability of HEMS (Home Energy Management System) application. Wireless or wired type of communication module is also optional due to customers’ switchboard. Smart meter in AMI is not only a point of common coupling between customers and utilities, but also brings in new data applications through Route B (P2/P4).

MDMS(Meter Data Management System)

Along with the schedule of AMI deployment, Taipower is planning to construct a MDMS (Meter Data Management System) which can accommodate with some millions of customers’ AMI data.

MDMS is extremely important in the architecture of AMI. It should be able to offer processed data, which is consistent and can be directly used by other applications, to make sure the applications can be integrated on the same basis. The repetitive data pre-processing work (ETL, Extract-Transform-Load) can also be avoided.

MDMS in Taipower is about to complete in 2020, which will lead to various applications on demand/distribution side, that accommodates renewable energy penetration and enable electricity trading for future deregulated market in Taiwan. Big-data applications focusing on meter data will also make great contribution on promoting sensational customer service and innovative business model.

AMI Application Blueprint

Since the completion of the high-voltage AMI deployment in 2013, Taipower has developed related applications along with the historical data. However, Taipower is a regulated (vertical-integrated) utility, and the applications are usually separated by different departments. Through a comprehensive survey, that coordinates the stakeholders in Taipower, we proposed a blueprint of AMI data applications as the attached A3 map.

The architecture focuses on 6 major topics, including AMI infrastructure, system improvement and refinement, refinement of power distribution, refinement of power sales business, refinement of demand side management and data integration application analysis. Each topic contains many subjects and items, which are categorized into three responsible groups to manage and control the schedules.

According to different icons, we can identify if the subject is for high-voltage customers or low-voltage;on-going or still planning, and the main stakeholders, utility, industry or customers.

Applications in Different Domains

The contents of AMI applications in 6 topics mentioned before (AMI infrastructure, system improvement and refinement, refinement of power distribution, refinement of power sales business, refinement of demand side management and data integration application analysis) are briefly explained as follows. The expected benefit s are attached at the bottom of this page (Related Pictures).

AMI Infrastructure

Installation of AMI infrastructure, including smart meter design, solution of communication portfolio, and the construction of MDMS, brings meter production, communication services, IT technology and related sectors a huge bussiness opportunity to join. These applications will profit to industries. Furthermore, the meter data can be useful for Taipower’s grid operation, also can help customers to underdtand their electricity consumption behaviors to do further applications.

This topic contains auxiliary service(operating reserve) provided by demand response; and the estimation of the generation of PV and wind turbine, etc. Monitoring distribution system to achieve direct/wheeling power supply metering and measuring is also included.

The main idea of this topic is about improving the safety and efficiency of distribution system, to strengthen distributed generation integration and relevant issues. For example, promoting the construction of distribution automation to help data collecting and monitoring. Using these data, predictive maintenance can be done for distributed transformers; also, the outage can be isolated by the automation system. On the other hand, the system operator can be quickly informed by smart meter event and check where the outage is located on distributed GIS system to shorten the restoration time. Combined feeder network data with MDMS, via the implement of storage system, makes renewable energy be perfectly integrated within distribution network to enable future as the VPP (Virtual Power Plant) application.

Based on AMI deployment, with remote communication, human resource can be saved from on-site meter data reading or restoration. AMI data can be visualized for customers to check their power usage information on-line, and the unusual power usage alarm can be provided. Big data and AI (Artificial Intelligence) technology, such as clustering, can be applied for business applications, help business department to do diversified management, offer better services to customers, increase customers’ satisfaction.

Relevant subjects of the structure including energy-saving services, such as promotion of ESCO (Energy Services Company) and HEMS; demand side management enhancement, using AMI data with big data analysis, assist DR programs and rate design applications.

Data Integration Application Analysis

Data integration should be generally managed by MDMS. While the data source is consistent, the applications are ensured being developed on the same basis. Data application can be applied to domains like grid operation, billing business, asset management and maintenance, etc. Combined with other external data or open data, such as weather information or economic indexes, the analytics application would be diversified, efficient and valuable.

Achievements

The section below will highlight some key subjects/items of research and development group as examples to illustrate the application contents of the plan. Every other application subject/item within the framework have been assigned to responsible departments for the administration, which are regularly tracked and controlled.

CEMS (Community Energy Management System)

The introduction of CEMS can help to manage the energy usage inside a community effectively. With measuring and monitoring the instant power load for every responsible area, the system can calculate reduced demand potential immediately within the community to support overall load management and operation.

In 2016, the Taiwan Power Research Institute of Taipower implemented the CEMS in the Shulin Campus. They can measure and record the power consumption of 12 buildings in the campus and manage the buildings in groups according to their electricity usage characteristics.

To achieve power usage visualization inside the campus, the project created a Web-based EMS operation interface for administers to manage power usage details and arrange settings. Besides, the project also set several In-Building Display (IBD) and App on mobile device for the users working there. Once the VEN (Virtual End Node, client of openADR2.0) receives a new DR event compatible with OpenADR 2.0 specification, the event detail information (start time, duration, effected items…) will be shown on IBDs to let users know.

The figure on the left shows one of the IBDs in Shulin Campus. The dashboard shows aggregated key information, such as instant total power demand, customer baseline load (CBL), the load and usage pattern in individual building, last auto-DR event result analysis and environment information (temperature, humidity…).

BEMS (Building Energy Management System)

CEMS focuses on the electricity balance management among buildings in the community, while BEMS focuses on the power management inside each building.

With checking the electrical loops and equipment inventory in the building, measurement and control elements are installed to master the real-time electricity usage. Besides, with the participation in DR programs of Taipower, users can reduce the peak load and get further rewards.

To promote the concept of energy management from the company, TPRI implemented the BEMS in the buildings inside Taipower Fengshan Branch in 2017. Through the developed IBD and mobile APP, workers there can know power demand need in different areas at the same time. The figure on the right shows a Web-based BEMS operating interface, helping the administrator to understand the real-time and predictive power consumption of each floor in the building. In addition, the website also provides other functions like historical record inquiry, real-time environmental information in the building, DR schedule setting and equipment management to help the administrator manage the power usage in the building and preset the strategy for coming ADR events.

In response to the energy-saving policy, electricity demand side management is promoted to government agencies for high priority. Bureau of Standards, Metrology and Inspection (BSMI) and Bureau of Foreign Trade (BOFT) are chosen to implement building energy management service first to let the power usage inside the buildings visualized and reduce the peak loads with the ADR mechanism. The figure shows the IBD set in the hall of BSMI. The upper field presents the information about the following DR event (time, duration, reduced load request, countdown to launch) to remind the users to prepare for that. The left line chart shows instant demand record for the whole and air-conditioners, contracted capacity, user baseline CBL (five-day average). The right side shows the electricity usage of each building, demand reduction potential, building environmental parameters (temperature and humidity…) as a reference for on-site workers. When the administrator finds out that the power demand is very close to the contract capacity, he can also adjust the AC power manually on the web to avoid the excessive use penalty.

HEMS (Home Energy Management System)

HEMS assists home members to master the electricity use inside the home. With the communication network technology, integration of AMI and HEMS and connection with energy-saving household appliances, HEMS can provide instant power usage information, manage and control appliances by intelligent schedule, analyze the power usage status on smart home platform, perform demand response request and energy management service functions. Taipower had set up a demo-room in Taipower Taipei City branch in 2017 to present the “smart home” concept in future life. The picture shows residents can get the energy information inside home by the dashboard (In-Home Display, IHD) including status of home appliances, household electricity demand, ADR execution details, solar power generation and energy storage status.

The Energy Bureau of MOEA had selected 1,000 households as demo sites to test the suitable communication combinations between AMI and HEMS through route B in 2018. The figure shows The AMI reading data are directly transmitted to the meter gateway inside home through route B module of a smart meter. Inside the house, home appliance is operated through the TaiSEIA communication protocol with HEMS. With the data collected, there may be more value-added services such as IHD and cloud APP so that residents can realize the power consumption information easily. Further HEMS technology and value-added business model will be carried out in the coming years.

Analysis of Demand-Bidding Participants Performance

Demand-Bidding program is one of the most effective DR programs of Taipower. However, the load reduction or even the transfer affects the accuracy of load forecasting. The analysis was done as a reference to system operators, so the expected load reduction or transfer can be considered and identified. It also provides system operator with better understanding of DR management. The graph shows the transfer effect from DR participants’ performance. The x-axis shows 48-hours timeline. During the event (D-day 15-17), the load reduction is obvious while transferred to the early morning of both D-day and the next day.

Potential Load Reduction Quantification of DR programs

The effectiveness of DR is decided by participants’ performance. Taipower uses ML (Machine Learning) and AI (Artificial Intelligence) technologies to estimate the amount of potential participants’ load reduction, which can help us to find the most wanted customers. After taking the experience and modeling technologies from previous result, we develop this analysis to precisely identify target customers with their reducible load.

The targeted customers with their individual profiles such as industry, location, contracted capacity and predictive load, etc. the result has been visualized as a dashboard to facilitating DR apartment for precision marketing.

Industrial Parks Power Usage Profiling

A descriptive statistics analysis was done for the pilot project of chosen industrial parks, the above figure illustrates an analysis result of the amount of power usage and users of different industries. More detailed cross-profiling has also been done, which takes feeder information into account. The analytics procedure is expected to duplicate to other industrial parks for investigating precise industrial features and development trend. A visualization map of all industrial parks can be done if all the data and locations(borders) were clearly defined.

Non-Intrusive Appliance Load Monitoring (NIALM)

This project applies the advanced Artificial Intelligence (AI) based Machine Learning (ML) theory to develop the Non-Intrusive Appliance Load Monitoring (NIALM) model which uses the minute and 15 minutes interval based active and reactive power provided by smart meter as learning patterns. The frequently used appliances as air conditioner, lighting, refrigerator, electric water heater, dehumidifier, and fan are tested in the laboratory house for evaluating the performance of NIALM model. The F-Score achieves 83%, which outperforms the published performance.

The NIALM model was also evaluated in 30 residentials for testing air conditioner and lighting, the average of F-Score achieves 85%, which also outperforms the latest domestic published performance.

Home Care System for Aging in Place

We conducted seniors home care field demonstrations to learn seniors’ behavioral patterns by machine learning technique based on electricity consumption data recorded by Advanced Metering Infrastructure (AMI), including daily activities, sleeping, etc. With this information, we can pre-detect abnormal and comply preventive care.
We use Instrumental activities of daily living (IADLs), which are things you do every day to take care of yourself and your home, to measure the ability of a senior individual to live independently in a community which include housekeeping, cooking, sleeping, entertainment, and cleaning. We analyzed house energy usage data collected from smart meters, in which data collection interval is 15 minutes, to recognize energy consumption behaviors of households. The instrumental activities of one model household on December 29 in 2020 is illustrated below. We improve the accuracy of our method through analyzing residential electricity use questionnaires. Various electricity characteristics of different family residences are better understood.

Open Data Platform of Government and Taipower

As of May 4, 2024, Taipower has 186 Datasets available on the open data platform for downloading and use by the public. In accordance with the Ministry of Economic Affairs’ data openness promotion strategy and set goals, Taipower regularly takes stock of business data and evaluates the demand for external data from time to time on the basis of the three principles of non-openness, including personal data privacy, business secrets, and national social security. After structuring, de-identifying, and passing data quality checks, we will promote the diversification of data applications and their scope of application and open them to the public in open formats or APIs to create higher value in the electricity market together with the public.