The power distribution sector is undergoing a structural transformation as utilities seek to balance efficiency, reliability and long-term sustainability. Speaking at a recent Power Line conference, Prudhvitej Immadi, IAS, Chairman and Managing Director, Andhra Pradesh Eastern Power Distribution Company Limited (APEPDCL), outlined how the utility is leveraging technology and data-driven decision-making to strengthen power procurement, enhance network reliability and optimise costs, while remaining aligned with its sustainability objectives.
Serving nearly 7.2 million consumers with a peak demand of around 5,500 MW, APEPDCL has demonstrated consistent strong operational performance over the past four years. The utility has maintained a billing efficiency of 93-94 per cent, collection efficiency of 98-99 per cent, and aggregate technical and commercial losses at 6-7 per cent, reflecting strong performance for a public sector discom. To sustain these outcomes, APEPDCL has been advancing digital initiatives and renewable energy adoption to further improve reliability and cost efficiency.
AI/ML-based demand forecasting
APEPDCL is using artificial intelligence (AI) and machine learning (ML) to optimise power purchase costs by improving demand forecasting. The utility has co-developed two tools, one for short-term forecasting and power procurement and another for long-term forecasting and resource adequacy planning up to 2036.
In the short term, the energy portfolio management system (EPMS) supports real-time, day-ahead and week-ahead forecasting of up to 10-14 days. These forecasts are generated using past demand patterns, live load data and weather inputs collected from 274 weather stations across the state. Based on these forecasts, EPMS performs daily unit commitment to optimise power procurement by backing down high-cost generators when lower market prices are expected. The platform has been integrated with the Indian Energy Exchange, enabling direct bid submission in the day-ahead market. It also supports optimal bilateral trading through visibility of contracts on the Discovery of Efficient Electricity Price and Term-Ahead Market portals and power exchanges with states such as Haryana and Uttar Pradesh to balance deficits and surpluses. Over 155 days of operation, forecast errors have generally remained around 2 per cent, except during extreme weather events such as cyclones. Regulatory reporting requirements for short-term power purchases are also being built into the system.
For long-term planning, APEPDCL has developed an AI-based tool along with REInt AI, which is a custom made alternative to PLEXOS. The model uses 10 years of historical demand, gross domestic product, sectoral gross value added, population and weather data, among other inputs, to forecast demand and optimise capacity over the next decade. It aims to reduce reliance on costly short-term market purchases, which currently account for 10-15 per cent of demand. Projections indicate that, without new capacity addition, cumulative deficits could reach 48,000 MUs by FY 2036. The optimal mix over the next five years prioritises additional solar, wind and battery energy storage, followed by thermal capacity after FY 2030 to meet baseload requirements. Based on this mix, power purchase costs are expected to reduce by about 14 per cent by FY 2030.
SCADA-enabled unmanned substations
APEPDCL is implementing supervisory control and data acquisition (SCADA)-based unmanned substations in Visakhapatnam to improve reliability and reduce operating costs. Although SCADA was initially implemented in 28 substations in Visakhapatnam in 2017, its full potential could not be realised. This was primarily due to unreliable field equipment, such as circuit breakers, along with limited capacity building and insufficient training for remote operations. As a result, most substations continued to operate in manual mode.
From 2024 onwards, APEPDCL began systematically integrating more substations into the SCADA system and converting them into unmanned substations. While the initial roll-out faced challenges, these were gradually addressed. The first conversion took nearly three months, but the pace has since accelerated to four to five substations per month. Initially, field engineers were hesitant about remote operations, but resistance has eased with increased familiarity. So far, 42 substations have been made unmanned, and the plan is to extend this to all 110 substations in Visakhapatnam. Once fully integrated, the entire city’s power network is expected to be operated remotely through the SCADA control centre.
Unmanned substations have already delivered both financial and operational benefits. Eliminating on-site staffing has reduced manpower requirements, resulting in annual incremental savings in operation expenditure of about Rs 1.33 million per unmanned substation. More significantly, the initiative has led to marked improvements in service quality. Earlier, a 33 kV incoming feeder failure at a manually operated substation would result in power interruptions lasting 20-30 minutes. With SCADA-enabled remote visibility of feeder loads and system parameters, restoration time has been reduced to about 3-4 minutes. This has translated into a 56 per cent improvement in the system average interruption duration index (SAIDI) across the converted substations.
Digitalisation and advanced analytics
APEPDCL has undertaken major digital initiatives to improve network visibility and operational efficiency. A key initiative is the integration of geographic information system (GIS) with systems, applications and products in data processing (SAP) to create a digital twin of the power distribution network. Earlier, project estimation and execution relied on manual sketches, tape measurements and manual SAP entries, which led to inaccurate material estimates, poor visibility of network layouts, data duplication, delays and audit challenges. Asset records were often incomplete, as GIS mapping after execution was not mandatory.
To address this, APEPDCL’s in-house IT team developed and implemented a fully integrated GIS-SAP workflow. Field officers now conduct GPS-based GIS surveys using mobile applications to capture pole locations, line routes and material requirements. This data flows automatically into SAP, where estimates are generated without manual intervention. After work completion, a mandatory post-execution GIS survey captures exact asset locations, and billing is allowed only after verification. A web-based GIS platform enables officers to visually compare planned and executed layouts, improving traceability, accountability and cost control. Despite challenges related to system integration, data accuracy, connectivity in remote areas and user adoption, APEPDCL has achieved 100 per cent GIS-based infrastructure monitoring, reduced project turnaround time and strengthened governance.
Apart from this, APEPDCL has also established a data analytics unit to address revenue leakage and operational inefficiencies. The unit has analysed 18 months of billing and meter data to identify abnormal consumption patterns, including consumers with consistently narrow usage, repeated zero-consumption readings under incorrect meter statuses, and frequent meter status changes. These cases are flagged for field inspection. With the roll-out of smart meters, APEPDCL is now using advanced analytics to monitor consumer behaviour, power quality, feeder and transformer performance, reliability indices such as SAIDI and the system average interruption frequency index, remote disconnection and reconnection, and exception handling. Smart meter data also helps detect anomalies such as daytime streetlight usage and after-hours consumption in government offices.
Solarisation of SC-ST consumers
Like many states, Andhra Pradesh provides 200 units of free electricity to below poverty line (BPL) scheduled caste (SC) and scheduled tribe (ST) households, which results in an annual subsidy burden of around Rs 8 billion-Rs 9 billion. To address this, APEPDCL has adopted a utility-led aggregation model under the PM Surya Ghar: Muft Bijli Yojana scheme. The discom has been installing rooftop solar systems of up to 2 kWp for SC and ST households that have usable rooftop space.
While APEPDCL serves around 0.7 million subsidised consumers, only about 0.2 million have technically feasible roofs, enabling a planned solar capacity of about 400 MW. A typical 2 kWp rooftop system can generate about 200-240 units per month, while the average monthly consumption of BPL consumers is only 60-70 units. Under Andhra Pradesh’s virtual net metering regulations, the electricity generated from these rooftop solar systems is not adjusted only against the consumption of the individual households. Instead, the total solar generation is offset against the combined consumption of all subsidised consumers.
APEPDCL has completed the tendering process and awarded 400 MW of rooftop solar capacity. The contract includes a provision for five years of warranty and free operations and maintenance by the engineering, procurement and construction vendors. For households willing to provide access to their rooftops, the government also provides roof-lease payments.
This approach reverses a common discom problem where high-paying consumers migrate to solar while low-paying consumers remain. By solarising subsidised consumers instead, APEPDCL protects its revenue base and improves system efficiency. The discom also benefits through additional revenue from surplus energy exported at feed-in tariffs determined by the Andhra Pradesh Electricity Regulatory Commission. Over the 25-year project life, solar generation is expected to reduce power purchase costs by about Rs 46.8 billion and generate subsidy
savings of about Rs 29.83 billion for the Andhra Pradesh government.
Together, these initiatives position APEPDCL as a digital pioneer in the distribution sector. Its experience shows how data-driven planning, automation and targeted renewable deployment can strengthen utility finances, improve reliability, reduce subsidy burden and deliver measurable gains across power procurement, network operations and consumer services.
